To see the other types of publications on this topic, follow the link: Citation networks.
Dissertations / Theses on the topic 'Citation networks'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 dissertations / theses for your research on the topic 'Citation networks.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse dissertations / theses on a wide variety of disciplines and organise your bibliography correctly.
1
Leifeld, Philip. "Policy networks a citation analysis of the quantitative literature /." [S.l. : s.n.], 2007. http://nbn-resolving.de/urn:nbn:de:bsz:352-opus-26631.
Full text
2
Dunaiski, Marcel Paul. "Analysing ranking algorithms and publication trends on scholarly citation networks." Thesis, Stellenbosch : Stellenbosch University, 2014. http://hdl.handle.net/10019.1/96106.
Full textAbstract:
Thesis (MSc)--Stellenbosch University, 2014.ENGLISH ABSTRACT: Citation analysis is an important tool in the academic community. It can aid universities, funding bodies, and individual researchers to evaluate scientific work and direct resources appropriately. With the rapid growth of the scientific enterprise and the increase of online libraries that include citation analysis tools, the need for a systematic evaluation of these tools becomes more important. The research presented in this study deals with scientific research output, i.e., articles and citations, and how they can be used in bibliometrics to measure academic success. More specifically, this research analyses algorithms that rank academic entities such as articles, authors and journals to address the question of how well these algorithms can identify important and high-impact entities. A consistent mathematical formulation is developed on the basis of a categorisation of bibliometric measures such as the h-index, the Impact Factor for journals, and ranking algorithms based on Google’s PageRank. Furthermore, the theoretical properties of each algorithm are laid out. The ranking algorithms and bibliometric methods are computed on the Microsoft Academic Search citation database which contains 40 million papers and over 260 million citations that span across multiple academic disciplines. We evaluate the ranking algorithms by using a large test data set of papers and authors that won renowned prizes at numerous Computer Science conferences. The results show that using citation counts is, in general, the best ranking metric. However, for certain tasks, such as ranking important papers or identifying high-impact authors, algorithms based on PageRank perform better. As a secondary outcome of this research, publication trends across academic disciplines are analysed to show changes in publication behaviour over time and differences in publication patterns between disciplines.
AFRIKAANSE OPSOMMING: Sitasiesanalise is ’n belangrike instrument in die akademiese omgewing. Dit kan universiteite, befondsingsliggams en individuele navorsers help om wetenskaplike werk te evalueer en hulpbronne toepaslik toe te ken. Met die vinnige groei van wetenskaplike uitsette en die toename in aanlynbiblioteke wat sitasieanalise insluit, word die behoefte aan ’n sistematiese evaluering van hierdie gereedskap al hoe belangriker. Die navorsing in hierdie studie handel oor die uitsette van wetenskaplike navorsing, dit wil sê, artikels en sitasies, en hoe hulle gebruik kan word in bibliometriese studies om akademiese sukses te meet. Om meer spesifiek te wees, hierdie navorsing analiseer algoritmes wat akademiese entiteite soos artikels, outeers en journale gradeer. Dit wys hoe doeltreffend hierdie algoritmes belangrike en hoë-impak entiteite kan identifiseer. ’n Breedvoerige wiskundige formulering word ontwikkel uit ’n versameling van bibliometriese metodes soos byvoorbeeld die h-indeks, die Impak Faktor vir journaale en die rang-algoritmes gebaseer op Google se PageRank. Verder word die teoretiese eienskappe van elke algoritme uitgelê. Die rang-algoritmes en bibliometriese metodes gebruik die sitasiedatabasis van Microsoft Academic Search vir berekeninge. Dit bevat 40 miljoen artikels en meer as 260 miljoen sitasies, wat oor verskeie akademiese dissiplines strek. Ons gebruik ’n groot stel toetsdata van dokumente en outeers wat bekende pryse op talle rekenaarwetenskaplike konferensies gewen het om die rang-algoritmes te evalueer. Die resultate toon dat die gebruik van sitasietellings, in die algemeen, die beste rangmetode is. Vir sekere take, soos die gradeering van belangrike artikels, of die identifisering van hoë-impak outeers, presteer algoritmes wat op PageRank gebaseer is egter beter. ’n Sekondêre resultaat van hierdie navorsing is die ontleding van publikasie tendense in verskeie akademiese dissiplines om sodoende veranderinge in publikasie gedrag oor tyd aan te toon en ook die verskille in publikasie patrone uit verskillende dissiplines uit te wys.
3
Glötzl, Florentin, and Ernest Aigner. "Orthodox Core-Heterodox Periphery? Contrasting Citation Networks of Economics Departments in Vienna." Taylor & Francis, 2018. http://epub.wu.ac.at/6631/1/09538259.2018.pdf.
Full textAbstract:
The notion of an "orthodox core-heterodox periphery" structure and the extent of interdisciplinary links have been widely discussed, and partially investigated bibliometrically, within economic discourse. We extend this research by applying tools from social network analysis to citation data of three economics departments located in Vienna, two mainstream and one non-mainstream, to assess their relative citation patterns. We show that both mainstream economics departments follow the asserted core-periphery pattern and have a mono-disciplinary research focus, while the citation network of the non-mainstream department has a polycentric structure and is both more heterodox and interdisciplinary. These findings suggest that discussions about the future of heterodox economics should pay more attention to the organizational level and seek allies from other disciplines.
4
Meiklejohn, Luke S. "How to attribute credit if you must." Master's thesis, Faculty of Commerce, 2021. http://hdl.handle.net/11427/33802.
Full textAbstract:
Data ownership is of fundamental importance in the digital economy of today. Commercializing academic research, whilst maintaining ownership of it, is a task that can now be accomplished due to the strengths of blockchain technology, which allows data to be registered, made unique, and traced to its origins. We propose a blockchain use-case for licencing academic research, based off an academic project named UniCoin. In this thesis, we discuss how to fairly attribute credit between all sources of knowledge that contribute to new pieces of academic research, using citation network analysis and centrality measures. Katz centrality, in-degree centrality, and PageRank are three potentially useful centrality measures, with varying results: these are compared using case studies based on three papers co-authored by Andrei Shleifer. We use these centrality measures to guide how to fairly attribute credit, and thus how to distribute licencing revenues generated through UniCoin.
5
AbuRa'ed, Ahmed Ghassan Tawfiq. "Automatic generation of descriptive related work reports." Doctoral thesis, Universitat Pompeu Fabra, 2020. http://hdl.handle.net/10803/669975.
Full textAbstract:
A related work report is a section in a research paper which integrates key information from a list of related scientific papers providing context to the work being presented. Related work reports can either be descriptive or integrative. Integrative related work reports provide a high-level overview and critique of the scientific papers by comparing them with each other, providing fewer details of individual studies. Descriptive related work reports, instead, provide more in-depth information about each mentioned study providing information such as methods and results of the cited works.
In order to write a related work report, scientist have to identify, condense/summarize, and combine relevant information from different scientific papers. However, such task is complicated due to the available volume of scientific papers. In this context, the automatic generation of related work reports appears to be an important problem to tackle. The automatic generation of related work reports can be considered as an instance of the multi-document summarization problem where, given a list of scientific papers, the main objective is to automatically summarize those scientific papers and generate related work reports.
In order to study the problem of related work generation, we have developed a manually annotated, machine readable data-set of related work sections, cited papers (e.g. references) and sentences, together with an additional layer of papers citing the references. We have also investigated the relation between a citation context in a citing paper and the scientific paper it is citing so as to properly model cross-document relations and inform our summarization approach. Moreover, we have also investigated the identification of explicit and implicit citations to a given scientific paper which is an important task in several scientific text mining activities such as citation purpose identification, scientific opinion mining, and scientific summarization.
We present both extractive and abstractive methods to summarize a list of scientific papers by utilizing their citation network. The extractive approach follows three stages: scoring the sentences of the scientific papers based on their citation network, selecting sentences from each scientific paper to be mentioned in the related work report, and generating an organized related work report by grouping the sentences of the scientific papers that belong to the same topic together. On the other hand, the abstractive approach attempts to generate citation sentences to be included in a related work report, taking advantage of current sequence-to-sequence neural architectures and resources that we have created specifically for this task.
The thesis also presents and discusses automatic and manual evaluation of the generated related work reports showing the viability of the proposed approaches.La sección de trabajos relacionados de un artículo científico resume e integra información clave de una lista de documentos científicos relacionados con el trabajo que se presenta. Para redactar esta sección del artículo científico el autor debe identificar, condensar/resumir y combinar información relevante de diferentes artículos. Esta tarea es complicada debido al gran volumen disponible de artículos científicos. En este contexto, la generación automática de tales secciones es un problema importante a abordar. La generación automática de secciones de trabajo relacionados puede ser considerada como una instancia del problema de resumen de documentos múltiples donde, dada una lista de documentos científicos, el objetivo es resumir automáticamente esos documentos científicos y generar la sección de trabajos relacionados. Para estudiar este problema, hemos creado un corpus de secciones de trabajos relacionados anotado manualmente y procesado automáticamente. Asimismo, hemos investigado la relación entre las citaciones y el artículo científico que se cita para modelar adecuadamente las relaciones entre documentos y, así, informar nuestro método de resumen automático. Además, hemos investigado la identificación de citaciones implícitas a un artículo científico dado que es una tarea importante en varias actividades de minería de textos científicos. Presentamos métodos extractivos y abstractivos para resumir una lista de artículos científicos utilizando su red de citaciones. El enfoque extractivo sigue tres etapas: cálculo de la relevancia las oraciones de cada artículo en función de la red de citaciones, selección de oraciones de cada artículo científico para integrarlas en el resumen y generación de la sección de trabajos relacionados agrupando las oraciones por tema. Por otro lado, el enfoque abstractivo intenta generar citaciones para incluirlas en un resumen utilizando redes neuronales y recursos que hemos creado específicamente para esta tarea. La tesis también presenta y discute la evaluación automática y manual de los resúmenes generados automáticamente, demostrando la viabilidad de los enfoques propuestos.
Una secció d’antecedents o estat de l’art d’un articulo científic resumeix la informació clau d'una llista de documents científics relacionats amb el treball que es presenta. Per a redactar aquesta secció de l’article científic l’autor ha d’identificar, condensar / resumir i combinar informació rellevant de diferents articles. Aquesta activitat és complicada per causa del gran volum disponible d’articles científics. En aquest context, la generació automàtica d’aquestes seccions és un problema important a abordar. La generació automàtica d’antecedents o d’estat de l’art pot considerar-se com una instància del problema de resum de documents. Per estudiar aquest problema, es va crear un corpus de seccions d’estat de l’art d’articles científics manualment anotat i processat automàticament. Així mateix, es va investigar la relació entre citacions i l’article científic que es cita per modelar adequadament les relacions entre documents i, així, informar el nostre mètode de resum automàtic. A més, es va investigar la identificació de citacions implícites a un article científic que és un problema important en diverses activitats de mineria de textos científics. Presentem mètodes extractius i abstractius per resumir una llista d'articles científics utilitzant el conjunt de citacions de cada article. L’enfoc extractiu segueix tres etapes: càlcul de la rellevància de les oracions de cada article en funció de les seves citacions, selecció d’oracions de cada article científic per a integrar-les en el resum i generació de la secció de treballs relacionats agrupant les oracions per tema. Per un altre costat, l’enfoc abstractiu implementa la generació de citacions per a incloure-les en un resum que utilitza xarxes neuronals i recursos que hem creat específicament per a aquest tasca. La tesi també presenta i discuteix l'avaluació automàtica i el manual dels resums generats automàticament, demostrant la viabilitat dels mètodes proposats.
6
Alshareef, Abdulrhman M. "Academic Recommendation System Based on the Similarity Learning of the Citation Network Using Citation Impact." Thesis, Université d'Ottawa / University of Ottawa, 2019. http://hdl.handle.net/10393/39111.
Full textAbstract:
In today's significant and rapidly increasing amount of scientific publications, exploring recent studies in a given research area and building an effective scientific collaboration has become more challenging than any time before. Scientific production growth has been increasing the difficulties for identifying the most relevant papers to cite or to find an appropriate conference or journal to submit a paper to publish. As a result, authors and publishers rely on different analytical approaches in order to measure the relationship among the citation network. Different parameters have been used such as the impact factor, number of citations, co-citation to assess the impact of the produced research publication. However, using one assessing factor considers only one level of relationship exploration, since it does not reflect the effect of the other factors. In this thesis, we propose an approach to measure the Academic Citation Impact that will help to identify the impact of articles, authors, and venues at their extended nearby citation network. We combine the content similarity with the bibliometric indices to evaluate the citation impact of articles, authors, and venues in their surrounding citation network. Using the article metadata, we calculate the semantic similarity between any two articles in the extended network. Then we use the similarity score and bibliometric indices to evaluate the impact of the articles, authors, and venues among their extended nearby citation network.
Furthermore, we propose an academic recommendation model to identify the latent preferences among the citation network of the given article in order to expose the concealed connection between the academic objects (articles, authors, and venues) at the citation network of the given article. To reveal the degree of trust for collaboration between academic objects (articles, authors, and venues), we use the similarity learning to estimate the collaborative confidence score that represents the anticipation of a prospect relationship between the academic objects among a scientific community. We conducted an offline experiment to measure the accuracy of delivering personalized recommendations, based on the user’s selection preferences; real-world datasets were used. Our evaluation results show a potential improvement to the quality of the recommendation when compared to baseline recommendation algorithms that consider co-citation information.
7
Alfraidi, Hanadi Humoud A. "Interactive System for Scientific Publication Visualization and Similarity Measurement based on Citation Network." Thesis, Université d'Ottawa / University of Ottawa, 2015. http://hdl.handle.net/10393/33135.
Full textAbstract:
Online scientific publications are becoming more and more popular. The number of publications we can access almost instantaneously is rapidly increasing. This makes it more challenging for researchers to pursue a topic, review literature, track research history or follow research trends. Using online resources such as search engines and digital libraries is helpful to find scientific publications, however most of the time the user ends up with an overwhelming amount of linear results to go through.
This thesis proposes an alternative system, which takes advantage of citation/reference relations between publications. This demonstrates better insight of the hierarchy distribution of publications around a given topic. We also utilize information visualization techniques to represent the publications as a network. Our system is designed to automatically retrieve publications from Google Scholar and visualize them as a 2-dimensional graph representation using the citation relations. In this, the nodes represent the documents while the links represent the citation/reference relations between them.
Our visualization system provides a better view of publications, making it easier to identify the research flow, connect publications, and assess similarities/differences between them. It is an interactive web based system, which allows the users to get more information about any selected publication and calculate a similarity score between two selected publications.
Traditionally, similar documents are found using Natural Language Processing (NLP), which compares documents based on matching their contents. In the proposed method, similar documents are found using the citation/reference relations which are
iii
represented by the relationship that was originally inputted by the authors. We propose a new path based metric for measuring the similarity scores between any pair of publications. This is based on both the number of paths and the length of each path. More paths and shorter lengths increase the similarity score. We compare our similarity score results with another similarity score from Scurtu’s Document Similarity [1] that uses the NLP method. We then use the average of the similarity scores collected from 15 users as a ground truth to validate the efficiency of our method. The results indicate that our Citation Network approach yielded better scores than Scurtu’s approach.
8
Maier, Gunther, Alexander Kaufmann, and Michael Vyborny. "Is regional science a scientific discipline? Answers from a citation based Social Network Analysis." Institut für Regional- und Umweltwirtschaft, WU Vienna University of Economics and Business, 2008. http://epub.wu.ac.at/1226/1/document.pdf.
Full textAbstract:
From its very beginnings, regional science has been open to intellectual exchange with many other scientific disciplines. This has led to cross-fertilization, but also to problems concerning the intellectual identity of regional science. After half a century of history of the field, it is time to ask the question, whether or not regional science has developed into a scientific discipline in these decades. In this paper we use cross-citation data between 464 journals in different disciplines to answer this question. With this data set we attempt to find out, how strongly regional science journals are interconnected by citations as compared to their citation links to journals in neighbouring disciplines. We find that when we consider the raw citation data, regional science becomes fragmented with its journals tied to those from economics, geography, planning, etc. When we standardize the citation information to take into account size differences between journals, however, regional science appears to form a strong and well connected dscientific discipline.Series: SRE - Discussion Papers
9
Runelöv, Martin. "Finding seminal scientific publications with graph mining." Thesis, KTH, Skolan för datavetenskap och kommunikation (CSC), 2015. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-172382.
Full textAbstract:
We investigate the applicability of network analysis to the problem of finding seminal publications in scientific publishing. In particular, we focus on the network measures betweenness centrality, the so-called backbone graph, and the burstiness of citations. The metrics are evaluated using precision-related scores with respect to gold standards based on fellow programmes and manual annotation. Citation counts, PageRank, and random selection are used as baselines. We find that the backbone graph provides us with a way to possibly discover seminal publications with low citation count, and combining betweenness and burstiness gives results on par with citation count.I detta examensarbete undersöks det huruvida analys av citeringsgrafer kan användas för att finna betydelsefulla vetenskapliga publikationer. Framför allt studeras ”betweenness”-centralitet, den så kallade ”backbone”-grafen samt ”burstiness” av citeringar. Dessa mått utvärderas med hjälp av precisionsmått med avseende på guldstandarder baserade på ’fellow’-program samt via manuell annotering. Antal citeringar, PageRank, och slumpmässigt urval används som jämförelse. Resultaten visar att ”backbone”-grafen kan bidra till att eventuellt upptäcka betydelsefulla publikationer med ett lågt antal citeringar samt att en kombination av ”betweenness” och ”burstiness” ger resultat i nivå med de man får av att räkna antal citeringar.
10
Glötzl, Florentin, and Ernest Aigner. "Pluralism in the Market of Science? A citation network analysis of economic research at universities in Vienna." WU Vienna University of Economics and Business, 2015. http://epub.wu.ac.at/4730/1/EcolEcon_WorkingPaper_2015_5.pdf.
Full textAbstract:
Pluralism has become a central issue not only in the public discourse but also in heterodox economics, as the focus on impact factors and rankings based on citations continues to increase. This marketization of science has been an institutional vehicle for the economic mainstream to
promote its ideas. Citations thus have become a central currency in economics as a discipline. At the same time they allow to investigate patterns in the discourse. Analyzing articles published by the two major economics departments and the more interdisciplinary Department for
Socioeconomics in Vienna, this paper is novel in applying both bibliometric techniques and citation network analysis on the department level. We find that (1) Articles in heterodox journals strongly reference the economic mainstream, while the mainstream does not cite heterodox
journals, (2) Articles written by researchers of the Department of Socioeconomics cite more heterodox journals irrespective of whether they are published in mainstream or heterodox journals, (3) The economics departments display a citation network exhibiting a clear "mainstream core - heterodox periphery" structure, as Dobusch & Kapeller (2012b) suggest the overall discourse in economics to be, while the Department of Socioeconomics could be described as a plural though not pluralistic department with many distinct modules in the network , reflecting various disciplines, topics and schools of thought. (authors' abstract)Series: Ecological Economic Papers
11
Mead, Susan Virginia. "Identifying academic subcultures within higher education research : an examination of scholars' careers through author cocitation /." Diss., This resource online, 1993. http://scholar.lib.vt.edu/theses/available/etd-10242005-124106/.
Full text
12
Kim, Amy Chan Hyung. "Knowledge Structure in Sport Management: Bibliometric and Social Network Analyses." The Ohio State University, 2012. http://rave.ohiolink.edu/etdc/view?acc_num=osu1338378142.
Full text
13
Baldi, Stephane. "A network approach to the analysis of citation flows: A comparative study of two research areas in the natural and the social sciences /." The Ohio State University, 1997. http://rave.ohiolink.edu/etdc/view?acc_num=osu1487943610785938.
Full text
14
Romanello, Matteo. "From index locorum to citation network : an approach to the automatic extraction of canonical references and its applications to the study of classical texts." Thesis, King's College London (University of London), 2015. http://kclpure.kcl.ac.uk/portal/en/theses/from-index-locorum-to-citation-network-an-approavch-to-the-automatic-extraction-of-canonical-reeferences-and-its-applications-to-the-study-of-classical-texts(7c5af968-545b-48b9-9aad-108e25979fa0).html.
Full textAbstract:
My research focusses on the automatic extraction of canonical references from publications in Classics. Such references are the standard way of citing classical texts and are found in great numbers throughout monographs, journal articles and commentaries. In chapters 1 and 2 I argue for the importance of canonical citations and for the need to capture them automatically. Their importance and function is to signal text passages that are studied and discussed, often in relation to one another as can be seen in parallel passages found in modern commentaries. Scholars in the field have long been exploiting this kind of information by manually creating indexes of cited passages, the so-called indices locorum. However, the challenge we now face is find new ways of indexing and retrieving information contained in the growing volume of digital archives and libraries. Chapters 3 and 4 look at how this problem can be tackled by translating the extraction of canonical citations into a computationally solvable problem. The approach I developed consists of treating the extraction of such citations as a problem of named entity extraction. This problem can be solved with some degree of accuracy by applying and adapting methods of Natural Language Processing. In this part of the dissertation I discuss the implementation of this approach as a working prototype and an evaluation of its performance. Once canonical references have been extracted from texts, the web of relations between documents that they create can be represented as a network. This network can then be searched, manipulated, visualised and analysed in various ways. In chapter 5 I focus specifically on how this network can be leveraged to search through bodies of secondary literature. Finally in chapter 6 I discuss how my work opens up new research perspectives in terms of visualisation, analysis and the application of such automatically extracted citation networks.
15
Mendonça, Junior Moacir Lopes de. "Metodologia para análise de relevância de publicações através de rede de citações." Universidade Federal da Paraíba, 2015. http://tede.biblioteca.ufpb.br:8080/handle/tede/7849.
Full textAbstract:
Submitted by Viviane Lima da Cunha (viviane@biblioteca.ufpb.br) on 2016-02-16T10:51:10Z
No. of bitstreams: 1
arquivototal.pdf: 3174848 bytes, checksum: f060b5ac76aa0a5bf42f2a4e540f78ef (MD5)Made available in DSpace on 2016-02-16T10:51:10Z (GMT). No. of bitstreams: 1 arquivototal.pdf: 3174848 bytes, checksum: f060b5ac76aa0a5bf42f2a4e540f78ef (MD5) Previous issue date: 2015-02-13
Scientific research is defined as a set of activities that are aimed at the discovery of new knowledge relevant to the solution of existing problems. Scientific knowledge is not just the discovery of new facts and laws, but also in its publication. This is to obtain and communicate results through forms of scientific production. To understand the complex scientific production system numerous analytical techniques have been applied in digital repositories. These techniques aim to identify relevant scientific productions based on indicators. In this sense the present work aims to create a methodology that facilitate the identification of publications that are relevant to specific areas of expertise. For this we used three contexts, the first on the area of social network analysis, the second on the records of 20 years from webmedia and finally on area of embedded systems. As a source of study our software tool achieved several results for the areas of knowledge between them we can mention the development of publications for the most relevant publication vehicles and the classification of network communities.
A pesquisa científica é definida como um conjunto de atividades que têm por objetivo a descoberta de novos conhecimentos de interesse para a solução de problemas existentes. O conhecimento científico não se resume na descoberta de fatos e leis novas, mas também em sua publicação. Trata-se de obter e comunicar resultados através de formas de produção científica. Visando compreender o complexo sistema de produção científica inúmeras técnicas de análise vêm sendo aplicadas em repositórios digitais. Essas técnicas objetivam a identificação de produções cientificas relevantes baseadas em indicadores. Neste sentido o presente trabalho de pesquisa tem como objetivo criar uma metodologia que facilite identificar publicações que são relevantes a determinadas áreas de conhecimento. Para isto utilizamos três contextos, o primeiro sobre a área de análise de redes sociais, o segundo sobre os anais dos 20 anos do webmedia e por último sobre área de sistemas embarcados. Como fonte de estudo nossa ferramenta de software conseguiu diversos resultados referentes às áreas de conhecimento, entre eles a evolução de publicações para os veículos de publicação mais relevantes, a classificação das comunidades pertencentes a rede, e entre outros resultados.
16
Benkoussas, Chahinez. "Approches non supervisées pour la recommandation de lectures et la mise en relation automatique de contenus au sein d'une bibliothèque numérique." Thesis, Aix-Marseille, 2016. http://www.theses.fr/2016AIXM4379/document.
Full textAbstract:
Cette thèse s’inscrit dans le domaine de la recherche d’information (RI) et la recommandation de lecture. Elle a pour objets :— La création de nouvelles approches de recherche de documents utilisant des techniques de combinaison de résultats, d’agrégation de données sociales et de reformulation de requêtes ;— La création d’une approche de recommandation utilisant des méthodes de RI et les graphes entre les documents. Deux collections de documents ont été utilisées. Une collection qui provient de l’évaluation CLEF (tâche Social Book Search - SBS) et la deuxième issue du domaine des sciences humaines et sociales (OpenEdition, principalement Revues.org). La modélisation des documents de chaque collection repose sur deux types de relations :— Dans la première collection (CLEF SBS), les documents sont reliés avec des similarités calculées par Amazon qui se basent sur plusieurs facteurs (achats des utilisateurs, commentaires, votes, produits achetés ensemble, etc.) ;— Dans la deuxième collection (OpenEdition), les documents sont reliés avec des relations de citations (à partir des références bibliographiques).Le manuscrit est structuré en deux parties. La première partie «état de l’art» regroupe une introduction générale, un état de l’art sur la RI et sur les systèmes de recommandation. La deuxième partie «contributions» regroupe un chapitre sur la détection de comptes rendus de lecture au sein de la collection OpenEdition (Revues.org), un chapitre sur les méthodes de RI utilisées sur des requêtes complexes et un dernier chapitre qui traite l’approche de recommandation proposée qui se base sur les graphesThis thesis deals with the field of information retrieval and the recommendation of reading. It has for objects:— The creation of new approach of document retrieval and recommendation using techniques of combination of results, aggregation of social data and reformulation of queries;— The creation of an approach of recommendation using methods of information retrieval and graph theories.Two collections of documents were used. First one is a collection which is provided by CLEF (Social Book Search - SBS) and the second from the platforms of electronic sources in Humanities and Social Sciences OpenEdition.org (Revues.org). The modelling of the documents of every collection is based on two types of relations:— For the first collection (SBS), documents are connected with similarity calculated by Amazon which is based on several factors (purchases of the users, the comments, the votes, products bought together, etc.);— For the second collection (OpenEdition), documents are connected with relations of citations, extracted from bibliographical references.We show that the proposed approaches bring in most of the cases gain in the performances of research and recommendation. The manuscript is structured in two parts. The first part "state of the art" includes a general introduction, a state of the art of informationretrieval and recommender systems. The second part "contributions" includes a chapter on the detection of reviews of books in Revues.org; a chapter on the methods of IR used on complex queries written in natural language and last chapter which handles the proposed approach of recommendation which is based on graph
17
Heck, Joaquim. "Problem structuring methods: um estudo metodológico em cartografia estrutural e sua aplicação." reponame:Repositório Institucional do FGV, 2018. http://hdl.handle.net/10438/20402.
Full textAbstract:
Submitted by Joaquim Heck (joaquimheck@uol.com.br) on 2018-03-06T23:24:07Z
No. of bitstreams: 1
PDF_CDAE_Tese_Joaquim_Heck.pdf: 10473820 bytes, checksum: ad23dda74b39a1cdacaf8ac5345e3c9d (MD5)Approved for entry into archive by Debora Nunes Ferreira (debora.nunes@fgv.br) on 2018-03-07T12:33:18Z (GMT) No. of bitstreams: 1 PDF_CDAE_Tese_Joaquim_Heck.pdf: 10473820 bytes, checksum: ad23dda74b39a1cdacaf8ac5345e3c9d (MD5)
Made available in DSpace on 2018-03-07T12:39:47Z (GMT). No. of bitstreams: 1 PDF_CDAE_Tese_Joaquim_Heck.pdf: 10473820 bytes, checksum: ad23dda74b39a1cdacaf8ac5345e3c9d (MD5) Previous issue date: 2018-02-23
Esta tese apresenta os resultados de um estudo em metodologia que estabeleceu um novo método específico de análise documental e histórica, denominado cartografia estrutural para revisão de literatura, e que foi aplicado de forma experimental no estudo histórico de um tema da área de Pesquisa Operacional, os Problem Structuring Methods (PSMs). A cartografia estrutural para revisão de literatura é um método rigoroso e interdisciplinar que revela a estrutura subjacente à uma literatura por meio dos conceitos metodológicos encontrados em pesquisa documental, pesquisa histórica, Teoria dos Grafos, Análise de redes de citações e Cartografia. Verificou-se, a partir dessa interdisciplinaridade, que as relações entre diferentes autores, de diferentes épocas e que publicaram em diferentes periódicos são essenciais para aprofundar a compreensão e familiarizar o pesquisador com uma determinada área do conhecimento. Depois de introduzir a natureza básica da indexação de citações e da análise de rede, esse estudo apresenta a elaboração de um atlas bibliográfico, formado por mapas visuais e diagramas. A aplicação desse método resultou na composição do atlas bibliográfico sobre os PSMs no período de 1950 a 1989. O mapeamento de ideias e conceitos em um arranjo organizado, obtido pela análise exploratória de uma rede de citações longitudinal, assegura familiaridade com os conceitos constitutivos dos PSMs. O atlas bibliográfico é constituído por três análises principais: a exploração da abrangência panorâmica, a das referências e a dos periódicos. Esse estudo fornece subsídios para uma reflexão importante sobre a noção de unidade dos PSMs e a coesão de seus conceitos constituintes encontrada em seus precedentes teóricos. Finalmente, o método de cartografia estrutural possibilita realizar uma revisão de literatura sofisticada, bem como identificar temas fundamentais para futuras pesquisas mais produtivas.
This thesis presents the results of a methodological study that has established a specific method of historical and documental investigation, denominated structural cartography for literature review, which was experimentally applied in the study of Problem Structuring Methods (PSMs) history. Structural cartography for literature review is a rigorous and interdisciplinary method that reveals the underlying structure of a field literature through the methodological notions found in historical research, documental investigation, Graph Theory, and its subfield of citation network analysis, and Cartography. Due to its interdisciplinarity, it becomes clear that the relations between different authors, from different periods of time and from different media are essential to familiarize scholars with their fields of knowledge. After introducing the basic concepts of citation indexing and network analysis, this study shows how to build a bibliographic atlas composed of visual maps and diagrams. The application of this method resulted in the bibliographic atlas on the PSMs from 1950 to 1989. The mapping of ideas and concepts in an organized arrangement, which is obtained by the analysis of a longitudinal exploratory citation network, ensures familiarity with primitive concepts. The bibliographic atlas is composed by three main analysis: the exploration of coverage, of sources and of media. Moreover, this study provided insights for an important reflection on the notion of PSMs unity and the cohesion of their constituent concepts found in their theoretical precedents. Finally, the method of structural cartography for literature review made possible to conduct sophisticate literature review and has provided substantial themes for future research.
18
Spera, Henrique Baraldi. "Avaliação da produção científica em Ciências Sociais e Humanas: revisão da literatura recuperada em base de dados e rede de autores." Universidade de São Paulo, 2017. http://www.teses.usp.br/teses/disponiveis/27/27151/tde-12012018-104739/.
Full textAbstract:
As Ciências Sociais e Humanas (CSH) vêm enfrentando problemas para ter sua produção acadêmica integralmente reconhecida pelos sistemas de avaliação em todo o mundo. Tanto o processo de avaliação por pares quanto a mensuração por dados cientométricos possuem características distintas que afetam a maneira como a pesquisa é avaliada, mas a utilização de indicadores de citação de bases de dados internacionais como a Web of Science (WoS) em sistemas nacionais de avaliação têm sido especialmente desfavorável às CSH, devido às suas características singulares de publicação. Objetivo: apresentar uma síntese da literatura sobre avaliação da produção científica das CSH para compreender como os especialistas neste tema tratam das questões atuais já mencionadas. Metodologia: revisão de literatura. Um corpus composto de 107 artigos de periódicos foi recuperado por busca livre na WoS e na produção científica disponível na rede científica Research Gate, passando posteriormente por seleção final a partir de critérios qualitativos. Procedeu-se em sequência uma análise bibliométrica e uma análise qualitativa do corpus. Resultados: em termos geográficos e institucionais, a principal produção do corpus é oriunda da Espanha (CSIC), Bélgica (Universidade da Antuérpia) e Holanda (Universidade de Leiden). As publicações mais frequentes foram Scientometrics, Research Evaluation e Journal of American Society of Information Science and Technology, sendo que 43% dos periódicos do corpus são de Ciência da Informação. A avaliação quantitativa das CSH está presente em 81,3% do corpus, a avaliação qualitativa, em 42,1% e a mista, em 15%. As pesquisas empíricas formam 80,4% do corpus. Estudos reflexivos e propositivos formam 9,3% do corpus, são na maioria pesquisas empíricas (80%) e tendem a abordar a avaliação das CSH como um processo ao mesmo tempo quantitativo e qualitativo (70%). Conclusões: a literatura recuperada sobre avaliação da produção das CSH encontra-se em fase intermediária de desenvolvimento, apontando algumas alternativas, propostas e estudos aplicados para adequação dos instrumentos de avaliação. A Ciência da Informação emerge como disciplina proeminente na análise deste objeto em consolidação. Apesar de se identificar uma tendência ao uso de instrumentos que combinem aspectos quantitativos e qualitativos da produção, indicadores voltados à avaliação das CSH ainda estão por ser criados e não existe um modelo avaliativo que se possa apontar como consensual.Social Sciences and Humanities (SSH) are facing problems to have their scholar output fully recognized by evaluation systems worldwide. Both peer review and scientometric data have different characteristics that can influence the way the research is evaluated, but the usage of citation indicators in international databases such as Web of Science (WoS) for national evaluation systems has been especially harmful to SSH, due to their peculiar characteristics of publication. Aim: present a synthesis of the literature on evaluation of the SSH output and perceive how specialists deal with these current questions. Methods: literature review. A corpus composed of 107 journal articles was retrieved by direct search in WoS and also from the output available in the scientific network Research Gate. A final selection was made based on qualitative criteria. A bibliometric analysis and a qualitative analysis were carried out in sequence. Results and discussions: geographic and institutional distribution show that the main output of the corpus comes from Spain (CSIC), Belgium (University of Antwerp) and The Netherlands (University of Leiden). The most frequent publications were Scientometrics, Research Evaluation and Journal of the American Society of Information Science and Technology, and 43% of journals belong to the Information Science area. The quantitative evaluation of SSH is present in 81.3% of the corpus; the qualitative evaluation, in 42.1% and the mixed evaluation, in 15%. Empirical studies form 80.4% of the corpus. Reflective and propositional studies form 9.3% of the corpus, and they are mostly empirical research (80%) and also tend to approach the evaluation of SSH as a process both quantitative and qualitative (70%). Conclusions: the literature on evaluation of SSH output is in an intermediate stage of development, in which some alternatives, proposals and applied studies to the adequacy of evaluation instruments are pointed out. Information Science emerges as a prominent discipline in the analysis of this object, which is in consolidation. Although there is a tendency to use tools that combine quantitative and qualitative aspects of the output, an indicator for SSH evaluation has not yet been created and there is no assessment model that can be identified as consensual.
19
Kroon, Frederick William. "Finding Communities in Typed Citation Networks." Thesis, 2008. http://hdl.handle.net/10012/4037.
Full textAbstract:
As the Web has become more and more important to our daily lives, algorithms that can effectively utilize the link structure have become more and more important. One such task has been to find communities in social network data. Recently, however, there has been increased interest in augmenting links with additional semantic information. We examine link classification from the point of view of scientometrics, with an eye towards applying what has been learned about scientific citation to Web linking. Some community detection algorithms are reviewed, and one that has been developed for topical community finding on the Web is adapted to typed scientific citations.
20
Kao, Kung-Ming, and 高孔明. "The Design and Implementation of Citation Networks Visualization System." Thesis, 2008. http://ndltd.ncl.edu.tw/handle/10219676991751825154.
Full textAbstract:
碩士國立臺北大學
資訊管理研究所
96
In the age of information overloading, there are voluminous information readily available to us. Researchers develop the information visualization study to facilitate the effective comprehending the huge information. Through information visualization, we can better comprehend large amount of information. Complex relationships of large networks may be grasping more easily and intuitively. In this research, we developed the visualization system, HelloCite. We use prefuse, an open source toolkit, which was implemented using Java programming language. In our system, we focus on visualizing the relationships of papers. We want to utilize this tool to illustrate the literatures’ relationship of a given knowledge domain. With interactive interface, we can offer users a more flexible view of citation networks. The features of HelloCite include the following: (1) It can read data from a *.net file, which is defined by a popular network analysis tool called Pajek. (2) It integrates a linkage analysis’ evaluation measurement, PageRank, as an importance ranking weight for each node in citation networks. (3) It provides several filters such as weight scaling filter and distance filter to help user navigate in the citation networks.
21
Lin, Shu-Wei, and 林樹煒. "Using Citation Networks Position Analysis for patent future Evaluation." Thesis, 2007. http://ndltd.ncl.edu.tw/handle/46178884342102089276.
Full textAbstract:
碩士國立清華大學
科技管理研究所
95
Patent analysis is very important information to compete with the competitors of enterprises and control the research progress for business. There are more and more scholars and research methodology to help patent analysis, but most crucial thing is that lots of patent information like the citing number only provided the emphasis of current time point; it can not get the emphasis of future from citing number. Social network analysis is a theory to analyses network graph, discus the actors function in the social network and it can present the current patent value by patent citation graph. Betweenness and closure are the major two forces to affect the future advance by the network structure of node. This study hopes penetrate the social network analysis to research patent citation graph can predict the future advance for every patent and provide the useful information for patent scholars.
22
邱俊旺. "Relative Centrality and Local Community Detection on Citation Networks." Thesis, 2013. http://ndltd.ncl.edu.tw/handle/37285638019709435955.
Full textAbstract:
碩士國立清華大學
通訊工程研究所
101
Currently, the community detection in networks has gathered a lot of attention. How- ever, if we are only interested in certain nodes, then we need local community detection. Moreover, If the graph is directed one, just like citation networks, then there would be lots of dierences. A new way of searching papers by using relative centrality on di- rected graph as our local community detection method is provided. Modications of our undirected version to directed version are also been made. Then we have two methods of random walk, we are going to show that by using general type of random walk with walking length under two steps is better than the rst type of random walk with walking length in single step. After our experiment, we can nd a larger size of community and we believe our ranking order has more sense compared to only considering citation size, because we take triangle into consideration, which means that our prior adding nodes not only have direct link to the community but also have some two steps of links to the community. Finally, we list some problems for our future works.
23
Huang, Jheng-Peng, and 黃正鵬. "Knowledge Inference through Contextual Analysis of Titles in Citation Networks." Thesis, 2015. http://ndltd.ncl.edu.tw/handle/28256681643992158375.
Full textAbstract:
碩士國立臺灣科技大學
資訊工程系
103
The literature review process is often time-consuming because the keyword or text matching-based search is unable to provide sufficient knowledge. Specifically, while conducting a scientific study in the early stage, the keyword-based information retrieval often suffers from the improper use of search terms provided by the user. Two primary causes of mis-used keywords are the insufficient information and the word ambiguity. Since the composition of words may eliminate the ambiguity and generate a more accurate concept, this paper adopts concepts and their semantic relations instead of term-document vectors to better represent a scientific article. This paper proposes a concept retrieval method to handle the synonym and polysemy of search terms and keyword mismatches. A graph-based model is used to represent the concepts contained in the titles of scientific articles and the corresponding citation relations. Scores of concepts are derived accordingly in order to estimate the significance of a concept relative to a certain article. For a given query, related articles are retrieved and evaluated according to the importance of the induced concepts, so that users may continue their literature review in a more informative fashion. We have implemented a prototype system based on the CiteSeerX data, which contains over 3.6 million article records. We have evaluated queries from different research domains and showed that the proposed method successfully extracts articles with related concepts that are not limited by the exact keywords specified in a query.
24
Tsai, Ming-Kwen, and 蔡明錕. "Patent Analysis of Phosphor-Converted Visible Light-Emitting Diodes: A Perspective on Citation Networks." Thesis, 2012. http://ndltd.ncl.edu.tw/handle/p5v97x.
Full textAbstract:
碩士國立臺灣科技大學
專利研究所
100
Phosphor-converted white LEDs have become one of the most environment-friendly solid-state lighting products. This study offers a “phosphor-converted visible LEDs” development scenario from a perspective different from previous studies. In this thesis, we conduct data retrieval of academic papers and patent documents from ISI Web of Science (WOS) and USPTO database, respectively. Directional networks are constructed based on citation relationships among academic papers and patent publications to visualize the citation patterns. Main-path analyses are further conducted to trace the main knowledge flow through citation data, from which some papers and patents are found to have stronger impacts. Finally, a dual main-path approach is used to visualize the science-technology linkage, by which we measure how influential the scientific frontier is upon the related technological discipline. Dual main-path analysis is based on the citation relation between the paper main path and the patent main path, both of which are constructed respectively by key actors connected by directional arrows and are linked from papers to patents. Our findings could provide policy makers, especially those dealing with government-level research projects, and research group leaders with an intellectual basis for evaluating academic papers and forecasting possible opportunities for the industry.
25
Ko, Pei Chun, and 柯佩均. "The Network mechanism of scholarly productivity in Taiwan sociology: An Example of citation networks of sociological academic journals in 2001~2006." Thesis, 2008. http://ndltd.ncl.edu.tw/handle/62892709748916665131.
Full textAbstract:
碩士國立政治大學
社會學研究所
96
Abstract In recent years, as the world has been trending toward a Knowledge-based Economy, governments worldwide have recognized the importance of academic research, providing resources to upgrade the academic research level in order to internationalize scholarly pursuit. Taiwan, as a latecomer to the concept of Knowledge-based Economy, has begun to constitute science and social science rules and evaluations for academic development. The study intends to capture the transformation of the academic field by examining citations. In early works in the science of sociology, citation was an important indication of scholarly productivity. Social network analysis (SNA) enriches the methodology, and makes the indication to the idea of citation networks. Based on the perspective of SNA, the study investigates the citation network database of sociological journals between 2001 and 2006, and the concurrent citation networks of sociologists from three prior sociological journals. The results include three parts: first, the structure of journals' citation networks shows the trend of centralization, and two academic journals attain privileged status by means of structural equivalence. Second, the dual network of authors and journals demonstrate the citation divisions of sociologists and social workers. The sociological professional journals and social worker professional journals also are divided by time. Finally, the citation mechanism of sociologists verifies the normative pattern. In conclusion, the analysis confirms the impact of social science policy, which influences the centralization of citation networks and the advantageous status of specific sociological journals. The sociologists' citation networks are related to the specialty similarities of scholars, not the social relations. The study gives a pioneer explanation of citation networks of Taiwanese sociology.
26
Liao, Pei-Wen, and 廖珮雯. "Exploring the Networks of Patent Citation and Patent Transaction from the Social Network Analysis Perspective- The Case of TFT-LCD Technology." Thesis, 2015. http://ndltd.ncl.edu.tw/handle/j7zyk3.
Full textAbstract:
碩士國立暨南國際大學
國際企業學系
103
As the time goes by, the development of technology has been advanced and changed rapidly in the few decades. For business companies, how to launch the key products are the important factors determining success or fail of the company fate. The research focuses on the TFT-LCD industry via the patent data of USPTO from 1976 to 2012 to construct the patent citation matrix and patent transaction matrix for the further explore. There are three levels to discuss about: the macro level for configuration role; the meso level for structural role; and the micro level for ego role. By analyzing the different perspectives is much complete to explore the characteristics each networks they are in the various patterns. Moreover, the paper applies the methodology Social Network Analysis (SNA) to measure. There are some indexes to discuss such as the Degree Centrality and the Betweenness Centrality in the whole network; the Network Cohesion, the Structural Equivalence, and the Blockmodeling for the cluster players; the Structural Holes, and the Co-opetition for the ego firms. The research finds that it is to know most of the patents are from the citation side to the transaction side that after considering clearly the company would make the accurate action on the transaction steps. That the phenomenon could be seen as the progress the TFT-LCD truly developed that is much likely to verify the situation form then on. Moreover, there are fewer researches focus on the exploring on the both citation side and transaction side. Each of the matrices has its own characteristics for the further analysis that the two matrices are with the close relationship between each other that could help the decision-makers for the complete management.
27
FANG, CHUN-HAO, and 方群皓. "Information Visualization：A Case study in Citation Network." Thesis, 2007. http://ndltd.ncl.edu.tw/handle/07922889216671440305.
Full textAbstract:
碩士國立臺北大學
資訊管理研究所
95
Information visualization can help researchers know the revolution of knowledge domain and future development in large amount of citation data. We use open source Prefuse and programming language JAVA to implement a visualization system. Our system is able to draw graphs from GraphML file, .net file and database. In order to reduce the number of unnecessary nodes, our system provides two kinds of pruning methods: in-degree filter and out-degree filter. Combined with degree filter and title keyword search, we attain keyword relative domain’s citation connection. Compared with Pajek in several cases, our system shows better visual presentation. We can get various graphs by connecting to database, not just the single one graph represented in the graph file. Also, Our system can deal with weighted graphs, find nodes’ traversal, and search for specified nodes. From the meanings of graphs, we are able to understand the cluster relationships. Furthermore, we can research deeper theories based on these earlier works.
28
Akujuobi, Uchenna Thankgod. "Link Label Prediction in Signed Citation Network." Thesis, 2016. http://hdl.handle.net/10754/607760.
Full textAbstract:
Link label prediction is the problem of predicting the missing labels or signs of all the unlabeled edges in a network. For signed networks, these labels can either be positive or negative. In recent years, different algorithms have been proposed such as using regression, trust propagation and matrix factorization. These approaches have tried to solve the problem of link label prediction by using ideas from social theories, where most of them predict a single missing label given that labels of other edges are known. However, in most real-world social graphs, the number of labeled edges is usually less than that of unlabeled edges. Therefore, predicting a single edge label at a time would require multiple runs and is more computationally demanding.
In this thesis, we look at link label prediction problem on a signed citation network with missing edge labels. Our citation network consists of papers from three major machine learning and data mining conferences together with their references, and edges showing the relationship between them. An edge in our network is labeled either positive (dataset relevant) if the reference is based on the dataset used in the paper or negative otherwise. We present three approaches to predict the missing labels. The first approach converts the label prediction problem into a standard classification problem. We then, generate a set of features for each edge and then adopt Support Vector Machines in solving the classification problem. For the second approach, we formalize the graph such that the edges are represented as nodes with links showing similarities between them. We then adopt a label propagation method to propagate the labels on known nodes to those with unknown labels. In the third
approach, we adopt a PageRank approach where we rank the nodes according to the number of incoming positive and negative edges, after which we set a threshold. Based on the ranks, we can infer an edge would be positive if it goes a node above the threshold. Experimental results on our citation network corroborate the efficacy of these approaches.
With each edge having a label, we also performed additional network analysis where we extracted a subnetwork of the dataset relevant edges and nodes in our citation network, and then detected different communities from this extracted sub-network. To understand the different detected communities, we performed a case study on several dataset communities. The study shows a relationship between the major topic areas in a dataset community and the data sources in the community.
29
Wang, Tun-Wei, and 王敦威. "The complex network of paper citation:Single Topic citation network analysis." Thesis, 2007. http://ndltd.ncl.edu.tw/handle/77993851391525967741.
Full textAbstract:
碩士臺灣大學
醫學工程學研究所
95
To analyze single topic literature citation network we focus on the topic of NOD2 gene. Our research focuses on the cluster of the network and paper citation raise and fall trends .After find out the important Hub Node in this Network then we try to predict the citation count. The topic is about NOD2 gene. First we search topic NOD2 in the ISI Web of Knowledge. Second, we use each paper’s reference to build citation network. After network construction, we can analysis network’s characteristics. At first we use Poisson distribution and probability to generate node degree distribution and use this to build random network. Then we use this random network to compare with our network. According to Cluster Coefficient value, Average Shortest Path Length value and Network citation distribution of our network, we know our network is Scale Free Network. Bigger C value compare to random network means our network is a lot more aggregate than random network. Small L value compare to random network means we have Hub Nodes in our network. Thus we provide a hub node search algorithm to search Hub nodes. Besides, we also want to predict the raise and fall trend of paper citation. We provide algorithm to distinguish those nodes raise and fall. That included Threshold Network and Order Probit Model. The goal of Threshold Network is to distinguish the trends of raise and fall. Order Probit Model is used to distinguish the significance of growth. Which we had verified those methods in KDD 2003 citation network. The result in KDD tells us this method can reduce the prediction error rate. Thus we use this on our network and retrieve network’s characteristics.
30
Chen, Jia-Yu, and 陳佳瑜. "A Novel Citation Network for Research Topic Evolution." Thesis, 2019. http://ndltd.ncl.edu.tw/handle/d5j5cc.
Full textAbstract:
碩士國立臺灣大學
資訊管理學研究所
107
In the past, people consumed related research thesis, journal papers or patent specifications to conclude the research trend of a topic area. However, with the coming of information explosion, consuming such a large number of data only by human seems to be inefficient. Therefore, it is important to develop a method to help users observe the evolution of research topics. In this study, we propose a novel citation network for detecting research trend to replace the past citation network that use a single document as a node and the citation relationships between documents as links. We extract the keywords which were specified by authors from the documents and redefine the citation relationships between nodes as well as the weight of edges. After deleting edges whose weight is lower than designated threshold, nodes in the final citation network would be clustered to find the research topics. Each cluster of nodes is considered as a research topic. The details of a research topic can be realized from the keywords in the cluster. Finally, we are able to observe the evolution of a topic area by checking the relationships among research topics in different years. The experiment shows that the proposed novel citation network can extract useful research topics from numerous literature and assist domain experts to observe the change of research topics.
31
Lin, Li-Ling, and 林莉陵. "Evaluating patent citation analysis from Social Network Analysis perspective." Thesis, 2009. http://ndltd.ncl.edu.tw/handle/56319265138786768533.
Full textAbstract:
碩士國立暨南國際大學
國際企業學系
97
Since the life cycle of Hi-Tech products becomes shorter and technology development and variety of market uncertainty get more complicated, the Network relation has more influence on these phenomena. Under the same environment and the limited resources, strategic makers have to deliberate the competition, cooperation or the complementariness of competition and cooperation strategy. In the past, researchers who only used dyadic view for patent citation analysis, so they can’t find the triadic or even multi information. In addition, some scholars even thought the traditional patient citation analysis were mature, if someone who wants to find more information, they should used new analytic method. Hence, the traditional patent citation analysis was a good contribution, but sometime limitations were caused of error information. As the result, we adopt the popular concept, social network, to discuss the position, role, influence and the situation of interaction with limited resources in RFID industry. Moreover, we also confer on the strength of the relation and the situation within the internal area. In short, the study will discuss the influence of structure and characteristics of firm from the whole, cluster and individual level with the top 20 firms, produce patent occupied 95% from all data, in the RFID industry. Discussing when firms in an environment, limited in resources, what the operation of these firms will do. The empirical results show that the characteristic and structure of firms certainly influence the relation of each other and the strategic choice. For firms at whole level, the technology diffusers are more independence; the technology absorbers require higher dependence; medium firms have more broker benefits from the technology transmission. In addition, the concept of Cluster and Blockmodeling shows that under the same environment and limited resources, the complementariness of competition and cooperation would appear at the same time. Finally, from the individual level, we could find firms who have more specialism and basic technology in the field and will be the core group in the future. The study expands the citation information of patent owned by firms through Network views and offers more messages.
32
Yeh, Li-Tzu, and 葉力慈. "The Determinants of Patent Citation Network: The Case of Photovoltaic." Thesis, 2014. http://ndltd.ncl.edu.tw/handle/69414965697532762470.
Full textAbstract:
碩士國立中央大學
產業經濟研究所
102
The purpose of this article is to investigate the determinants of patent citation network. The analysis is based on patents of photovoltaic granted by the US Patent and Trademark Office (USPTO) from 1976/01/13 to 2014/03/11. The way we weigh the patent in the citation network is “Centrality” proposed by Freeman (1979). In order to find what critical elements affect the position of patent in the citation network most, we use tobit model to analysis. In the beginning, we put patent characteristics variables in our model. Then, we add firm characteristics variables. In the end, we try to figure out if the number of claims or the scope has concave relation toward centrality. There are five interesting findings. First, the most important determinant is the time lag between granted year and first cited year. If a patent that is immediately cited by other patent, it will have more direct and indirect forward citations. And the citation lag can also affect the position of a patent in the citation network. Second, if assignee keeps paying the renewal fee, it will raise the frequency of direct and indirect forward citations especially when it is due to the last term. Third, the number of claims has a positive effect toward direct forward citations. The degree of influence decreases as the number of claims increases. Fourth, the use of non-patent knowledge positively affects direct and indirect backward citations. Final, the broader the scope a patent has, the higher the frequency of backward citations and forward citations it can receive. The degree of influence toward indirect forward citation decreases as the scope increases.
33
Chen, Shi-An, and 陳璽安. "Analyzing Technology Trajectory of Solar Cell via Patent Citation Network." Thesis, 2016. http://ndltd.ncl.edu.tw/handle/37249454859439569925.
Full textAbstract:
碩士元智大學
經營管理碩士班(企業管理與服務科學學程)
104
In the recent years, dramatic climate change phenomenon comes one after an-other over the world because of consuming fossil fuels and discharging a large amount of carbon dioxide lead to an intense greenhouse effect. Every country has devoted to promoting clean energy so that we can break away from fossil fuels addiction; it seems that solar cell is the key to finding the way out. We conducted a research on the development of solar cell technology via ana-lyzing patent citation networks. To find the crucial technology and develop trend within a complex citation network, we primary applied Edge-betweenness Clustering to divide those patents cites each other intensely into several clusters, and then con-ducted the global key-route main path analysis to find out the patents with critical in-formation and the relationship among citations. In this research, the solar cell patents are separated into four clusters, they are CIS/CIGS thin-film solar cell manufacturing technique, solar cell power system, solar cell module system and silicon base solar cell manufacturing technique. There are several important technological fields are identified, including the development of thin-film CIGS/CIS solar cell processes, the maximum power point tracking tech-niques, DC/DC inverter with high conversion rate, safety structures for solar cell module, installation and mounting techniques of solar arrays, etc. We found out that the entire industry focuses on cost reduction and increasing efficiency. To find high-value patents within a complex patent citation network rapidly, the main path analysis and clustering technique provide a feasible solution, which can explain the development trends of technologies, and prove that the development of industry is associated with patents applications. The results are very useful for related researchers.
34
Tung-Hsuan, Wu, and 吳東軒. "Patent Citation Network Analysis for The Development of Technology Life Cycle." Thesis, 2013. http://ndltd.ncl.edu.tw/handle/24346574469267362797.
Full textAbstract:
碩士國立暨南國際大學
國際企業學系
101
The changing rapidly economic environment and fierce increasingly competition that require companies to be innovative, which are in both their products and marketing strategies, if they are to continue to flourish. Before the product strategy formulated, a technology strategy must be developed to provide competitive products, materials, processes, or system technologies. The first step for devising a technology strategy is to decide whether the technology being worth to invest. How will the technology develop in the future? Will the technology still flourish in the future or will it decline? To answer these questions, one should know the life cycle stages of the technology in order to estimate the future development trends of the technology and make informed decisions whether invest in the technology or not. This study takes the patents of floppy disk and modems for example, and uses the technology flow network of citing and cited to discuss the network structure. Defining and distinguishing each stages of technology life cycle by utilize these indicators, including out-degree centrality and in-degree centrality. Finally, exploiting cohesion and structure position to determine the relationships of competition and cooperation in the floppy disk and modems’ technical fields, to realize each patents belongs to what sub-technologies and what roles in each stages of technology life cycle by firms own. The research result shows that using indicators of patent network citation analysis, out-degree centrality and in-degree centrality could recognize the direction of technology and knowledge’s flow. Moreover, the appearance of design dominance’s time point is the peak of out-degree centrality curve in growth stage. And by the maturity of industry’s supply chain, the more stable between upstream and cooperation of downstream, the more competitive between the same level’s firms. The result can help to recognize the character of other firms in strategy, and relocate enterprise’s R&D resources to enhance strategically planning.
35
張弘軒. "Analyzing Network Citation Styles Currently Used in Taiwan's Visual-Art Theses." Thesis, 2009. http://ndltd.ncl.edu.tw/handle/85663315156757198770.
Full textAbstract:
碩士臺北市立教育大學
視覺藝術學系碩士班
97
In the field of visual arts, citing from network literature and researching on network phenomena have been increased in recent years, which renders the necessity of investigating the current practices of network citation. The purpose of the study is to compare four network citation styles: APA, MLA, Chicago, and the Thesis Writing Style Manual published for the Visual Arts Department of Taipei Municipal University of Education. The comparisons include: basic documentation principles, contents, online books, online periodicals, general websites, official websites, online communications, databases, other online sources. Also, the 2006-2008 practices of networks citation in visual-art theses are investigated. The conclusions are the followings: (1) None of the styles covers all kinds of network literatures. (2) The network citation styles used by the theses are chaotic. (3) The successful retrieval rate of network citations in the theses is to be improved. The suggestions are the followings: (1) Provide general format suggestions as detailed in the text. (2) Archive the pages to avoid the failure of search. (3) Revive the styles to cover the various network literatures.
36
Hsieh, Hui-Chen, and 謝惠媜. "Constructing an Enhanced Patent Citation Network by Adding Unused Relevant Patents." Thesis, 2009. http://ndltd.ncl.edu.tw/handle/52933247709166010346.
Full textAbstract:
碩士國立臺灣大學
工業工程學研究所
97
The patent citation analyses rely on the citations between patents, including quality of patents, knowledge flow and spillover, technology development and industrial trend. The inventors record relevant information as prior art but not all the relevant prior studies would be cited as references. Some highly relevant patents may be unused for the citation time lag (CTL). This paper used the bibliographical coupling (BC) and Pareto principle to identify the unused relevant patents (URP). Some of the missing citation links can then be made up by adding the URP and an enhanced patent citation network (EPCN) can be constructed by taking the URP into account. The patent citation network (PCN) and EPCN were discussed at patent and assignee level in this paper. The differences between the two networks were studied through the Freeman vertex betweenness centrality and the Johnson’s hierarchical clustering. The light emitting diode (LED) illuminating technology was chosen for case study in this paper in order to demonstrate the feasibility of the research methodology. As shown in this work, the relationship between patents can be enhanced by adding the URP.
37
Hsu, Che-Jung, and 許哲榮. "The Impact of Patent Citation Network on Innovation: Evidence from Semiconductor Firms." Thesis, 2007. http://ndltd.ncl.edu.tw/handle/60627327352024860734.
Full textAbstract:
碩士臺灣大學
經濟學研究所
95
This study examines the impact of patent citation networks on technology capability in the semiconductors industry among advanced firms in US, Japan, Germany, France and Netherlands and latecomer firms in Taiwan, Korea and Singapore during 1990-2005. We find that learning could improve semiconductors firms’ technology capability. Moreover, the level of improvement in latecomer firms was greater than advanced ones. In addition, the more important position a firm had in the patent citation network, the better technology capability it had and latecomer firms were significantly better than advanced ones only in recent years, i.e. 2001-2005.
38
周永佳. "How Construction of the Evaluation Indicators on Scholarly Literatures Under Citation Network." Thesis, 2011. http://ndltd.ncl.edu.tw/handle/96193451044687192436.
Full textAbstract:
碩士國立交通大學
資訊學院碩士在職專班數位圖書資訊組
99
The main function of the university is research and teaching. In university ranking, someone pay attention rating in the way artificially, but someone pay attention in scientific.University ranks have far-reaching about image and popularity. It not only merely understands the difference of academic results of research, but also regard as choose the reference that study in the school. There are many different ways in ranking university, and data source is also different too. The search engine of this research is Google Scholar. It is easily to get and free to everyone. We use the scholars of computer science of domestic national university as sample. Cited papers of scholars in the angle and consult indicator from Shanghai Chiao Tung University and Higher Education Evaluation and Accreditation Council of Taiwan.We construct evaluation indicators on scholarly literature which meet the nature of Taiwan region and academic background. It quoted the situation for scholar's personal thesis, and then obtains the academic research ability of this institute. We construct the evaluation indicators on scholarly literatures under citation network with different angles and go to rank. By the way of seeing trees and see the forest too, and probe into its meaning.
39
Yang, Wen-Lin, and 楊文霖. "The Patent Citation Network Analysis of Technical Evolution of Electric Bicycles Motor." Thesis, 2011. http://ndltd.ncl.edu.tw/handle/74249216617633172634.
Full textAbstract:
碩士國立彰化師範大學
工業教育與技術學系
100
As the trend of environmental consciousness is getting stronger, usage of resources and harm in environment are coming into bigger conflict. Therefore, energy conservation, low pollution and sustainability are becoming the key point in development of technology. By means of electric bicycle motor study and patent citation network analysis, technological evolution of electric bicycle manufacture in Taiwan is being investigated. Also, its design capability and patent development are being interpreted. In the end, prospective design and patent orientation of electric bicycles are being anticipated. The study shows that when seeking a certain key or typical technique, if patent citation network analysis is adopted, differences made out of artificial identification will be reduced. Meanwhile, artificial limitation of related researches will also be reduced, making the key technique more scientifically-based. The motor technology of electric bicycles has evolved from the motor with brush to the brushless motor, and the brushless motor technology nowadays is heading for the sensorless brushless motor, in which the control of the three-phase brushless motor is the very key technique and the speed control is the most significant in-between technique among the brushless motor technology. Therefore, the thesis is trying to provide the manufacturers a reference of strategy and orientation in research and development, hoping to make an effort toward the electric bicycle manufacture in Taiwan.
40
Saw, EweChai, and 蘇有財. "The Development Trajectory of Fuel Cell Technologies via Academic Papers Citation Network Analysis." Thesis, 2012. http://ndltd.ncl.edu.tw/handle/42015053428332667789.
Full textAbstract:
碩士元智大學
經營管理碩士班(企業管理與服務科學學程)
100
As the power generation technologies with highest energy conversion efficiency, fuel cell technologies had long been identified as one of the most promising candidates for future power generation sources. However, major technological barriers such as cost, durability, size and water management issues are currently hindering the massive deployment of this clean energy technology. Hence, to assist in identifying the most promising fuel cell technologies for effective investment in the scarcity of resources, citation network analysis is adopted in this study to discover the latest trend in the field of fuel cell development. Result of our analysis shows that the Proton Exchange Membrane Fuel Cell’s (PEMFC) performance is almost reaching to an acceptable level and is ready for mass commercialization. On the other hand, the Direct Methanol Fuel Cell (DMFC) is still suffering on the methanol and water crossover problems. Due to the toxicity of methanol, Direct Formic Acid Fuel Cell (DFAFC) and Direct Ethanol Fuel Cell (DEFC) have recently emerged and will possibly replace the DMFC due to superior advantages and significantly lower cost of these new technologies.
41
Lin, PIN-CHIEH, and 林品潔. "A research of social network analysis for citation pattern in Taiwan psychological journal." Thesis, 2008. http://ndltd.ncl.edu.tw/handle/61874183119356204686.
Full textAbstract:
碩士輔仁大學
心理學系
96
In the journal world，the academic Community development traces are being disclosed by the condition of cited and citing. In this research，we will adopt the idea of social network analysis to explore the botany、Pattern、and development behind the citation relation in Taiwan psychology Community The findings showed, the journal demarcation line and the domain model still might not neglect factor. In Chinese Journal of Psychology、Indigenous Psychological Research in Chinese Societies、and Research in Applied Psychology，the three journal quotation conditions are more obvious. The Three journal by the different model took respectively become different communities, the between quotation nature drops mutually, the different journal objective attracts to the dissimilar work, when the demonstration journal edition selection article, author also in selection journal. In the research aspect, is especially obvious in Chinese language aspect, regardless of how boundary under, the Chinese psychology journal Chinese language cognition research is for the independent crowd, are extremely few with other region intercourse. But organizes the subject of communities quotes the number of times between the journal to be vigorous. The penetration journal quotation relations observe the entire academic community development, discovered the different journal composition the field suits the different community, this research reappears its community modus by the social network analysis, the quotation crowded community demonstrated its exchange quite is close, there are positive significance to this community development in the future. Low Quotation density junior, then needs the author to care about this domain and the editor does farm work together, assists the community to be healthy gradually grow up. Generally speaking, this research will help the scholar to publish in the future, or will seek the correlation domain the scholar will exchange mutually has the help, might regard it will be a knowledge map, will want to have many interactions with other scholars to pay attention to this modus. People who Ambitious to exploration, or with attempts the new domain to be possible from this research to inquire the vein.
42
Peng, Jhih-Ci, and 彭志祺. "The Study of Supply Chain Management Using Co-citation Analysis and Social Network Analysis." Thesis, 2008. http://ndltd.ncl.edu.tw/handle/27423034581765049347.
Full textAbstract:
碩士國立交通大學
資訊管理研究所
96
In this era of global competitive environment, Supply Chain Management (SCM) plays an important role in the environment of an enterprise because the most important significant paradigm shifts of modern business environment that individual business no longer consider as unique and immutable, but rather must be seen as supply chain. Due to SCM, it is a relatively new extensive concept that many researchers analyze the literature from multiple disciplines by seeing how the supply chain concept has evolved and changed and defined. In this study, by using empirical experiment, we use co-citation method and social network analysis to discover the most closely related links between sets of subjects or documents of SCM. Based on our research results that we hope to help specialists easily realize the main trends, understand of intellectual structure and movement in the SCM and in other areas, and locate relevant papers efficiently.
43
Lee, Joahanna, and 李漢娜. "The study of Collaborative Product Commerce Using Co-citation Analysis and Social Network Analysis." Thesis, 2007. http://ndltd.ncl.edu.tw/handle/80190444330882236484.
Full textAbstract:
碩士國立交通大學
資訊管理研究所
95
This paper presents the analysis of Collaborative Product Commerce documents associated by using co-citation analysis and social network analysis. Co-citation is a new form of document coupling the frequency with which two documents are cited together. In this paper we report an experiment by using data from Google scholar search and Social Science Citation Index to identify clusters of highly interactive documents in the subject of Collaborative Product Commerce. They may provide a new approach to indexing and to the creation easier search CPC area. The study discovers five core papers which imply the four documents provide insight into the theory’s evolution and clarifies future research work in CPC field. The trend in the field focuses on organizational layer, included knowledge management, system problem solution, and collaborative mechanism design. The conclusion can provide future research direction for the researcher in this field.
44
Li, Ying-Yang, and 李英揚. "Using Citation Network Analysis to explore the Relationship between Patent Feature and Patent Quality." Thesis, 2012. http://ndltd.ncl.edu.tw/handle/59267001040423679942.
Full textAbstract:
碩士國立清華大學
服務科學研究所
100
Patents are important assets in a company. It not only represents the technology abilities, but also represents the competitive advantage of a company. Each patent owns different features that will affect the quality of patent in the future. Determining the impact from patent features to patent quality is always important for R&;D strategies. In this study, social network is regarded as a mediator to explore the relationship between patent features and patent quality. The analytical results shows that patent features will affect patent quality through network position. Thus, this study provides a method for the purpose of predicting patent quality and finds that a patent with higher originality or shorter technology cycle time will enhance patent quality through network position. Patent features are different depending on variation of industry environment. Thus, this study further explores the moderation efficiency of patent types for finding the different behavior in citation network with different patent types. This study suggests that it is need to adjust R&;D strategies by different purpose of using technology. At least for technology-oriented patents and service-oriented patents, the R&;D strategies should be different between them.
45
Duverge, kenderly Cling Jester, and 杜肯德. "The Development Trajectory of Readiness for Environmental Change: An Academic Papers Citation Network Analysis." Thesis, 2018. http://ndltd.ncl.edu.tw/handle/bjpvzm.
Full textAbstract:
碩士元智大學
經營管理碩士班(國際企業學程)
106
This study is a tentative to identify the overall development trajectory of readiness for environmental change. the areas of study are business and management, decision science and economics. In this study, 2949 academic papers are analyzed by two major citation network technics: Edge-betweeness clustering and Key-route main path. Four important topics have been identified: 1) Consumer willingness to pay for organic and eco-friendly products, 2) Valuation of environmental goods, 3) Contingent valuation method, 4) Green consumerism and consumer environmental behavior. The results show that the contingent Valuation is the base of readiness for environmental change, this method is used to value environmental goods and eco-friendly products. The results also show that climate change will likely be a new track of research in readiness for environmental change.
46
Lan, Yun-Lin, and 藍云琳. "Analyzing Technological Trajectory via Patent Citation Network: An Application to Radio Frequency Identification Technology." Thesis, 2011. http://ndltd.ncl.edu.tw/handle/74029771409201644569.
Full textAbstract:
碩士元智大學
企業管理與服務科學學程
99
As one of the representative indicators of intellectual property, patent not only enhances the exclusive right to develop particular product or technology, but also protects intellectual capital. Therefore, if we can properly use the patent information, we will be able to understand competitors’ strength and weakness, and assure the market opportunities. This study applies main path analysis to find the relationship among patent citation network of RFID (Radio Frequency Identification), and explore technological development trajectories and important patents related to RFID. In addition, this study also observes the RFID technological development status through logistic growth model. USPTO (United States Patent and Trademark Office) database is the source of data. The results show that RFID technology is at the matured stage. IPC G08B, G06F and G06K are the main foci of RFID technological development. Antenna and tag structure or related materials are the major components. American and Japan are the countries that contributed most to RFID development. Currently, there are three major directions in the market: providing low cost chips, developing portable RFID transponder and related integrated systems, and developing RFID application technology.
47
Tseng, Yinchiao, and 曾瀛巧. "Using social network analysis to explore the citation relationships of business and management disciplines." Thesis, 2011. http://ndltd.ncl.edu.tw/handle/89386141564767366899.
Full textAbstract:
碩士國立臺北大學
企業管理學系
99
Articles being published on academic journals represents the knowledge creation and the transmission. While the development of social network analysis (SNA), more and more studies explore the relationship of journals to journals citation network. Based on SNA, this study assesses citation relationship in business and management field. In the procedure, we used 102 journals from JCR to establish the citation matrix and then applied Pajek and UCINET as the analytical tool to measure the strength of citation relations, cluster analysis, information flow, role of journals and observation of similarity in citation structure. The purpose is to provide suggestions about journals of publishing in business and management, especially in other related discipline, for teachers and researchers. The results show journals in business and management have citation relationship with many other areas. In particular the journals of psychology, after four years it increases the links with journals in business and management categories, and the two fields become the core groups in bi-connected component analysis. In the analysis of information flow, more journals in business and management field exist information exchange process with other discipline, and most of them are citing journals, as well as information receiver. In multidimensional scaling analysis, as expected, most similar groups are in same academic field.
48
Liang, Chung-Ming, and 梁中明. "A Study of Applying Social Network Analysis to Patent Citation－Case of Solar Cell." Thesis, 2007. http://ndltd.ncl.edu.tw/handle/03982998369727489978.
Full textAbstract:
碩士元智大學
資訊管理學系
95
This study propose a method of patent analysis,combine patent citation data applying Social network analysis,data source from USPTO(United States Patent and Trademark Office)database. Study period between 1987~2007,scope in solar cell,add the concept with technology field and time separate,become a network linking by time and technology field,using by UCINET software tools,through this way find out relation between patent,and helpful to patent analysis work. The result present past technology field effect technology trend,most past technology field modified by new technology, and few chance transfer to do innovation field;Most new technology field intend to same country,technology in the past and in the same country has import position on solar cell technology field.
49
Tu, Li-Hsiang, and 杜立翔. "The Development Trajectory of R&D Internationalization Academic Papers: A Citation-based Network Analysis." Thesis, 2011. http://ndltd.ncl.edu.tw/handle/46547506854146990032.
Full textAbstract:
碩士元智大學
企業管理與服務科學學程
99
With expansion of globalization and increment of transnational corporations（TNCs）, R&D internationalization becomes a key point when TNCs execute innovation activities. Through analyzing the citations among academic articles, this paper uses different kinds of main path analysis to discover two major development trajectories and four recent active sub-areas of R&D internationalization. By analyzing the nodes on the main path, we could understand the evolution of research topic in this academic field. This paper has extracted the most influential journals and researchers through g-index. In the end, we concluded that R&D internationalization related researches have already reached the maturity stage according to the S-curve analysis.
50
LIU, RUI-RONG, and 劉瑞榮. "Explore the Role of Patent Litigation Network and the Structure & Properties of Patent Citation Network Based on Patent Litigation Data." Thesis, 2017. http://ndltd.ncl.edu.tw/handle/gk3bg6.
Full textAbstract:
博士朝陽科技大學
企業管理系台灣產業策略發展博士班
106
All countries in the world have started fierce technical competitions around the development of LED since 2000, and patent infringement has occurred from time to time, which has also triggered a large-scale patent war. Identifying the position of the firm in the litigation relationship becomes an important issue in the implementation of the litigation strategy of "Know the enemy, know yourself". In addition, the flow of technological knowledge hidden behind the patent becomes the primary solution to patent layout of the enterprises. Previous studies have mostly focused on assessing the number and quality of patents held by companies to provide information on patent portfolios and assessments. Due to factors such as security, the research based on patents tends to have limited access, patent litigation is easy to access and reflects the importance of the patents well even with a small number of cases. Therefore, this study proposes new ideas on the basis of patent litigation data, two aspects such as the patent litigation network constructed by litigation subject and the patent citation network constructed by litigation object. This study collected data on LED patent litigation between 2000 and 2016. Firstly, the litigation subject information was extracted and the patent litigation network was constructed. The research on the role of patent litigation network was completed through three steps of network centrality analysis, multivariate analysis and of position & role analysis. The results show that LED litigation companies can be divided into four groups which label leaders, core competitors, Non-practicing entities and potential threats, with good effect of clustering and be consistent with market position of the enterprise. Then, the object of litigation was extracted and the patent citation network of the country, the institution and the technology was built. The structure and properties of the patent citation network were analyzed in depth through three aspects: network visualization, network topology analysis and key nodes analysis. The results show that the distributions of the three patent citation networks follow the power law distribution and belong to the scale-free network. The United States, Japan, the Netherlands, Germany and South Korea are the key nodes in the country citation network. The most important nodes in the institution citation network is Philips, Cree, Nichia, Osram, Seoul Semiconductor and GE, H01L, F21V and H05B are the key nodes in the technology citation network. The new perspective of research not only can provide enterprises with the management opinions of patent litigation strategy and patent layout, but also can provide structural approach and small sample research ideas for follow-up theoretical research so as to improve the reliability and validity of the research.