Dissertations / Theses on the topic 'Fouille de Données Textuelles Hétérogènes'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 27 dissertations / theses for your research on the topic 'Fouille de Données Textuelles Hétérogènes.'
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.
Alencar, Medeiros Gabriel Henrique. "ΡreDiViD Τοwards the Ρredictiοn οf the Disseminatiοn οf Viral Disease cοntagiοn in a pandemic setting." Electronic Thesis or Diss., Normandie, 2025. http://www.theses.fr/2025NORMR005.
Full textEvent-Based Surveillance (EBS) systems are essential for detecting and tracking emerging health phenomena such as epidemics and public health crises. However, they face limitations, including strong dependence on human expertise, challenges processing heterogeneous textual data, and insufficient consideration of spatiotemporal dynamics. To overcome these issues, we propose a hybrid approach combining knowledge-driven and data-driven methodologies, anchored in the Propagation Phenomena Ontology (PropaPhen) and the Description-Detection-Prediction Framework (DDPF), to enhance the description, detection, and prediction of propagation phenomena. PropaPhen is a FAIR ontology designed to model the spatiotemporal spread of phenomena. It has been specialized in the biomedical domain through the integration of UMLS and World-KG, leading to the creation of the BioPropaPhenKG knowledge graph. The DDPF framework consists of three modules: description, which generates domain-specific ontologies; detection, which applies relation extraction techniques to heterogeneous textual sources; and prediction, which uses advanced clustering methods. Tested on COVID-19 and Monkeypox datasets and validated against WHO data, DDPF demonstrated its effectiveness in detecting and predicting spatiotemporal clusters. Its modular architecture ensures scalability and adaptability to various domains, opening perspectives in public health, environmental monitoring, and social phenomena
Tisserant, Guillaume. "Généralisation de données textuelles adaptée à la classification automatique." Thesis, Montpellier, 2015. http://www.theses.fr/2015MONTS231/document.
Full textWe have work for a long time on the classification of text. Early on, many documents of different types were grouped in order to centralize knowledge. Classification and indexing systems were then created. They make it easy to find documents based on readers' needs. With the increasing number of documents and the appearance of computers and the internet, the implementation of text classification systems becomes a critical issue. However, textual data, complex and rich nature, are difficult to treat automatically. In this context, this thesis proposes an original methodology to organize and facilitate the access to textual information. Our automatic classification approache and our semantic information extraction enable us to find quickly a relevant information.Specifically, this manuscript presents new forms of text representation facilitating their processing for automatic classification. A partial generalization of textual data (GenDesc approach) based on statistical and morphosyntactic criteria is proposed. Moreover, this thesis focuses on the phrases construction and on the use of semantic information to improve the representation of documents. We will demonstrate through numerous experiments the relevance and genericity of our proposals improved they improve classification results.Finally, as social networks are in strong development, a method of automatic generation of semantic Hashtags is proposed. Our approach is based on statistical measures, semantic resources and the use of syntactic information. The generated Hashtags can then be exploited for information retrieval tasks from large volumes of data
Azé, Jérôme. "Extraction de Connaissances à partir de Données Numériques et Textuelles." Phd thesis, Université Paris Sud - Paris XI, 2003. http://tel.archives-ouvertes.fr/tel-00011196.
Full textL'analyse de telles données est souvent contrainte par la définition d'un support minimal utilisé pour filtrer les connaissances non intéressantes.
Les experts des données ont souvent des difficultés pour déterminer ce support.
Nous avons proposé une méthode permettant de ne pas fixer un support minimal et fondée sur l'utilisation de mesures de qualité.
Nous nous sommes focalisés sur l'extraction de connaissances de la forme "règles d'association".
Ces règles doivent vérifier un ou plusieurs critères de qualité pour être considérées comme intéressantes et proposées à l'expert.
Nous avons proposé deux mesures de qualité combinant différents critères et permettant d'extraire des règles intéressantes.
Nous avons ainsi pu proposer un algorithme permettant d'extraire ces règles sans utiliser la contrainte du support minimal.
Le comportement de notre algorithme a été étudié en présence de données bruitées et nous avons pu mettre en évidence la difficulté d'extraire automatiquement des connaissances fiables à partir de données bruitées.
Une des solutions que nous avons proposée consiste à évaluer la résistance au bruit de chaque règle et d'en informer l'expert lors de l'analyse et de la validation des connaissances obtenues.
Enfin, une étude sur des données réelles a été effectuée dans le cadre d'un processus de fouille de textes.
Les connaissances recherchées dans ces textes sont des règles d'association entre des concepts définis par l'expert et propres au domaine étudié.
Nous avons proposé un outil permettant d'extraire les connaissances et d'assister l'expert lors de la validation de celles-ci.
Les différents résultats obtenus montrent qu'il est possible d'obtenir des connaissances intéressantes à partir de données textuelles en minimisant la sollicitation de l'expert dans la phase d'extraction des règles d'association.
Fize, Jacques. "Mise en correspondance de données textuelles hétérogènes fondée sur la dimension spatiale." Thesis, Montpellier, 2019. http://www.theses.fr/2019MONTS099.
Full textWith the rise of Big Data, the processing of Volume, Velocity (growth and evolution) and data Variety concentrates the efforts of communities to exploit these new resources. These new resources have become so important that they are considered the new "black gold". In recent years, volume and velocity have been aspects of the data that are controlled, unlike variety, which remains a major challenge. This thesis presents two contributions in the field of heterogeneous data matching, with a focus on the spatial dimension.The first contribution is based on a two-step process for matching heterogeneous textual data: georepresentation and geomatching. In the first phase, we propose to represent the spatial dimension of each document in a corpus through a dedicated structure, the Spatial Textual Representation (STR). This graph representation is composed of the spatial entities identified in the document, as well as the spatial relationships they maintain. To identify the spatial entities of a document and their spatial relationships, we propose a dedicated resource, called Geodict. The second phase, geomatching, computes the similarity between the generated representations (STR). Based on the nature of the STR structure (i.e. graph), different algorithms of graph matching were studied. To assess the relevance of a match, we propose a set of 6 criteria based on a definition of the spatial similarity between two documents.The second contribution is based on the thematic dimension of textual data and its participation in the spatial matching process. We propose to identify the themes that appear in the same contextual window as certain spatial entities. The objective is to induce some of the implicit spatial similarities between the documents. To do this, we propose to extend the structure of STR using two concepts: the thematic entity and the thematic relationship. The thematic entity represents a concept specific to a particular field (agronomic, medical) and represented according to different spellings present in a terminology resource, in this case a vocabulary. A thematic relationship links a spatial entity to a thematic entity if they appear in the same window. The selected vocabularies and the new form of STR integrating the thematic dimension are evaluated according to their coverage on the studied corpora, as well as their contributions to the heterogeneous textual matching process on the spatial dimension
Holat, Pierre. "Fouille de motifs et modélisation statistique pour l'extraction de connaissances textuelles." Thesis, Sorbonne Paris Cité, 2018. http://www.theses.fr/2018USPCD045.
Full textIn natural language processing, two main approaches are used : machine learning and data mining. In this context, cross-referencing data mining methods based on patterns and statistical machine learning methods is apromising but hardly explored avenue. In this thesis, we present three major contributions: the introduction of delta-free patterns, used as statistical model features; the introduction of a semantic similarity constraint for the mining, calculated using a statistical model; and the introduction of sequential labeling rules, created from the patterns and selected by a statistical model
Séguéla, Julie. "Fouille de données textuelles et systèmes de recommandation appliqués aux offres d'emploi diffusées sur le web." Thesis, Paris, CNAM, 2012. http://www.theses.fr/2012CNAM0801/document.
Full textLast years, e-recruitment expansion has led to the multiplication of web channels dedicated to job postings. In an economic context where cost control is fundamental, assessment and comparison of recruitment channel performances have become necessary. The purpose of this work is to develop a decision-making tool intended to guide recruiters while they are posting a job on the Internet. This tool provides to recruiters the expected performance on job boards for a given job offer. First, we identify the potential predictors of a recruiting campaign performance. Then, we apply text mining techniques to the job offer texts in order to structure postings and to extract information relevant to improve their description in a predictive model. The job offer performance predictive algorithm is based on a hybrid recommender system, suitable to the cold-start problem. The hybrid system, based on a supervised similarity measure, outperforms standard multivariate models. Our experiments are led on a real dataset, coming from a job posting database
Séguéla, Julie. "Fouille de données textuelles et systèmes de recommandation appliqués aux offres d'emploi diffusées sur le web." Electronic Thesis or Diss., Paris, CNAM, 2012. http://www.theses.fr/2012CNAM0801.
Full textLast years, e-recruitment expansion has led to the multiplication of web channels dedicated to job postings. In an economic context where cost control is fundamental, assessment and comparison of recruitment channel performances have become necessary. The purpose of this work is to develop a decision-making tool intended to guide recruiters while they are posting a job on the Internet. This tool provides to recruiters the expected performance on job boards for a given job offer. First, we identify the potential predictors of a recruiting campaign performance. Then, we apply text mining techniques to the job offer texts in order to structure postings and to extract information relevant to improve their description in a predictive model. The job offer performance predictive algorithm is based on a hybrid recommender system, suitable to the cold-start problem. The hybrid system, based on a supervised similarity measure, outperforms standard multivariate models. Our experiments are led on a real dataset, coming from a job posting database
Zenasni, Sarah. "Extraction d'information spatiale à partir de données textuelles non-standards." Thesis, Montpellier, 2018. http://www.theses.fr/2018MONTS076/document.
Full textThe extraction of spatial information from textual data has become an important research topic in the field of Natural Language Processing (NLP). It meets a crucial need in the information society, in particular, to improve the efficiency of Information Retrieval (IR) systems for different applications (tourism, spatial planning, opinion analysis, etc.). Such systems require a detailed analysis of the spatial information contained in the available textual data (web pages, e-mails, tweets, SMS, etc.). However, the multitude and the variety of these data, as well as the regular emergence of new forms of writing, make difficult the automatic extraction of information from such corpora.To meet these challenges, we propose, in this thesis, new text mining approaches allowing the automatic identification of variants of spatial entities and relations from textual data of the mediated communication. These approaches are based on three main contributions that provide intelligent navigation methods. Our first contribution focuses on the problem of recognition and identification of spatial entities from short messages corpora (SMS, tweets) characterized by weakly standardized modes of writing. The second contribution is dedicated to the identification of new forms/variants of spatial relations from these specific corpora. Finally, the third contribution concerns the identification of the semantic relations associated withthe textual spatial information
Pantin, Jérémie. "Détection et caractérisation sémantique de données textuelles aberrantes." Electronic Thesis or Diss., Sorbonne université, 2023. https://accesdistant.sorbonne-universite.fr/login?url=https://theses-intra.sorbonne-universite.fr/2023SORUS347.pdf.
Full textMachine learning answers to the problem of handling dedicated tasks with a wide variety of data. Such algorithms can be either simple or difficult to handle depending of the data. Low dimensional data (2-dimension or 3-dimension) with an intuitive representation (average of baguette price by years) are easier to interpret/explain for a human than data with thousands of dimensions. For low dimensional data, the error leads to a significant shift against normal data, but for the case of high dimensional data it is different. Outlier detection (or anomaly detection, or novelty detection) is the study of outlying observations for detecting what is normal and abnormal. Methods that perform such task are algorithms, methods or models that are based on data distributions. Different families of approaches can be found in the literature of outlier detection, and they are mainly independent of ground truth. They perform outlier analysis by detecting the principal behaviors of majority of observations. Thus, data that differ from normal distribution are considered noise or outlier. We detail the application of outlier detection with text. Despite recent progress in natural language processing, computer still lack profound understanding of human language in absence of information. For instance, the sentence "A smile is a curve that set everything straight" has several levels of understanding and a machine can encounter hardship to chose the right level of lecture. This thesis presents the analysis of high-dimensional outliers, applied to text. Recent advances in anomaly detection and outlier detection are not significantly represented with text data and we propose to highlight the main differences with high-dimensional outliers. We also approach ensemble methods that are nearly nonexistent in the literature for our context. Finally, an application of outlier detection for elevate results on abstractive summarization is conducted. We propose GenTO, a method that prepares and generates split of data in which anomalies and outliers are inserted. Based on this method, evaluation and benchmark of outlier detection approaches is proposed with documents. The proposed taxonomy allow to identify difficult and hierarchised outliers that the literature tackles without knowing. Also, learning without supervision often leads models to rely in some hyperparameter. For instance, Local Outlier Factor relies to the k-nearest neighbors for computing the local density. Thus, choosing the right value for k is crucial. In this regard, we explore the influence of such parameter for text data. While choosing one model can leads to obvious bias against real-world data, ensemble methods allow to mitigate such problem. They are particularly efficient with outlier analysis. Indeed, the selection of several values for one hyperparameter can help to detect strong outliers.Importance is then tackled and can help a human to understand the output of black box model. Thus, the interpretability of outlier detection models is questioned. We find that for numerous dataset, a low number of features can be selected as oracle. The association of complete models and restrained models helps to mitigate the black-box effect of some approaches. In some cases, outlier detection refers to noise removal or anomaly detection. Some applications can benefit from the characteristic of such task. Mail spam detection and fake news detection are one example, but we propose to use outlier detection approaches for weak signal exploration in marketing project. Thus, we find that the model of the literature help to improve unsupervised abstractive summarization, and also to find weak signals in text
Hussain, Syed Fawad. "Une nouvelle mesure de co-similarité : applications aux données textuelles et génomique." Phd thesis, Grenoble, 2010. http://www.theses.fr/2010GRENM049.
Full textClustering is the unsupervised classification of patterns (observations, data items, or feature vectors) into homogeneous and contrasted groups (clusters As datasets become larger and more varied, adaptations to existing algorithms are required to maintain the quality of cluster. Ln this regard, high¬dimensional data poses sorne problems for traditional clustering algorithms known as the curse of dimensionality. This thesis proposes a co-similarity based algorithm that is based on the concept of higher-order co-occurrences, which are extracted from the given data. Ln the case of text analysis, for example, document similarity is calculated based on word similarity, which in turn is calculated on the basis of document similarity. Using this iterative approach, we can bring similar documents closer together even if they do not share the same words but share similar words. This approach doesn't need externallinguistic resources like a thesaurus Furthermore this approach can also be extended to incorporate prior knowledge from a training dataset for the task of text categorization. Prior categor labels coming from data in the training set can be used to influence similarity measures between worlds to better classify incoming test dataset among the different categories. Thus, the same conceptual approach, that can be expressed in the framework of the graph theory, can be used for both clustering and categorization task depending on the amount of prior information available. Our results show significant increase in the accuracy with respect to the state of the art of both one-way and two-way clustering on the different datasets that were tested
Hussain, Syed Fawad. "Une Nouvelle Mesure de Co-Similarité : Applications aux Données Textuelles et Génomique." Phd thesis, Grenoble, 2010. http://tel.archives-ouvertes.fr/tel-00525366.
Full textEl, Haddadi Anass. "Fouille multidimensionnelle sur les données textuelles visant à extraire les réseaux sociaux et sémantiques pour leur exploitation via la téléphonie mobile." Toulouse 3, 2011. http://thesesups.ups-tlse.fr/1378/.
Full textCompetition is a fundamental concept of the liberal economy tradition that requires companies to resort to Competitive Intelligence (CI) in order to be advantageously positioned on the market, or simply to survive. Nevertheless, it is well known that it is not the strongest of the organizations that survives, nor the most intelligent, but rather, the one most adaptable to change, the dominant factor in society today. Therefore, companies are required to remain constantly on a wakeful state to watch for any change in order to make appropriate solutions in real time. However, for a successful vigil, we should not be satisfied merely to monitor the opportunities, but before all, to anticipate risks. The external risk factors have never been so many: extremely dynamic and unpredictable markets, new entrants, mergers and acquisitions, sharp price reduction, rapid changes in consumption patterns and values, fragility of brands and their reputation. To face all these challenges, our research consists in proposing a Competitive Intelligence System (CIS) designed to provide online services. Through descriptive and statistics exploratory methods of data, Xplor EveryWhere display, in a very short time, new strategic knowledge such as: the profile of the actors, their reputation, their relationships, their sites of action, their mobility, emerging issues and concepts, terminology, promising fields etc. The need for security in XPlor EveryWhere arises out of the strategic nature of information conveyed with quite a substantial value. Such security should not be considered as an additional option that a CIS can provide just in order to be distinguished from one another. Especially as the leak of this information is not the result of inherent weaknesses in corporate computer systems, but above all it is an organizational issue. With Xplor EveryWhere we completed the reporting service, especially the aspect of mobility. Lastly with this system, it's possible to: View updated information as we have access to our strategic database server in real-time, itself fed daily by watchmen. They can enter information at trade shows, customer visits or after meetings
Garcelon, Nicolas. "Problématique des entrepôts de données textuelles : dr Warehouse et la recherche translationnelle sur les maladies rares." Thesis, Sorbonne Paris Cité, 2017. http://www.theses.fr/2017USPCB257/document.
Full textThe repurposing of clinical data for research has become widespread with the development of clinical data warehouses. These data warehouses are modeled to integrate and explore structured data related to thesauri. These data come mainly from machine (biology, genetics, cardiology, etc.) but also from manual data input forms. The production of care is also largely providing textual data from hospital reports (hospitalization, surgery, imaging, anatomopathologic etc.), free text areas in electronic forms. This mass of data, little used by conventional warehouses, is an indispensable source of information in the context of rare diseases. Indeed, the free text makes it possible to describe the clinical picture of a patient with more precision and expressing the absence of signs and uncertainty. Particularly for patients still undiagnosed, the doctor describes the patient's medical history outside any nosological framework. This wealth of information makes clinical text a valuable source for translational research. However, this requires appropriate algorithms and tools to enable optimized re-use by doctors and researchers. We present in this thesis the data warehouse centered on the clinical document, which we have modeled, implemented and evaluated. In three cases of use for translational research in the context of rare diseases, we attempted to address the problems inherent in textual data: (i) recruitment of patients through a search engine adapted to textual (data negation and family history detection), (ii) automated phenotyping from textual data, and (iii) diagnosis by similarity between patients based on phenotyping. We were able to evaluate these methods on the data warehouse of Necker-Enfants Malades created and fed during this thesis, integrating about 490,000 patients and 4 million reports. These methods and algorithms were integrated into the software Dr Warehouse developed during the thesis and distributed in Open source since September 2017
Ramiandrisoa, Iarivony. "Extraction et fouille de données textuelles : application à la détection de la dépression, de l'anorexie et de l'agressivité dans les réseaux sociaux." Thesis, Toulouse 3, 2020. http://www.theses.fr/2020TOU30191.
Full textOur research mainly focuses on tasks with an application purpose: depression and anorexia detection on the one hand and aggression detection on the other; this from messages posted by users on a social media platform. We have also proposed an unsupervised method of keyphrases extraction. These three pieces of work were initiated at different times during this thesis work. Our first contribution concerns the automatic keyphrases extraction from scientific documents or news articles. More precisely, we improve an unsupervised graph-based method to solve the weaknesses of graph-based methods by combining existing solutions. We evaluated our approach on eleven data collections including five containing long documents, four containing short documents and finally two containing news articles. We have shown that our proposal improves the results in certain contexts. The second contribution of this thesis is to provide a solution for early depression and anorexia detection. We proposed models that use classical classifiers, namely logistic regression and random forest, based on : (a) features and (b) sentence embedding. We evaluated our models on the eRisk data collections. We have observed that feature-based models perform very well on precision-oriented measures both for depression or anorexia detection. The model based on sentence embedding is more efficient on ERDE_50 and recall-oriented measures. We also obtained better results compared to the state-of-the-art on precision and ERDE_50 for depression detection, and on precision and recall for anorexia detection. Our last contribution is to provide an approach for aggression detection in messages posted by users on social networks. We reused the same models used for depression or anorexia detection to create models. We added other models based on deep learning approach. We evaluated our models on the data collections of TRAC shared task. We observed that our models using deep learning provide better results than our models using classical classifiers. Our results in this part of the thesis are in the middle (fifth or ninth results) compared to the competitors. We still got the best result on one of the data collections
Dermouche, Mohamed. "Modélisation conjointe des thématiques et des opinions : application à l'analyse des données textuelles issues du Web." Thesis, Lyon 2, 2015. http://www.theses.fr/2015LYO22007/document.
Full textThis work is located at the junction of two domains : topic modeling and sentiment analysis. The problem that we propose to tackle is the joint and dynamic modeling of topics (subjects) and sentiments (opinions) on the Web. In the literature, the task is usually divided into sub-tasks that are treated separately. The models that operate this way fail to capture the topic-sentiment interaction and association. In this work, we propose a joint modeling of topics and sentiments, by taking into account associations between them. We are also interested in the dynamics of topic-sentiment associations. To this end, we adopt a statistical approach based on the probabilistic topic models. Our main contributions can be summarized in two points : 1. TS (Topic-Sentiment model) : a new probabilistic topic model for the joint extraction of topics and sentiments. This model allows to characterize the extracted topics with distributions over the sentiment polarities. The goal is to discover the sentiment proportions specfic to each of theextracted topics. 2. TTS (Time-aware Topic-Sentiment model) : a new probabilistic model to caracterize the topic-sentiment dynamics. Relying on the document's time information, TTS allows to characterize the quantitative evolutionfor each of the extracted topic-sentiment pairs. We also present two other contributions : a new evaluation framework for measuring the performance of topic-extraction methods, and a new hybrid method for sentiment detection and classification from text. This method is based on combining supervised machine learning and prior knowledge. All of the proposed methods are tested on real-world data based on adapted evaluation frameworks
Egho, Elias. "Extraction de motifs séquentiels dans des données séquentielles multidimensionnelles et hétérogènes : une application à l'analyse de trajectoires de patients." Thesis, Université de Lorraine, 2014. http://www.theses.fr/2014LORR0066/document.
Full textAll domains of science and technology produce large and heterogeneous data. Although a lot of work was done in this area, mining such data is still a challenge. No previous research work targets the mining of heterogeneous multidimensional sequential data. This thesis proposes a contribution to knowledge discovery in heterogeneous sequential data. We study three different research directions: (i) Extraction of sequential patterns, (ii) Classification and (iii) Clustering of sequential data. Firstly we generalize the notion of a multidimensional sequence by considering complex and heterogeneous sequential structure. We present a new approach called MMISP to extract sequential patterns from heterogeneous sequential data. MMISP generates a large number of sequential patterns as this is usually the case for pattern enumeration algorithms. To overcome this problem, we propose a novel way of considering heterogeneous multidimensional sequences by mapping them into pattern structures. We develop a framework for enumerating only patterns satisfying given constraints. The second research direction is in concern with the classification of heterogeneous multidimensional sequences. We use Formal Concept Analysis (FCA) as a classification method. We show interesting properties of concept lattices and of stability index to classify sequences into a concept lattice and to select some interesting groups of sequences. The third research direction in this thesis is in concern with the clustering of heterogeneous multidimensional sequential data. We focus on the notion of common subsequences to define similarity between a pair of sequences composed of a list of itemsets. We use this similarity measure to build a similarity matrix between sequences and to separate them in different groups. In this work, we present theoretical results and an efficient dynamic programming algorithm to count the number of common subsequences between two sequences without enumerating all subsequences. The system resulting from this research work was applied to analyze and mine patient healthcare trajectories in oncology. Data are taken from a medico-administrative database including all information about the hospitalizations of patients in Lorraine Region (France). The system allows to identify and characterize episodes of care for specific sets of patients. Results were discussed and validated with domain experts
Siolas, Georges. "Modèles probabilistes et noyaux pour l'extraction d'informations à partir de documents." Paris 6, 2003. http://www.theses.fr/2003PA066487.
Full textEgho, Elias. "Extraction de motifs séquentiels dans des données séquentielles multidimensionnelles et hétérogènes : une application à l'analyse de trajectoires de patients." Electronic Thesis or Diss., Université de Lorraine, 2014. http://www.theses.fr/2014LORR0066.
Full textAll domains of science and technology produce large and heterogeneous data. Although a lot of work was done in this area, mining such data is still a challenge. No previous research work targets the mining of heterogeneous multidimensional sequential data. This thesis proposes a contribution to knowledge discovery in heterogeneous sequential data. We study three different research directions: (i) Extraction of sequential patterns, (ii) Classification and (iii) Clustering of sequential data. Firstly we generalize the notion of a multidimensional sequence by considering complex and heterogeneous sequential structure. We present a new approach called MMISP to extract sequential patterns from heterogeneous sequential data. MMISP generates a large number of sequential patterns as this is usually the case for pattern enumeration algorithms. To overcome this problem, we propose a novel way of considering heterogeneous multidimensional sequences by mapping them into pattern structures. We develop a framework for enumerating only patterns satisfying given constraints. The second research direction is in concern with the classification of heterogeneous multidimensional sequences. We use Formal Concept Analysis (FCA) as a classification method. We show interesting properties of concept lattices and of stability index to classify sequences into a concept lattice and to select some interesting groups of sequences. The third research direction in this thesis is in concern with the clustering of heterogeneous multidimensional sequential data. We focus on the notion of common subsequences to define similarity between a pair of sequences composed of a list of itemsets. We use this similarity measure to build a similarity matrix between sequences and to separate them in different groups. In this work, we present theoretical results and an efficient dynamic programming algorithm to count the number of common subsequences between two sequences without enumerating all subsequences. The system resulting from this research work was applied to analyze and mine patient healthcare trajectories in oncology. Data are taken from a medico-administrative database including all information about the hospitalizations of patients in Lorraine Region (France). The system allows to identify and characterize episodes of care for specific sets of patients. Results were discussed and validated with domain experts
Haddad, Mohamed Hatem. "Extraction et impact des connaissances sur les performances des systèmes de recherche d'information." Phd thesis, Université Joseph Fourier (Grenoble), 2002. http://tel.archives-ouvertes.fr/tel-00004459.
Full textKarouach, Saïd. "Visualisations interactives pour la découverte de connaissances, concepts, méthodes et outils." Toulouse 3, 2003. http://www.theses.fr/2003TOU30082.
Full textHô, Dinh Océane. "Caractérisation différentielle de forums de discussion sur le VIH en vietnamien et en français : Éléments pour la fouille comportementale du web social." Thesis, Sorbonne Paris Cité, 2017. http://www.theses.fr/2017USPCF022/document.
Full textThe standard discourse produced by official organisations is confronted with the unofficial or informal discourse of the social web. Empowering people to express themselves results in a new balance of authority, when it comes to knowledge and changes the way people learn. Social web discourse is available to each and everyone and its size is growing fast, which opens up new fields for both humanities and social sciences to investigate. The latter, however, are not equipped to engage with such complex and little-analysed data. The aim of this dissertation is to investigate how far social web discourse can help supplement official discourse. In it we set out a method to collect and analyse data that is in line with the characteristics of a digital environment, namely data size, anonymity, transience, structure. We focus on forums, where such discourse is built, and test our method on a specific social issue, ie the HIV/AIDS epidemic in Vietnam. This field of investigation encompasses several related questions that have to do with health, society, the evolution of morals, the mismatch between different kinds of discourse. Our study is also grounded in the analysis of a comparable French corpus dealing with the same topic, whose genre and discourse characteristics are equivalent to those of the Vietnamese one: this two-pronged research highlights the specific features of different socio-cultural environments
Saneifar, Hassan. "Locating Information in Heterogeneous log files." Thesis, Montpellier 2, 2011. http://www.theses.fr/2011MON20092/document.
Full textIn this thesis, we present contributions to the challenging issues which are encounteredin question answering and locating information in complex textual data, like log files. Question answering systems (QAS) aim to find a relevant fragment of a document which could be regarded as the best possible concise answer for a question given by a user. In this work, we are looking to propose a complete solution to locate information in a special kind of textual data, i.e., log files generated by EDA design tools.Nowadays, in many application areas, modern computing systems are instrumented to generate huge reports about occurring events in the format of log files. Log files are generated in every computing field to report the status of systems, products, or even causes of problems that can occur. Log files may also include data about critical parameters, sensor outputs, or a combination of those. Analyzing log files, as an attractive approach for automatic system management and monitoring, has been enjoying a growing amount of attention [Li et al., 2005]. Although the process of generating log files is quite simple and straightforward, log file analysis could be a tremendous task that requires enormous computational resources, long time and sophisticated procedures [Valdman, 2004]. Indeed, there are many kinds of log files generated in some application domains which are not systematically exploited in an efficient way because of their special characteristics. In this thesis, we are mainly interested in log files generated by Electronic Design Automation (EDA) systems. Electronic design automation is a category of software tools for designing electronic systems such as printed circuit boards and Integrated Circuits (IC). In this domain, to ensure the design quality, there are some quality check rules which should be verified. Verification of these rules is principally performed by analyzing the generated log files. In the case of large designs that the design tools may generate megabytes or gigabytes of log files each day, the problem is to wade through all of this data to locate the critical information we need to verify the quality check rules. These log files typically include a substantial amount of data. Accordingly, manually locating information is a tedious and cumbersome process. Furthermore, the particular characteristics of log files, specially those generated by EDA design tools, rise significant challenges in retrieval of information from the log files. The specific features of log files limit the usefulness of manual analysis techniques and static methods. Automated analysis of such logs is complex due to their heterogeneous and evolving structures and the large non-fixed vocabulary.In this thesis, by each contribution, we answer to questions raised in this work due to the data specificities or domain requirements. We investigate throughout this work the main concern "how the specificities of log files can influence the information extraction and natural language processing methods?". In this context, a key challenge is to provide approaches that take the log file specificities into account while considering the issues which are specific to QA in restricted domains. We present different contributions as below:> Proposing a novel method to recognize and identify the logical units in the log files to perform a segmentation according to their structure. We thus propose a method to characterize complex logicalunits found in log files according to their syntactic characteristics. Within this approach, we propose an original type of descriptor to model the textual structure and layout of text documents.> Proposing an approach to locate the requested information in the log files based on passage retrieval. To improve the performance of passage retrieval, we propose a novel query expansion approach to adapt an initial query to all types of corresponding log files and overcome the difficulties like mismatch vocabularies. Our query expansion approach relies on two relevance feedback steps. In the first one, we determine the explicit relevance feedback by identifying the context of questions. The second phase consists of a novel type of pseudo relevance feedback. Our method is based on a new term weighting function, called TRQ (Term Relatedness to Query), introduced in this work, which gives a score to terms of corpus according to their relatedness to the query. We also investigate how to apply our query expansion approach to documents from general domains.> Studying the use of morpho-syntactic knowledge in our approaches. For this purpose, we are interested in the extraction of terminology in the log files. Thus, we here introduce our approach, named Exterlog (EXtraction of TERminology from LOGs), to extract the terminology of log files. To evaluate the extracted terms and choose the most relevant ones, we propose a candidate term evaluation method using a measure, based on the Web and combined with statistical measures, taking into account the context of log files
Ailem, Melissa. "Sparsity-sensitive diagonal co-clustering algorithms for the effective handling of text data." Thesis, Sorbonne Paris Cité, 2016. http://www.theses.fr/2016USPCB087.
Full textIn the current context, there is a clear need for Text Mining techniques to analyse the huge quantity of unstructured text documents available on the Internet. These textual data are often represented by sparse high dimensional matrices where rows and columns represent documents and terms respectively. Thus, it would be worthwhile to simultaneously group these terms and documents into meaningful clusters, making this substantial amount of data easier to handle and interpret. Co-clustering techniques just serve this purpose. Although many existing co-clustering approaches have been successful in revealing homogeneous blocks in several domains, these techniques are still challenged by the high dimensionality and sparsity characteristics exhibited by document-term matrices. Due to this sparsity, several co-clusters are primarily composed of zeros. While homogeneous, these co-clusters are irrelevant and must be filtered out in a post-processing step to keep only the most significant ones. The objective of this thesis is to propose new co-clustering algorithms tailored to take into account these sparsity-related issues. The proposed algorithms seek a block diagonal structure and allow to straightaway identify the most useful co-clusters, which makes them specially effective for the text co-clustering task. Our contributions can be summarized as follows: First, we introduce and demonstrate the effectiveness of a novel co-clustering algorithm based on a direct maximization of graph modularity. While existing graph-based co-clustering algorithms rely on spectral relaxation, the proposed algorithm uses an iterative alternating optimization procedure to reveal the most meaningful co-clusters in a document-term matrix. Moreover, the proposed optimization has the advantage of avoiding the computation of eigenvectors, a task which is prohibitive when considering high dimensional data. This is an improvement over spectral approaches, where the eigenvectors computation is necessary to perform the co-clustering. Second, we use an even more powerful approach to discover block diagonal structures in document-term matrices. We rely on mixture models, which offer strong theoretical foundations and considerable flexibility that makes it possible to uncover various specific cluster structure. More precisely, we propose a rigorous probabilistic model based on the Poisson distribution and the well known Latent Block Model. Interestingly, this model includes the sparsity in its formulation, which makes it particularly effective for text data. Setting the estimate of this model’s parameters under the Maximum Likelihood (ML) and the Classification Maximum Likelihood (CML) approaches, four co-clustering algorithms have been proposed, including a hard, a soft, a stochastic and a fourth algorithm which leverages the benefits of both the soft and stochastic variants, simultaneously. As a last contribution of this thesis, we propose a new biomedical text mining framework that includes some of the above mentioned co-clustering algorithms. This work shows the contribution of co-clustering in a real biomedical text mining problematic. The proposed framework is able to propose new clues about the results of genome wide association studies (GWAS) by mining PUBMED abstracts. This framework has been tested on asthma disease and allowed to assess the strength of associations between asthma genes reported in previous GWAS as well as discover new candidate genes likely associated to asthma. In a nutshell, while several text co-clustering algorithms already exist, their performance can be substantially increased if more appropriate models and algorithms are available. According to the extensive experiments done on several challenging real-world text data sets, we believe that this thesis has served well this objective
Ailem, Melissa. "Sparsity-sensitive diagonal co-clustering algorithms for the effective handling of text data." Electronic Thesis or Diss., Sorbonne Paris Cité, 2016. http://www.theses.fr/2016USPCB087.
Full textIn the current context, there is a clear need for Text Mining techniques to analyse the huge quantity of unstructured text documents available on the Internet. These textual data are often represented by sparse high dimensional matrices where rows and columns represent documents and terms respectively. Thus, it would be worthwhile to simultaneously group these terms and documents into meaningful clusters, making this substantial amount of data easier to handle and interpret. Co-clustering techniques just serve this purpose. Although many existing co-clustering approaches have been successful in revealing homogeneous blocks in several domains, these techniques are still challenged by the high dimensionality and sparsity characteristics exhibited by document-term matrices. Due to this sparsity, several co-clusters are primarily composed of zeros. While homogeneous, these co-clusters are irrelevant and must be filtered out in a post-processing step to keep only the most significant ones. The objective of this thesis is to propose new co-clustering algorithms tailored to take into account these sparsity-related issues. The proposed algorithms seek a block diagonal structure and allow to straightaway identify the most useful co-clusters, which makes them specially effective for the text co-clustering task. Our contributions can be summarized as follows: First, we introduce and demonstrate the effectiveness of a novel co-clustering algorithm based on a direct maximization of graph modularity. While existing graph-based co-clustering algorithms rely on spectral relaxation, the proposed algorithm uses an iterative alternating optimization procedure to reveal the most meaningful co-clusters in a document-term matrix. Moreover, the proposed optimization has the advantage of avoiding the computation of eigenvectors, a task which is prohibitive when considering high dimensional data. This is an improvement over spectral approaches, where the eigenvectors computation is necessary to perform the co-clustering. Second, we use an even more powerful approach to discover block diagonal structures in document-term matrices. We rely on mixture models, which offer strong theoretical foundations and considerable flexibility that makes it possible to uncover various specific cluster structure. More precisely, we propose a rigorous probabilistic model based on the Poisson distribution and the well known Latent Block Model. Interestingly, this model includes the sparsity in its formulation, which makes it particularly effective for text data. Setting the estimate of this model’s parameters under the Maximum Likelihood (ML) and the Classification Maximum Likelihood (CML) approaches, four co-clustering algorithms have been proposed, including a hard, a soft, a stochastic and a fourth algorithm which leverages the benefits of both the soft and stochastic variants, simultaneously. As a last contribution of this thesis, we propose a new biomedical text mining framework that includes some of the above mentioned co-clustering algorithms. This work shows the contribution of co-clustering in a real biomedical text mining problematic. The proposed framework is able to propose new clues about the results of genome wide association studies (GWAS) by mining PUBMED abstracts. This framework has been tested on asthma disease and allowed to assess the strength of associations between asthma genes reported in previous GWAS as well as discover new candidate genes likely associated to asthma. In a nutshell, while several text co-clustering algorithms already exist, their performance can be substantially increased if more appropriate models and algorithms are available. According to the extensive experiments done on several challenging real-world text data sets, we believe that this thesis has served well this objective
Duchêne, Florence. "Fusion de Données Multicapteurs pour un Système de Télésurveillance Médicale de Personnes à Domicile." Phd thesis, Université Joseph Fourier (Grenoble), 2004. http://tel.archives-ouvertes.fr/tel-00007607.
Full textMorbieu, Stanislas. "Leveraging textual embeddings for unsupervised learning." Electronic Thesis or Diss., Université Paris Cité, 2020. http://www.theses.fr/2020UNIP5191.
Full textTextual data is ubiquitous and is a useful information pool for many companies. In particular, the web provides an almost inexhaustible source of textual data that can be used for recommendation systems, business or technological watch, information retrieval, etc. Recent advances in natural language processing have made possible to capture the meaning of words in their context in order to improve automatic translation systems, text summary, or even the classification of documents according to predefined categories. However, the majority of these applications often rely on a significant human intervention to annotate corpora: This annotation consists, for example in the context of supervised classification, in providing algorithms with examples of assigning categories to documents. The algorithm therefore learns to reproduce human judgment in order to apply it for new documents. The object of this thesis is to take advantage of these latest advances which capture the semantic of the text and use it in an unsupervised framework. The contributions of this thesis revolve around three main axes. First, we propose a method to transfer the information captured by a neural network for co-clustering of documents and words. Co-clustering consists in partitioning the two dimensions of a data matrix simultaneously, thus forming both groups of similar documents and groups of coherent words. This facilitates the interpretation of a large corpus of documents since it is possible to characterize groups of documents by groups of words, thus summarizing a large corpus of text. More precisely, we train the Paragraph Vectors algorithm on an augmented dataset by varying the different hyperparameters, classify the documents from the different vector representations and apply a consensus algorithm on the different partitions. A constrained co-clustering of the co-occurrence matrix between terms and documents is then applied to maintain the consensus partitioning. This method is found to result in significantly better quality of document partitioning on various document corpora and provides the advantage of the interpretation offered by the co-clustering. Secondly, we present a method for evaluating co-clustering algorithms by exploiting vector representations of words called word embeddings. Word embeddings are vectors constructed using large volumes of text, one major characteristic of which is that two semantically close words have word embeddings close by a cosine distance. Our method makes it possible to measure the matching between the partition of the documents and the partition of the words, thus offering in a totally unsupervised setting a measure of the quality of the co-clustering. Thirdly, we are interested in recommending classified ads. We present a system that allows to recommend similar classified ads when consulting one. The descriptions of classified ads are often short, syntactically incorrect, and the use of synonyms makes it difficult for traditional systems to accurately measure semantic similarity. In addition, the high renewal rate of classified ads that are still valid (product not sold) implies choices that make it possible to have low computation time. Our method, simple to implement, responds to this use case and is again based on word embeddings. The use of these has advantages but also involves some difficulties: the creation of such vectors requires choosing the values of some parameters, and the difference between the corpus on which the word embeddings were built upstream. and the one on which they are used raises the problem of out-of-vocabulary words, which have no vector representation. To overcome these problems, we present an analysis of the impact of the different parameters on word embeddings as well as a study of the methods allowing to deal with the problem of out-of-vocabulary words
Yahaya, Alassan Mahaman Sanoussi. "Amélioration du système de recueils d'information de l'entreprise Semantic Group Company grâce à la constitution de ressources sémantiques." Thesis, Paris 10, 2017. http://www.theses.fr/2017PA100086/document.
Full textTaking into account the semantic aspect of the textual data during the classification task has become a real challenge in the last ten years. This difficulty is in addition to the fact that most of the data available on social networks are short texts, which in particular results in making methods based on the "bag of words" representation inefficient. The approach proposed in this research project is different from the approaches proposed in previous work on the enrichment of short messages for three reasons. First, we do not use external knowledge like Wikipedia because typically short messages that are processed by the company come from specific domains. Secondly, the data to be processed are not used for the creation of resources because of the operation of the tool. Thirdly, to our knowledge there is no work on the one hand, which uses structured data such as the company's data to constitute semantic resources, and on the other hand, which measure the impact of enrichment on a system Interactive grouping of text flows. In this thesis, we propose the creation of resources enabling to enrich the short messages in order to improve the performance of the tool of the semantic grouping of the company Succeed Together. The tool implements supervised and unsupervised classification methods. To build these resources, we use sequential data mining techniques