Dissertations / Theses on the topic 'Système de recommandation sémantique'
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 'Système de recommandation sémantique.'
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.
Lemdani, Roza. "Système hybride d'adaptation dans les systèmes de recommandation." Thesis, Université Paris-Saclay (ComUE), 2016. http://www.theses.fr/2016SACLC050/document.
Full textRecommender systems are tools used to present users with items that might interest them. Such systems use algorithms that rely on the domain application. These algorithms are then executed for each user in order to find the most relevant recommendations for him, without taking into account his specific needs.In this thesis, we define a hybrid recommender system which combines several recommendation algorithms in order to obtain more accurate recommendations. Moreover, the defined approach relies on the structure of the input ontology, which makes the framework reusable, adaptable and domain-independent (music, research papers, films, etc.).We also had an interest in detecting in which kind of recommendations a user responds better in order to adapt the recommendation process to each user category and obtain more targeted recommendations. Finally, our approach can explain each recommendation, which increases the user confidence in the system by proving him that the recommendations are adapted to him. We also allow the user to correct the explanations in order to help the system to get a better understanding of him and avoid non accurate recommendations in the future.Our recommender system has been experimented online with real users and offline by performing a cross-validation on the MovieLens dataset. The results of the experimentation are very satisfying so far
Soualah, Alila Fayrouz. "CAMLearn* : une architecture de système de recommandation sémantique sensible au contexte : application au domaine du m-learning." Thesis, Dijon, 2015. http://www.theses.fr/2015DIJOS032/document.
Full textGiven the rapid emergence of new mobile technologies and the growth of needs of a moving society in training, works are increasing to identify new relevant educational platforms to improve distant learning. The next step in distance learning is porting e-learning to mobile systems. This is called m-learning. So far, learning environment was either defined by an educational setting, or imposed by the educational content. In our approach, in m-learning, we change the paradigm where the system recommends content and adapts learning follow to learner's context
Benouaret, Idir. "Un système de recommandation contextuel et composite pour la visite personnalisée de sites culturels." Thesis, Compiègne, 2017. http://www.theses.fr/2017COMP2332/document.
Full textOur work concerns systems that help users during museum visits and access to cultural heritage. Our goal is to design recommender systems, implemented in mobile devices to improve the experience of the visitor, by recommending him the most relevant items and helping him to personalize the tour he makes. We consider two mainly domains of application : museum visits and tourism. We propose a context-aware hybrid recommender system which uses three different methods : demographic, semantic and collaborative. Every method is adapted to a specific step of the museum tour. First, the demographic approach is used to solve the problem of the cold start. The semantic approach is then activated to recommend to the user artworks that are semantically related to those that the user appreciated. Finally, the collaborative approach is used to recommend to the user artworks that users with similar preferences have appreciated. We used a contextual post filtering to generate personalized museum routes depending on artworks which were recommended and contextual information of the user namely : the physical environment, the location as well as the duration of the visit. In the tourism field, the items to be recommended can be of various types (monuments, parks, museums, etc.). Because of the heterogeneous nature of these points of interest, we proposed a composite recommender system. Every recommendation is a list of points of interest that are organized in a package, where each package may constitute a tour for the user. The objective is to recommend the Top-k packages among those who satisfy the constraints of the user (time, cost, etc.). We define a scoring function which estimates the quality of a package according to three criteria : the estimated appreciation of the user, the popularity of points of interest as well as the diversity of packages. We propose an algorithm inspired by composite retrieval to build the list of recommended packages. The experimental evaluation of the system we proposed using a real world data set crawled from Tripadvisor demonstrates its quality and its ability to improve both the relevance and the diversity of recommendations
Ben, Ticha Sonia. "Recommandation personnalisée hybride." Thesis, Université de Lorraine, 2015. http://www.theses.fr/2015LORR0168/document.
Full textFace to the ongoing rapid expansion of the Internet, user requires help to access to items that may interest her or him. A personalized recommender system filters relevant items from huge catalogue to particular user by observing his or her behavior. The approach based on observing user behavior from his interactions with the website is called usage analysis. Collaborative Filtering and Content-Based filtering are the most widely used techniques in personalized recommender system. Collaborative filtering uses only data from usage analysis to build user profile, while content-based filtering relies in addition on semantic information of items. Hybrid approach is another important technique, which combines collaborative and content-based methods to provide recommendations. The aim of this thesis is to present a new hybridization approach that takes into account the semantic information of items to enhance collaborative recommendations. Several approaches have been proposed for learning a new user profile inferring preferences for semantic information describing items. For each proposed approach, we address the sparsity and the scalability problems. We prove also, empirically, an improvement in recommendations accuracy against collaborative filtering and content-based filtering
Werner, David. "Indexation et recommandation d'informations : vers une qualification précise des items par une approche ontologique, fondée sur une modélisation métier du domaine : application à la recommandation d'articles économiques." Thesis, Dijon, 2015. http://www.theses.fr/2015DIJOS078/document.
Full textEffective management of large amounts of information has become a challenge increasinglyimportant for information systems. Everyday, new information sources emerge on the web. Someonecan easily find what he wants if (s)he seeks an article, a video or a specific artist. However,it becomes quite difficult, even impossible, to have an exploratory approach to discover newcontent. Recommender systems are software tools that aim to assist humans to deal withinformation overload. The work presented in this Phd thesis proposes an architecture for efficientrecommendation of news. In this document, we propose an architecture for efficient recommendationof news articles. Our ontological approach relies on a model for precise characterization of itemsbased on a controlled vocabulary. The ontology contains a formal vocabulary modeling a view on thedomain knowledge. Carried out in collaboration with the company Actualis SARL, this work has ledto the marketing of a new highly competitive product, FristECO Pro’fil
Duthil, Benjamin. "De l'extraction des connaissances à la recommandation." Phd thesis, Montpellier 2, 2012. http://tel.archives-ouvertes.fr/tel-00771504.
Full textTorres, Diego. "Co-Evolution between Social and Semantic Web." Nantes, 2014. https://archive.bu.univ-nantes.fr/pollux/show/show?id=ece31eb7-483b-4ad1-96bd-847476bfc8d6.
Full textSocial and Semantic Web has impacted in the manner of knowledge building is fulfill in the Web. The Social Web promoted the participation of users to create and edit Web content and knowledge. The content proliferation and the need to have a better machine management of such information trigger the Semantic Web. Currently, the Social and the Semantic Web are living together and they share a same topic: a better management of knowledge. However, most of the Social Web information is not part of the Semantic Web, and Semantic Web information is not used to improve the Social Web. This thesis introduced an innovative approach to stimulate a co- evolution between the Semantic and Social Web: social and machine forces work together in order to have mutual benefits. We claim that having a co-evolution between Social and Semantic Web will improve the generation of semantic data and a knowledge production improvement in the Social Web
Lully, Vincent. "Vers un meilleur accès aux informations pertinentes à l’aide du Web sémantique : application au domaine du e-tourisme." Thesis, Sorbonne université, 2018. http://www.theses.fr/2018SORUL196.
Full textThis thesis starts with the observation that there is an increasing infobesity on the Web. The two main types of tools, namely the search engine and the recommender system, which are designed to help us explore the Web data, have several problems: (1) in helping users express their explicit information needs, (2) in selecting relevant documents, and (3) in valuing the selected documents. We propose several approaches using Semantic Web technologies to remedy these problems and to improve the access to relevant information. We propose particularly: (1) a semantic auto-completion approach which helps users formulate longer and richer search queries, (2) several recommendation approaches using the hierarchical and transversal links in knowledge graphs to improve the relevance of the recommendations, (3) a semantic affinity framework to integrate semantic and social data to yield qualitatively balanced recommendations in terms of relevance, diversity and novelty, (4) several recommendation explanation approaches aiming at improving the relevance, the intelligibility and the user-friendliness, (5) two image user profiling approaches and (6) an approach which selects the best images to accompany the recommended documents in recommendation banners. We implemented and applied our approaches in the e-tourism domain. They have been properly evaluated quantitatively with ground-truth datasets and qualitatively through user studies
Patel, Namrata. "Mise en œuvre des préférences dans des problèmes de décision." Thesis, Montpellier, 2016. http://www.theses.fr/2016MONTT286/document.
Full textIntelligent ‘services’ are increasingly used on e-commerce platforms to provide assistance to customers. In this context, preferences have gained rapid interest for their utility in solving problems related with decision making. Research on preferences in AI has shed light on various ways of tackling this problem, ranging from the acquisition of preferences to their formal representation and eventually their proper manipulation. Following a recent trend of stepping back and looking at decision-support systems from the user’s point of view, i.e. designing them on the basis of psychological, linguistic and personal considerations, we take up the task of developing an “intelligent” tool which uses comparative preference statements for personalised decision support. We tackle and contribute to different branches of research on preferences in AI: (1) their acquisition (2) their formal representation and manipulation (3) their implementation. We first address a bottleneck in preference acquisition by proposing a method of acquiring user preferences, expressed in natural language (NL), which favours their formal representation and further manipulation. We then focus on the theoretical aspects of handling comparative preference statements for decision support. We finally describe our tool for product recommendation that uses: (1) a review-based analysis to generate a product database, (2) an interactive preference elicitation unit to guide users to express their preferences, and (3) a reasoning engine that manipulates comparative preference statements to generate a preference-based ordering on outcomes as recommendations
Galopin, Alexandre. "Modélisation ontologique des recommandations de pratique clinique pour une aide à la décision à niveaux d'abstraction variables." Thesis, Paris 6, 2015. http://www.theses.fr/2015PA066202/document.
Full textClinical practice guidelines (CPGs) are elaborated according to evidence-based medicine principles in order to improve healthcare quality. However, even when they are integrated into clinical decision support systems, recommendations are poorly implemented by physicians. Indeed, CPGs are often criticized for their lack of flexibility, and their inability to handle the singularity of patients encountered in clinical practice. In particular, CPGs are usually elaborated for a single pathology whereas patients usually suffer from multiple pathologies and comorbidities. We have proposed a method based on an ontological reasoning to enable the reconciliation of single-pathology CPGs to support the flexible management of patients with multiple pathologies. Knowledge bases are made of decision rules that formalize the content of single-pathology CPGs. Patient criteria are organized by a domain ontology, which allows the generation of a generalization-ordered graph of clinical patient profiles. The ontological reasoning allows to reason at different levels of abstraction to process clinical cases described with different levels of completeness. This method has been implemented in a decision support system called GO-DSS, and applied to the management of patients suffering from both arterial hypertension and type 2 diabetes, on the basis of CPGs produced by the VIDAL company (VIDAL Recos). The prototype and its user interfaces have been qualitatively evaluated by a sample of users including both computer scientists with medical knowledge and physicians with computer skills
Li, Siying. "Context-aware recommender system for system of information systems." Thesis, Compiègne, 2021. http://www.theses.fr/2021COMP2602.
Full textWorking collaboratively is no longer an issue but a reality, what matters today is how to implement collaboration so that it is as successful as possible. However, successful collaboration is not easy and is conditioned by different factors that can influence it. It is therefore necessary to take these impacting factors into account within the context of collaboration for promoting the effectiveness of collaboration. Among the impacting factors, collaborator is a main one, which is closely associated with the effectiveness and success of collaborations. The selection and/or recommendation of collaborators, taking into account the context of collaboration, can greatly influence the success of collaboration. Meanwhile, thanks to the development of information technology, many collaborative tools are available, such as e-mail and real-time chat tools. These tools can be integrated into a web-based collaborative work environment. Such environments allow users to collaborate beyond the limit of geographical distances. During collaboration, users can utilize multiple integrated tools, perform various activities, and thus leave traces of activities that can be exploited. This exploitation will be more precise when the context of collaboration is described. It is therefore worth developing web-based collaborative work environments with a model of the collaboration context. Processing the recorded traces can then lead to context-aware collaborator recommendations that can reinforce the collaboration. To generate collaborator recommendations in web-based Collaborative Working Environments, this thesis focuses on producing context-aware collaborator recommendations by defining, modeling, and processing the collaboration context. To achieve this, we first propose a definition of the collaboration context and choose to build a collaboration context ontology given the advantages of the ontology-based modeling approach. Next, an ontologybased semantic similarity is developed and applied in three different algorithms (i.e., PreF1, PoF1, and PoF2) to generate context-aware collaborator recommendations. Furthermore, we deploy the collaboration context ontology into web-based Collaborative Working Environments by considering an architecture of System of Information Systems from the viewpoint of web-based Collaborative Working Environments. Based on this architecture, a corresponding prototype of web-based Collaborative Working Environment is then constructed. Finally, a dataset of scientific collaborations is employed to test and evaluate the performances of the three context-aware collaborator recommendation algorithms
Gauthier, Luc-Aurélien. "Inférence de liens signés dans les réseaux sociaux, par apprentissage à partir d'interactions utilisateur." Thesis, Paris 6, 2015. http://www.theses.fr/2015PA066639/document.
Full textIn this thesis, we study the semantic of relations between users and, in particular, the antagonistic forces we naturally observe in various social relationships, such as hostility or suspicion. The study of these relationships raises many problems both techniques - because the mathematical arsenal is not really adapted to the negative ties - and practical, due to the difficulty of collecting such data (explaining a negative relationship is perceived as intrusive and inappropriate for many users). That’s why we focus on the alternative solutions consisting in inferring these negative relationships from more widespread content. We use the common judgments about items the users share, which are the data used in recommender systems. We provide three contributions, described in three distinct chapters. In the first one, we discuss the case of agreements about items that may not have the same semantics if they involve appreciated items or not by two users. We will see that disliking the same product does not mean similarity. Afterward, we consider in our second contribution the distributions of user ratings and items ratings in order to measure whether the agreements or disagreements may happen by chance or not, in particular to avoid the user and item biases observed in this type of data. Our third contribution consists in using these results to predict the sign of the links between users from the only positive ties and the common judgments about items, and then without any negative social information
Ben, Souissi Souhir. "Vers une nouvelle génération d'outils d'aide à la décision s'appliquant à la prévention des risques lors de la prescription des antibiotiques : combinaison des technologies Web sémantique et de l'aide multicritère à la décision." Thesis, Valenciennes, 2017. http://www.theses.fr/2017VALE0027/document.
Full textMotivated by the well documented worldwide spread of adverse drug events that are associated to antibiotics usage, as well as the increased danger of antibiotic resistance (caused mainly by inappropriate prescribing and overuse), we propose a general architecture for recommendation systems adapted for this kind of context and we develop a specific system for antibiotic prescription (PARS). The type of context that our architecture covers is characterised by highly risky decisions or decisions with high stakes. Such a system cannot be based on machine learning, since there are no available training data sets or case bases. However, rules of good practice and expert knowledge are available, therefore our system should be able to model and implement them. The proposed solution is intended to be used by a decision maker who must adapt his/her decision both to each subject’s specific needs and characteristics, as well as to different types of evolution. Our approach is based on the combination of semantic technologies with MCDA (Multi-Criteria Decision Aids). The decision support process involves two steps. First, by taking into account the specific application domain, the approach evaluates the relevance of each alternative (action) in order to satisfy the needs of a given subject. The first level of the decision support model aims to select all the alternatives that have the potential to fulfill the subject’s needs. Subsequently, the second level consists of evaluating and sorting the selected alternatives in categories according to their adequacy to the characteristics of the subject. We propose an approach that exploits the knowledge schemes of semantic web technologies (ontologies) and that structures the recommendation rules into a suitable sorting method: the MR-Sort with Veto. By doing so, our solution is able to link and match heterogeneous knowledge sources expressed by experts. In collaboration with the EpiCURA Hospital Center, we have applied this approach in the medical domain and more specifically in the prescription of antibiotics. The system’s recommendations were compared with those expressed in the guidelines currently in use at EpiCURA. The results showed us that PARS allows for a better consideration of the sensitivity of the patients to the adverse effects of antibiotics. Moreover, by taking into account the additional characteristics of the patients, the model is able to adapt to contextual changes (such as new antibiotics, side effects and development of resistant micro-organisms)
Lisena, Pasquale. "Knowledge-based music recommendation : models, algorithms and exploratory search." Electronic Thesis or Diss., Sorbonne université, 2019. http://www.theses.fr/2019SORUS614.
Full textRepresenting the information about music is a complex activity that involves different sub-tasks. This thesis manuscript mostly focuses on classical music, researching how to represent and exploit its information. The main goal is the investigation of strategies of knowledge representation and discovery applied to classical music, involving subjects such as Knowledge-Base population, metadata prediction, and recommender systems. We propose a complete workflow for the management of music metadata using Semantic Web technologies. We introduce a specialised ontology and a set of controlled vocabularies for the different concepts specific to music. Then, we present an approach for converting data, in order to go beyond the librarian practice currently in use, relying on mapping rules and interlinking with controlled vocabularies. Finally, we show how these data can be exploited. In particular, we study approaches based on embeddings computed on structured metadata, titles, and symbolic music for ranking and recommending music. Several demo applications have been realised for testing the previous approaches and resources
Lherisson, Pierre-René. "Système de recommandation équitable d'oeuvres numériques. En quête de diversité." Thesis, Lyon, 2018. http://www.theses.fr/2018LYSES018/document.
Full textRecommender systems play a leading role in user’s choice guidance. The search of accuracy in such systems is generally done through an optimization of a function between the items and the users. It has been proved that maximizing only the accuracy does not produce the most useful recommendation for the users. This can confine individuals inside the bubble of their own choices. Additionally, it tends to emphasize the agglomaration of the users’ behavior on few popular items. Thus, it produces a lack of diversity and novelty in recommendations and a limited coverage of the platform catalog. This can lead to an absence of discovery. Monotony and frustration are also induced for the users. This non-discovery is even more crucial if the platform wants to be fair in its recommendations with all contents’ producers (e.g, music artists, writers, video game developers or videographers). The non diversity, and novelty problem is more important for the users because it has been shown that human mind appreciates when moved outside of its comfort zone. For example, the discovery of new artists, the discovery of music genres for which he is not accustomed. In this thesis we present two families of model that aim to go beyond accuracy in content based recommender system scenario. Our two models are based on a user profile understanding prior to bring diversification. They capture the diversity in the user profile and respond to thisdiversity by looking to create a diverse list of recommendation without loosing to much accuracy. The first model is mainly built upon a clustering approach, while the second model is based on an wavelet function. This wavelet function in our model helps us delimit an area where the user will find item slightly different from what he liked in the past. This model is based on the assumption of the existence of a defined intermediate area between similar and different items. This area is also suitable for discovery. Our proposals are tested on a common experimental design that consider well-known datasets and state-of-the-art algorithm. The results of our experiments show that our approaches indeed bring diversity and novelty and are also competitive against state-of-the-art method. We also propose a user-experiment to validate our model based on the wavelet. The results of user centered experiments conclude that this model corresponds with human cognitive and perceptual behavior
Ghenname, Mérième. "Le web social et le web sémantique pour la recommandation de ressources pédagogiques." Thesis, Saint-Etienne, 2015. http://www.theses.fr/2015STET4015/document.
Full textThis work has been jointly supervised by U. Jean Monnet Saint Etienne, in the Hubert Curien Lab (Frederique Laforest, Christophe Gravier, Julien Subercaze) and U. Mohamed V Rabat, LeRMA ENSIAS (Rachida Ahjoun, Mounia Abik). Knowledge, education and learning are major concerns in today’s society. The technologies for human learning aim to promote, stimulate, support and validate the learning process. Our approach explores the opportunities raised by mixing the Social Web and the Semantic Web technologies for e-learning. More precisely, we work on discovering learners profiles from their activities on the social web. The Social Web can be a source of information, as it involves users in the information world and gives them the ability to participate in the construction and dissemination of knowledge. We focused our attention on tracking the different types of contributions, activities and conversations in learners spontaneous collaborative activities on social networks. The learner profile is not only based on the knowledge extracted from his/her activities on the e-learning system, but also from his/her many activities on social networks. We propose a methodology for exploiting hashtags contained in users’ writings for the automatic generation of learner’s semantic profiles. Hashtags require some processing before being source of knowledge on the user interests. We have defined a method to identify semantics of hashtags and semantic relationships between the meanings of different hashtags. By the way, we have defined the concept of Folksionary, as a hashtags dictionary that for each hashtag clusters its definitions into meanings. Semantized hashtags are thus used to feed the learner’s profile so as to personalize recommendations on learning material. The goal is to build a semantic representation of the activities and interests of learners on social networks in order to enrich their profiles. We also discuss our recommendation approach based on three types of filtering (personalized, social, and statistical interactions with the system). We focus on personalized recommendation of pedagogical resources to the learner according to his/her expectations and profile
Karoui, Hajer. "Système coopératif de type égal-à-égal pour la recommandation : Application à la gestion et la recommandation de références bibliographiques." Phd thesis, Université Paris-Nord - Paris XIII, 2007. http://tel.archives-ouvertes.fr/tel-00299935.
Full textDeux problématiques se présentent : comment obtenir les références pertinentes et comment choisir des agents avec qui collaborer ? Pour résoudre ces problèmes, nous nous sommes basés sur l'exploitation des historiques des interactions entre les agents.
Le RàPC est utilisée pour deux finalités :
a)déterminer pour une requête, des agents intéressants à interroger ;
b)chercher pour une requête, des références pertinentes.
Avillach, Paul. "Du système d'information clinique au système d'information épidémiologique : apport de l'intéropérabilité sémantique." Thesis, Aix-Marseille 2, 2011. http://www.theses.fr/2011AIX20697.
Full textMedical information collected during clinical care must be re-used to address other more collective goals. In this context of re-using data from a clinical information system for epidemiological research, the objective of this work is to study the contribution of semantic interoperability across a number of practical situations we have met and discussed which illustrate the nature of semantic consistency problems associated with processing of medical data.Coexistence at a given time, of several semantic repositories should not be considered as an obstacle to interoperability. Generic tools can be designed and developed to move seamlessly from one component to another with as little loss of information as possible. The Unified Medical Language System (UMLS) is one of the semantic integration tools. Its use in this work shows the generality of this method and its potential for solving this class of semantic interoperability problems.The richness of each of the terminology can, when combined into a single pivot semantic repository, enrich the set of terminologies individually for a better representation of knowledge.Semantic interoperability improves the availability and quality of reusable data for public health research. It also enriches existing data. It provides access to new sources of data, aggregated in a valid manner, allowing benchmarking or richer analysis
Grossetti, Quentin. "Système de recommandation sur les plateformes de micro-blogging et bulles filtrantes." Electronic Thesis or Diss., Sorbonne université, 2018. http://www.theses.fr/2018SORUS304.
Full textWith the unprecedented growth of user-generated content produced on microblogging platforms, finding interesting content for a given user has become a major issue. However due to the intrinsic properties of microblogging systems, such as the volumetry, the short lifetime of posts and the sparsity of interactions between users and content, recommender systems cannot rely on traditional methods, such as collaborative filtering matrix factorization. After a thorough study of a large Twitter dataset, we present a propagation model which relies on homophily to propose post recommendations. Our approach relies on the construction of a similarity graph based on retweet behaviors on top of the Twitter graph. We then conduct experiments on our real dataset to demonstrate the quality and scalability of our method. Finally, we investigate community detection algorithms and we present a metric to compute the strength of the filter bubble. Our results show that filter bubble effects are in fact limited for a majority of users. We find that, counter-intuitively, in most cases recommender systems tend to open users perspectives. However, for some specific users, the bubble effect is noticeable and we propose a model relying on communities to provide a list of recommendations closer to the user’s usage of the platform
Fomba, Soumana. "Décision multicritère : un système de recommandation pour le choix de l'opérateur d'agrégation." Thesis, Toulouse 1, 2018. http://www.theses.fr/2018TOU10009/document.
Full textRecommendation systems are becoming more popular. This PhD focusses on MultiCriteriaDecision Analysis (MCDA). For MCDA, it exists multiplication lot of aggregation methods. This diversity of aggregation methods and decision-making situations means that there is no super method applicable in all decision-making situations. The question then is how to choose an appropriate aggregation operator for a given decision problem? In this thesis, we try to have some answers to this question, on the one hand by studying the decision support systems, on the other hand by analyzing different aggregation operators present in the literature. This allowed us to set up a recommendation system implementing several aggregation operators. During an aggregation procedure, the user has the possibility of choosing an aggregation operator from among the available operators. It can also be offered an aggregation operator by the system. The aggregation operator most appropriate to the decision-maker's decision problem is chosen according to several parameters
Ngo, Ba Hung. "Système de fichiers sémantique basé sur le contexte." Evry, Institut national des télécommunications, 2009. http://www.theses.fr/2009TELE0008.
Full textOrganizing the information that we call personal files such as files in a home directory, web pages found on the Internet, images, emails for later revisiting is currently required by many computer users. Several information retrieval models are proposed to fullfil this requirement. Each model is characterized by the types of personal files, their organization and the searching method used. Traditional file systems let a user organize his files into a directory tree and retrieve them later by browsing the directory tree. Desktop seach tools such as Google Desktop or Beagle automatically index file properties and file content (keywords) to provide the user with file retrieval by querying on file properties or on file content. Semantic file systems propose a searching method that combines querying with browsing to give to the users the advantages of both searching methods. For informations on the Internet, tagging systems are more and more used to facilitate the re-finding of these Internet ressources. Among personal file characteristics (properties, content, context) exploited by the above retrieval models, the working context of the user has been proved to be relevant to help a user to successfully retrieve his personal files. This work proposes a model for personal file retrieval, called « context-based model for personal file retrieval ». Our model allows a user to associate his personal files with a working context using tags. To retrieve a personal file, the user must describe the working context corresponding to each file. The searching method in our model gives to the users the advantages of both searching methods: browsing and querying. We develop our model by improving traditional tagging models. Based on tag relationships and popularities, we organize tags created by a user into a directed acyclic graph (DAGoT). This DAGoT is used as the basic data model to realize our context-based model for personal file retrieval. We use this graph to recognize working contexts associated to personal files, guide a user to reconstruct his working contexts, refine the searching requests, and retrieve personal files by context
Belliard, Serge. "Bases neuroanatomiques du système sémantique spécifique aux personnes." Aix-Marseille 2, 2005. http://www.theses.fr/2005AIX20654.
Full text27 patients with semantic dementia (with bilateral but asymmetric anterior temporal lesions) and 20 patients with unilateral temporal excision for intractable epilepsy recognised then identified famous faces and names. From the results of these experiments, we consider that person identification requires bilateral convergence zones (PINs) which lie on medial part of anterior temporal lobes. Each PIN bind together all semantic features which are stored in secondary cortices but have a preferential access to semantic features stored in homolateral hemisphere. Thus, right PINs have a preferential access to structural and shared biographical features, left PINs to specific biographical features. Right PINs are reached by faces and names, but left PINs only by names. Patients with semantic dementia do not show any sign of cognitive or emotional implicit recognition. This lead us to consider that implicit and explicit recognition occur from the same occipito-temporal identification network
Meyer, Frank. "Systèmes de recommandation dans des contextes industriels." Phd thesis, Université de Grenoble, 2012. http://tel.archives-ouvertes.fr/tel-00767159.
Full textFrainay, Clément. "Système de recommandation basé sur les réseaux pour l'interprétation de résultats de métabolomique." Thesis, Toulouse 3, 2017. http://www.theses.fr/2017TOU30297/document.
Full textMetabolomics allows large-scale studies of the metabolic profile of an individual, which is representative of its physiological state. Metabolic markers characterising a given condition can be obtained through the comparison of those profiles. Therefore, metabolomics reveals a great potential for the diagnosis as well as the comprehension of mechanisms behind metabolic dysregulations, and to a certain extent the identification of therapeutic targets. However, in order to raise new hypotheses, those applications need to put metabolomics results in the light of global metabolism knowledge. This contextualisation of the results can rely on metabolic networks, which gather all biochemical transformations that can be performed by an organism. The major bottleneck preventing this interpretation stems from the fact that, currently, no single metabolomic approach allows monitoring all metabolites, thus leading to a partial representation of the metabolome. Furthermore, in the context of human health related experiments, metabolomics is usually performed on bio-fluid samples. Consequently, those approaches focus on the footprints left by impacted mechanisms rather than the mechanisms themselves. This thesis proposes a new approach to overcome those limitations, through the suggestion of relevant metabolites, which could fill the gaps in a metabolomics signature. This method is inspired by recommender systems used for several on-line activities, and more specifically the recommendation of users to follow on social networks. This approach has been used for the interpretation of the metabolic signature of the hepatic encephalopathy. It allows highlighting some relevant metabolites, closely related to the disease according to the literature, and led to a better comprehension of the impaired mechanisms and as a result the proposition of new hypothetical scenario. It also improved and enriched the original signature by guiding deeper investigation of the raw data, leading to the addition of missed compounds. Models and data characterisation, alongside technical developments presented in this thesis, can also offer generic frameworks and guidelines for metabolic networks topological analysis
Jelassi, Mohamed Nidhal. "Un système personnalisé de recommandation à partir de concepts quadratiques dans les folksonomies." Thesis, Clermont-Ferrand 2, 2016. http://www.theses.fr/2016CLF22693/document.
Full textRecommender systems are now popular both commercially as well as within the research community, where many approaches have been suggested for providing recommendations. Folksonomies' users are sharing items (e.g., movies, books, bookmarks, etc.) by annotating them with freely chosen tags. Within the Web 2.0 age, users become the core of the system since they are both the contributors and the creators of the information. In this respect, it is of paramount importance to match their needs for providing a more targeted recommendation. For such purpose, we consider a new dimension in a folksonomy classically composed of three dimensions and propose an approach to group users with close interests through quadratic concepts. Then, we use such structures in order to propose our personalized recommendation system of users, tags and resources. We carried out extensive experiments on two real-life datasets, i.e., MovieLens and BookCrossing which highlight good results in terms of precision and recall as well as a promising social evaluation. Moreover, we study some of the key assessment metrics namely coverage, diversity, adaptivity, serendipity and scalability. In addition, we conduct a user study as a valuable complement to our evaluation in order to get further insights. Finally, we propose a new algorithm that aims to maintain a set of triadic concepts without the re-scan of the whole folksonomy. The first results comparing the performances of our proposition andthe running from scratch the whole process over four real-life datasets show its efficiency
Alchiekh, Haydar Charif. "Les systèmes de recommandation à base de confiance." Thesis, Université de Lorraine, 2014. http://www.theses.fr/2014LORR0203/document.
Full textRecommender systems (RS) exploit users' behaviour to recommend to them items they would appreciate. Users Behavioral divergence on the web results in a problem of performance fluctuations to (RS). This problem is observed in the approach of collaborative filtering (CF), which exploites the ratings attributed by users to items, and in the trust-based approach (TRS), which exploites the trust relations between the users. We propose a hybrid approach that increases the number of users receiving recommendation, without significant loss of accuracy. Thereafter, we identify several behavioral characteristics that define a user profile. Then we classify users according to their common behavior, and observe the performance of the approaches by class. Thereafter, we focus on the TRS. The concept of trust has been discussed in several disciplines. There is no real consensus on its definition. However, all agree on its positive effect. Subjective logic (LS) provides a flexible platform for modeling trust. We use it to propose and compare three trust models, which aims to predict whether a user source can trust a target user. Trust may be based on the personal experience of the source (local model), or on a system of mouth (collective model), or the reputation of the target (global model). We compare these three models in terms of accuracy, complexity, and robustness against malicious attacks
Bracops, Martine. "Le système de CAR: étude grammaticale, sémantique et pragmatique." Doctoral thesis, Universite Libre de Bruxelles, 1995. http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/212501.
Full textFedele, Carine. "Construction automatisée des compilateurs : le système CIGALE." Nice, 1991. http://www.theses.fr/1991NICE4469.
Full textCompiler-compilers are a well-known subject and many ideas have been explored. However, results are note entirely satisfactory. First, one should distinguish between compiler-compilers for experimental languages and those for implementation languages. In the first case, the efficiency of the generated compiler sis not important, and these systems are generally used bu people who do not wish to invest in compiler practice. In the second case, a resulting compiler which would be slow and generate inefficient code would be useless: all software products built using this implementation language would have unbearable performances, especially in the software world. On the contrary, users such a compiler-compiler are compiling practitioners and only ask for help in their task. Not much work is done in this last case and it is a pity. For an already long time, a theory of scanning an parsing has been developed. Today, automatically building a lexico-syntactic analyzer is easy. That is not the case for the other parts of the compiling process: contextual analysis and code generation. No « universal » theory is currently accepted by all scientists. The CIGALE system is a compiler writing system based on the well-known formalism of attribute grammars. From a description of the syntax and semantics of the language (the lexical aspect is implicit). CIGALE produces a compiler for this language generating EM code. This code is then processed by the ACK components until this language code is generated for a given actual machine. The language syntax is describing using a notation similar to BNF. The language semantics is described by the use of an abstract data type. This type is not frozen and the user can provide next tools for handling unforeseen language features. The thesis begins with the survey of nine formal semantic notations and of twenty compiler-compilers. The CIGALE system is then thoroughly xplained. The abstract data type for contextual analysis and dynamic semantics is then fully specified, and its use is demonstrated on a real size example. The thesis ends with the description of a higher-level notation deduced from this abstract data type
Tadlaoui, Mohammed. "Système de recommandation de ressources pédagogiques fondé sur les liens sociaux : Formalisation et évaluation." Thesis, Lyon, 2018. http://www.theses.fr/2018LYSEI053/document.
Full textWith the increasing amount of educational content produced daily by users, it becomes very difficult for learners to find the resources that are best suited to their needs. Recommendation systems are used in educational platforms to solve the problem of information overload. They are designed to provide relevant resources to a learner using some information about users and resources. The present work fits in the context of recommender systems for educational resources, especially systems that use social information. We have defined an educational resource recommendation approach based on research findings in the area of recommender systems, social networks, and Technology-Enhanced Learning. We rely on social relations between learners to improve the accuracy of recommendations. Our proposal is based on formal models that calculate the similarity between users of a learning environment to generate three types of recommendation, namely the recommendation of 1) popular resources; 2) useful resources; and 3) resources recently consulted. We have developed a learning platform, called Icraa, which integrates our recommendation models. The Icraa platform is a social learning environment that allows learners to download, view and evaluate educational resources. In this thesis, we present the results of an experiment conducted for almost two years on a group of 372 learners of Icraa in a real educational context. The objective of this experiment is to measure the relevance, quality and usefulness of the recommended resources. This study allowed us to analyze the user’s feedback on the three types of recommendations. This analysis is based on the users’ traces which was saved with Icraa and on a questionnaire. We have also performed an offline analysis using a dataset to compare our approach with four base line algorithms
Telechea, Pascal. "Contrôle de concurrence sémantique dans un système multibase de données." Toulouse 3, 1997. http://www.theses.fr/1997TOU30022.
Full textPicot-Clémente, Romain. "Une architecture générique de Systèmes de recommandation de combinaison d'items : application au domaine du tourisme." Phd thesis, Université de Bourgogne, 2011. http://tel.archives-ouvertes.fr/tel-00688994.
Full textYou, Wei. "Un système à l'approche basée sur le contenu pour la recommandation personnalisée d'articles de recherche." Compiègne, 2011. http://www.theses.fr/2011COMP1922.
Full textPersonalized research paper recommendation filters the publications according to the specific research interests of users, which could significantly alleviate the information overload problem. Content-based filtering is a promising solution for this task because it can effectively exploit the textual-nature of research papers. A content-based recommender system usually concerns three essential issues: item representation, user profiling, and a model that provides recommendations by comparing candidate item's content representation with the target user's interest representation. In this dissertation, we first propose an automatic keyphrase extraction technique for scientific documents, which improves the existing approaches by using a more precise location for potential keyphrases and a new strategy for eliminating the overlap in the output list. This technique helps to implement the representation of candidate papers and the analysis of users' history papers. Then for modeling the users' information needs, we present a new ontology-based approach. The basic idea is that each user is represented as an instance of a domain ontology in which concepts are assigned interest scores reflecting users' degree of interest. We distinguish senior researchers and junior researchers by deriving their individual research interests from different history paper sets. We also takes advantage of the structure of the ontology and apply spreading activation model to reason about the interests of users. Finally, we explore a novel model to generate recommendations by resorting to the Dempster-Shafer theory. Keyphrases extracted from the candidate paper are considered as sources of evidence. Each of them are linked to different levels of user interest and the strength of each link is quantified. Different from other similarity measures between user profiles and candidate papers, our recommendation result produced by combining all evidence is able to directly indicate the possibility that a user might be interested in the candidate paper. Experimental results show that the system we developed for personalized research paper recommendation outperforms other state-of-the-art approaches. The proposed method can be used as a generic way for addressing different types of recommendation problems
Stan, Johann. "Un cadre de développement sémantique pour la recherche sociale." Phd thesis, Université Jean Monnet - Saint-Etienne, 2011. http://tel.archives-ouvertes.fr/tel-00708781.
Full textDraidi, Fady. "Recommandation Pair-à-Pair pour Communautés en Ligne à Grande Echelle." Phd thesis, Université Montpellier II - Sciences et Techniques du Languedoc, 2012. http://tel.archives-ouvertes.fr/tel-00766963.
Full textFechter, Stéphane. "Sémantique des traits orientés objet de Focal." Paris 6, 2005. http://www.theses.fr/2005PA066203.
Full textRivière, Françoise. "La semeiologie dans le système stoi͏̈cien." Lyon 3, 1990. http://www.theses.fr/1990LYO31012.
Full textSemeiology in the stoic system propounds the sign as a key in order to understand the stoic doctrine. The study is almost exclusively founded on statements of stoics themselves, particularly the first stoics and the roman stoics. The "whole mixing theory" directs the analysis towords different "places" of the system : logic, physics and ethics. The sign appears as the permanent manifestation of the vital principle in the world. It especially offers the advantage to produce the bond wich joins the different parts of the whole, phenomenous, events, beings. But its apprehension sometimes does sums although its reality is a data, because it is men's duty to make a correct use of it. Now if the existence of the sign is uncontested, it is sometimes lost for these whocan't succed in seizing it. At the term of punctual analysis about dialectics of propositions about divination and about suicide, the sign comes to ethical perspective and places stoicism in mind of the world as a continuity
Szilagyi, Ioan. "Technologies sémantiques pour un système actif d’apprentissage." Thesis, Besançon, 2014. http://www.theses.fr/2014BESA1008/document.
Full textLearning methods keep evolving and new paradigms are added to traditional teaching models where the information and communication systems, particularly the Web, are an essential part. In order to improve the processing capacity of information systems, the Semantic Web defines a model for describing resources (Resource Description Framework - RDF), and a language for defining ontologies (Web Ontology Language – OWL). Based on concepts, methods, learning theories, and following a systemic approach, we have used Semantic Web technologies in order to provide a learning system that is able to enrich and personalize the experience of the learner. As a result of our work we are proposing a prototype for an Active Semantic Learning System (SASA). Following the identification and modeling of entities involved in the learning process, we created the following six ontologies that summarize the characteristics of these entities: (1) learner ontology, (2) learning object ontology, (3) learning objective ontology, (4) evaluation object ontology, (5) annotation object ontology and (6) learning framework ontology. Integrating certain rules in the declared ontologies combined with reasoning capacities of the inference engines embedded in the kernel of the SASA, allow the adaptation of learning content to the characteristics of learners. The use of semantic technologies facilitates the identification of existing learning resources on the web as well as the interpretation and aggregation of these resources within the context of SASA
Aleksandrova, Marharyta. "Factorisation de matrices et analyse de contraste pour la recommandation." Thesis, Université de Lorraine, 2017. http://www.theses.fr/2017LORR0080/document.
Full textIn many application areas, data elements can be high-dimensional. This raises the problem of dimensionality reduction. The dimensionality reduction techniques can be classified based on their aim: dimensionality reduction for optimal data representation and dimensionality reduction for classification, as well as based on the adopted strategy: feature selection and feature extraction. The set of features resulting from feature extraction methods is usually uninterpretable. Thereby, the first scientific problematic of the thesis is how to extract interpretable latent features? The dimensionality reduction for classification aims to enhance the classification power of the selected subset of features. We see the development of the task of classification as the task of trigger factors identification that is identification of those factors that can influence the transfer of data elements from one class to another. The second scientific problematic of this thesis is how to automatically identify these trigger factors? We aim at solving both scientific problematics within the recommender systems application domain. We propose to interpret latent features for the matrix factorization-based recommender systems as real users. We design an algorithm for automatic identification of trigger factors based on the concepts of contrast analysis. Through experimental results, we show that the defined patterns indeed can be considered as trigger factors
Dudognon, Damien. "Diversité et système de recommandation : application à une plateforme de blogs à fort trafic (convention CIFRE n°20091274)." Toulouse 3, 2014. http://thesesups.ups-tlse.fr/2546/.
Full textRecommender Systems aim at automatically providing objects related to user's interests. These tools are increasingly used on content platforms to help the users to access information. In this context, user's interests can be modeled from the visited content and/or user's actions (clicks, comments, etc). However, these interests can not be modeled for an unknown user (cold start issue). Therefore, modeling is complex and recommendations are often far away from the real user's interests. In addition, existing approaches are generally not able to guarantee good performances on platforms with high trafic and which host a significant volume of data. To obtain more relevant recommendations for each user, we propose a recommender system model that builds a list of recommendations aiming at covering a large range of interests, even when only few information about the user is available. The recommender system model we propose is based on diversity. It uses different interest measures and an aggregation function to build the final set of recommendations. We demonstrate the interest of our approach using reference collections and through a user study. Finally, we evaluate our model on the OverBlog platform to validate its scalability in an industrial context
Meilender, Thomas. "Un wiki sémantique pour la gestion des connaissances décisionnelles - Application à la cancérologie." Phd thesis, Université de Lorraine, 2013. http://tel.archives-ouvertes.fr/tel-00919997.
Full textCalvier, François-Élie. "Découverte de mappings dans un système pair-à-pair sémantique : application à SomeRDFS." Phd thesis, Université Paris Sud - Paris XI, 2010. http://tel.archives-ouvertes.fr/tel-00530075.
Full textSirri, Louah. "L'organisation du système lexico-sémantique dans le cerveau monolingue et bilingue en développement." Thesis, Sorbonne Paris Cité, 2015. http://www.theses.fr/2015PA05H103/document.
Full textThe present doctoral research explored the developing lexical-semantic system in monolingual and bilingual toddlers. The question of how and when word meanings are first related to each other and become integrated into an interconnected semantic system was investigated. Three studies were conducted with monolingual French learning children which aimed at exploring how words are organized, that is, according to taxonomic relationships (e.g., pig - horse) and to semantic similarity distances between words (e.g., cow - sheep versus cow - deer), and whether cognitive mechanisms, such as automatic activation and controlled processes, underlie priming effects. An additional two studies conducted with children learning two languages simultaneously, aimed at determining, first, whether taxonomically related word meanings, in each of the two languages, are processed in a similar manner. The second goal was to explore whether words presented in one language activate words in another language, and vice versa. In an attempt to answer these questions, lexical-semantic processing was explored by two techniques: eye-tracking and event-related potentials (ERPs) techniques. Both techniques provide high temporal resolution measures of word processing but differ in terms of responses. Eye-movement measurements (Study III) reflect looking preferences in response to spoken words and their time-course, whereas ERPs reflect implicit brain responses and their activity patterns (Study I, II, IV, and V). Study I and II revealed that words are taxonomically organized at 18 and 24-month-olds. Both automatic and controlled processes were shown to be involved in word processing during language development (Study II). Study III revealed that at 24-month-olds, categorical and feature overlap between items underpin the developing lexical-semantic system. That is, lexical-items in each semantic category are organized according to graded similarity distances. Productive vocabulary skills influenced word recognition and were related to underlying cognitive mechanisms. Study IV revealed no differences in terms of semantic processing in the bilinguals¿ two languages, but the ERP distribution across the scalp varied according to the language being processed. Study V showed that words presented in one language activate their semantic representations in the second language and the other way around. The distribution of the ERPs depended, however, on the direction of translation. The results suggest that even early dual language experience yields distinct neural resources underlying lexical-semantic processing in the dominant and non-dominant languages during language acquisition
Mulatéro, Frédéric. "Ramasse-mièttes et contrôle de concurrence sémantique dans un système multibase de données." Toulouse 3, 1997. http://www.theses.fr/1997TOU30069.
Full textMalanda, Paul. "Sémantique et syntaxe du système verbal dans "la vida de Lazarillo de Tormes"." Paris 10, 1994. http://www.theses.fr/1994PA100116.
Full textThe present work is a linguistic study of the verbal system found in the sixteenth century narrative, "la vida de Lazarillo de Tormes". This study is concerned with the syntax and the semantics of the verbal system in "la vida de Lazarillo de Tormes". It seeks to shed light on the following: the different categories of mood, of tense, of person, of aspect (of verb), of voice as manifested in flexional endings or in the form taken by a verb. The work aims at contributing to better understanding and use of this sub-system which characterizes classical Spanish
Calvier, François-Elie. "Découverte de mappings dans un système Pair à Pair sémantique : Application à SomeRDFS." Paris 11, 2010. http://www.theses.fr/2010PA112098.
Full textThe richness of answers to queries asked to peer to peer data management systems (PDMS) depends on the number of mappings between ontologies of different peers. Increasing this number can improve responses to queries. This is the problem considered in this thesis. We aims at discovering semantic links between ontologies of different peers. This problem, known as ontology alignment, is specific in peer-to-peer systems in which ontologies are not completely known a priori, the number of ontologies to align is very large and alignment should be done without any centralized control. We propose semi-automatic techniques for identifying: (1) mapping shortcut corresponding to a composition of existing mappings and (2) new mappings which can not be inferred in the current state of the system. These techniques are based on the use of reasoning mechanisms of PDMS and filtering criteria restricting the number of pairs of elements to align. Mapping shortcuts are identified from the analysis of trace of queries asked by users, but also after application of criteria considering their usefulness. The discovery of new mappings consists in identifying the elements of the ontology of a given peer that are judged interesting and then in selecting the elements from distant peer with which it is relevant to align them. The proposed alignment techniques are either adaptations of existing technology or innovative techniques exploiting the specificities of our framework
Hadjadj, Mohammed. "Modélisation de la Langue des Signes Française : Proposition d’un système à compositionalité sémantique." Thesis, Université Paris-Saclay (ComUE), 2017. http://www.theses.fr/2017SACLS560/document.
Full textThe recognition of French Sign Language (LSF) as a natural language in 2005 has created an important need for the development of tools to make information accessible to the deaf public. With this prospect, this thesis aims at linguistic modeling for a system of generation of LSF. We first present the different linguistic approaches aimed at describing the sign language (SL). We then present the models proposed in computer science. In a second step, we propose an approach allowing to take into account the linguistic properties of the SL while respecting the constraints of a formalisation process.By studying the links between semantic functions and their observed forms in LSF Corpora, we have identified several production rules. We finally present the rule functioning as a system capable of modeling an entire utterance in LSF
Essayeh, Aroua. "Une approche de personnalisation de la recherche d'information basée sur le Web sémantique." Thesis, Valenciennes, 2018. http://www.theses.fr/2018VALE0003.
Full textThis PhD thesis reports on a recent study in the field of information retrieval (IR), more specifically personalized IR. Traditional IR uses various methods and approaches. However, given the proliferation of data from different sources, traditional IR is no longer considered to be an effective means of meeting users’ requirements. (‘Users’ here refers to the main actor in an IR system.) In this thesis, we address two main problems related to personalized IR: (1) the development and implementation of a user model; and (2) the formulation of a search query to improve the results returned to users according to their perceptions and preferences. To achieve these goals, we propose a semantic information search approach, based on the use of semantic information and guided by ontologies. The contribution of our work is threefold. First, it models and constructs user profiles following a modular ontological approach; this model allows the capture of information related to the user, and models the data according to the semantic approach so that the data can be re-used for reasoning and inference tasks. Second, it provides evidence for reformulating a query by exploiting concepts, hierarchical and non-hierarchical relationships between concepts and properties. Third, based on our findings, we recommend search results that are informed by the user’s communities, built by the improved unsupervised classification approach called the ‘Fuzzy K-mode’. These communities are also semantically modeled with modular profile ontology. To validate our proposed approach, we implemented a system for searching the itineraries for public transport. Finally, this thesis proposes research perspectives based on the limitations we encountered
Ben, Ellefi Mohamed. "La recommandation des jeux de données basée sur le profilage pour le liage des données RDF." Thesis, Montpellier, 2016. http://www.theses.fr/2016MONTT276/document.
Full textWith the emergence of the Web of Data, most notably Linked Open Data (LOD), an abundance of data has become available on the web. However, LOD datasets and their inherent subgraphs vary heavily with respect to their size, topic and domain coverage, the schemas and their data dynamicity (respectively schemas and metadata) over the time. To this extent, identifying suitable datasets, which meet specific criteria, has become an increasingly important, yet challenging task to supportissues such as entity retrieval or semantic search and data linking. Particularlywith respect to the interlinking issue, the current topology of the LOD cloud underlines the need for practical and efficient means to recommend suitable datasets: currently, only well-known reference graphs such as DBpedia (the most obvious target), YAGO or Freebase show a high amount of in-links, while there exists a long tail of potentially suitable yet under-recognized datasets. This problem is due to the semantic web tradition in dealing with "finding candidate datasets to link to", where data publishers are used to identify target datasets for interlinking.While an understanding of the nature of the content of specific datasets is a crucial prerequisite for the mentioned issues, we adopt in this dissertation the notion of "dataset profile" - a set of features that describe a dataset and allow the comparison of different datasets with regard to their represented characteristics. Our first research direction was to implement a collaborative filtering-like dataset recommendation approach, which exploits both existing dataset topic proles, as well as traditional dataset connectivity measures, in order to link LOD datasets into a global dataset-topic-graph. This approach relies on the LOD graph in order to learn the connectivity behaviour between LOD datasets. However, experiments have shown that the current topology of the LOD cloud group is far from being complete to be considered as a ground truth and consequently as learning data.Facing the limits the current topology of LOD (as learning data), our research has led to break away from the topic proles representation of "learn to rank" approach and to adopt a new approach for candidate datasets identication where the recommendation is based on the intensional profiles overlap between differentdatasets. By intensional profile, we understand the formal representation of a set of schema concept labels that best describe a dataset and can be potentially enriched by retrieving the corresponding textual descriptions. This representation provides richer contextual and semantic information and allows to compute efficiently and inexpensively similarities between proles. We identify schema overlap by the help of a semantico-frequential concept similarity measure and a ranking criterion based on the tf*idf cosine similarity. The experiments, conducted over all available linked datasets on the LOD cloud, show that our method achieves an average precision of up to 53% for a recall of 100%. Furthermore, our method returns the mappings between the schema concepts across datasets, a particularly useful input for the data linking step.In order to ensure a high quality representative datasets schema profiles, we introduce Datavore| a tool oriented towards metadata designers that provides rankedlists of vocabulary terms to reuse in data modeling process, together with additional metadata and cross-terms relations. The tool relies on the Linked Open Vocabulary (LOV) ecosystem for acquiring vocabularies and metadata and is made available for the community
Labbé, Vincent. "Modélisation et apprentissage des préférences appliqués à la recommandation dans les systèmes d'impression." Phd thesis, Université Pierre et Marie Curie - Paris VI, 2009. http://tel.archives-ouvertes.fr/tel-00814267.
Full textPlaice, John. "Sémantique et compilation de LUSTRE, un langage déclaratif synchrone." Grenoble INPG, 1988. http://www.theses.fr/1988INPG0032.
Full text