The evolution of the Internet has brought us into a world that represents a huge amount of information items such as music, movies, books, web pages, etc. with varying quality. As a result of this huge universe of items, people get confused and the question &ldquo / Which one should I choose?&rdquo / arises in their minds. Recommendation Systems address the problem of getting confused about items to choose, and filter a specific type of information with a specific information filtering technique that attempts to present information items that are likely of interest to the user. A variety of information filtering techniques have been proposed for performing recommendations, including content-based and collaborative techniques which are the most commonly used approaches in recommendation systems. This thesis work introduces ReMovender, a content-based movie recommendation system which is empowered by collaborative missing data prediction. The distinctive point of this study lies in the methodology used to correlate the users in the system with one another and the usage of the content information of movies. ReMovender makes it possible for the users to rate movies in a scale from one to five. By using these ratings, it finds similarities among the users in a collaborative manner to predict the missing ratings data. As for the content-based part, a set of movie features are used in order to correlate the movies and produce recommendations for the users.

An information filtering (IF) system monitors an incoming document stream to find the documents that match the information needs specified by the user profiles. To learn to use the user profiles effectively is one of the most challenging tasks when developing an IF system. With the document selection criteria better defined based on the users’ needs, filtering large streams of information can be more efficient and effective. To learn the user profiles, term-based approaches have been widely used in the IF community because of their simplicity and directness. Term-based approaches are relatively well established. However, these approaches have problems when dealing with polysemy and synonymy, which often lead to an information overload problem. Recently, pattern-based approaches (or Pattern Taxonomy Models (PTM) [160]) have been proposed for IF by the data mining community. These approaches are better at capturing sematic information and have shown encouraging results for improving the effectiveness of the IF system. On the other hand, pattern discovery from large data streams is not computationally efficient. Also, these approaches had to deal with low frequency pattern issues. The measures used by the data mining technique (for example, “support” and “confidences”) to learn the profile have turned out to be not suitable for filtering. They can lead to a mismatch problem. This thesis uses the rough set-based reasoning (term-based) and pattern mining approach as a unified framework for information filtering to overcome the aforementioned problems. This system consists of two stages - topic filtering and pattern mining stages. The topic filtering stage is intended to minimize information overloading by filtering out the most likely irrelevant information based on the user profiles. A novel user-profiles learning method and a theoretical model of the threshold setting have been developed by using rough set decision theory. The second stage (pattern mining) aims at solving the problem of the information mismatch. This stage is precision-oriented. A new document-ranking function has been derived by exploiting the patterns in the pattern taxonomy. The most likely relevant documents were assigned higher scores by the ranking function. Because there is a relatively small amount of documents left after the first stage, the computational cost is markedly reduced; at the same time, pattern discoveries yield more accurate results. The overall performance of the system was improved significantly. The new two-stage information filtering model has been evaluated by extensive experiments. Tests were based on the well-known IR bench-marking processes, using the latest version of the Reuters dataset, namely, the Reuters Corpus Volume 1 (RCV1). The performance of the new two-stage model was compared with both the term-based and data mining-based IF models. The results demonstrate that the proposed information filtering system outperforms significantly the other IF systems, such as the traditional Rocchio IF model, the state-of-the-art term-based models, including the BM25, Support Vector Machines (SVM), and Pattern Taxonomy Model (PTM).

Made available in DSpace on 2014-06-12T15:59:01Z (GMT). No. of bitstreams: 2 arquivo4812_1.pdf: 2843132 bytes, checksum: cf053779fad5d73c77a2b107542256b3 (MD5) license.txt: 1748 bytes, checksum: 8a4605be74aa9ea9d79846c1fba20a33 (MD5) Previous issue date: 2003 / Ricardo de Melo Queiroz, Sérgio; de Assis Tenório Carvalho, Francisco. Group recommendation strategies based on collaborative filtering. 2003. Dissertação (Mestrado). Programa de Pós-Graduação em Ciência da Computação, Universidade Federal de Pernambuco, Recife, 2003.

Les systèmes de recommandation essayent de déduire les intérêts de leurs utilisateurs afin de leurs suggérer des items pertinents. Ces systèmes offrent ainsi aux utilisateurs un service utile car ils filtrent automatiquement les informations non-pertinentes, ce qui évite le problème de surcharge d’information qui est courant de nos jours. C’est pourquoi les systèmes de recommandation sont aujourd’hui populaires, si ce n’est omniprésents dans certains domaines tels que le World Wide Web. Cependant, les intérêts d’un individu sont des données personnelles et privées, comme par exemple son orientation politique ou religieuse. Les systèmes de recommandation recueillent donc des données privées et leur utilisation répandue nécessite des mécanismes de protection de la vie privée. Dans cette thèse, nous étudions la protection de la confidentialité des intérêts des utilisateurs des systèmes de recommandation appelés systèmes de filtrage collaboratif (FC). Notre première contribution est Hide & Share, un nouveau mécanisme de similarité, respectueux de la vie privée, pour la calcul décentralisé de graphes de K-Plus-Proches-Voisins (KPPV). C’est un mécanisme léger, conçu pour les systèmes de FC fondés sur les utilisateurs et décentralisés (ou pair-à-pair), qui se basent sur les graphes de KPPV pour fournir des recommandations. Notre seconde contribution s’applique aussi aux systèmes de FC fondés sur les utilisateurs, mais est indépendante de leur architecture. Cette contribution est double : nous évaluons d’abord l’impact d’une attaque active dite « Sybil » sur la confidentialité du profil d’intérêts d’un utilisateur cible, puis nous proposons une contre-mesure. Celle-ci est 2-step, une nouvelle mesure de similarité qui combine une bonne précision, permettant ensuite de faire de bonnes recommandations, avec une bonne résistance à l’attaque Sybil en question. / Recommendation systems try to infer their users’ interests in order to suggest items relevant to them. These systems thus offer a valuable service to users in that they automatically filter non-relevant information, which avoids the nowadays common issue of information overload. This is why recommendation systems are now popular, if not pervasive in some domains such as the World Wide Web. However, an individual’s interests are personal and private data, such as one’s political or religious orientation. Therefore, recommendation systems gather private data and their widespread use calls for privacy-preserving mechanisms. In this thesis, we study the privacy of users’ interests in the family of recommendation systems called Collaborative Filtering (CF) ones. Our first contribution is Hide & Share, a novel privacy-preserving similarity mechanism for the decentralized computation of K-Nearest-Neighbor (KNN) graphs. It is a lightweight mechanism designed for decentralized (a.k.a. peer-to-peer) user-based CF systems, which rely on KNN graphs to provide recommendations. Our second contribution also applies to user-based CF systems, though it is independent of their architecture. This contribution is two-fold: first we evaluate the impact of an active Sybil attack on the privacy of a target user’s profile of interests, and second we propose a counter-measure. This counter-measure is 2-step, a novel similarity metric combining a good precision, in turn allowing for good recommendations,with high resilience to said Sybil attack.

Apesar dos processos de recuperação e filtragem de informação sempre terem usado técnicas básicas de Processamento de Linguagem Natural (PLN) no suporte à estruturação de documentos, ainda são poucas as indicações sobre os avanços relacionados à utilização de técnicas mais sofisticadas de PLN que justifiquem o custo de sua utilização nestes processos, em comparação com as abordagens tradicionais. Este trabalho investiga algumas evidências que fundamentam a hipótese de que a aplicação de métodos que utilizam conhecimento linguístico é viável, demarcando importantes contribuições para o aumento de sua eficiência em adição aos métodos estatásticos tradicionais. É proposto um modelo de representação de texto fundamentado em sintagmas nominais, cuja representatividade de seus descritores é calculada utilizando-se o conceito de evidência, apoiado em métodos estatísticos. Filtros induzidos a partir desse modelo são utilizados para classificar os documentos recuperados analisando-se a relevância implícita no perfil do usuário. O aumento da precisão (e, portanto, da eficácia) em sistemas de Recuperação de Informação, conseqüência da pós-filtragem seletiva de informações, demonstra uma clara evidência de como o uso de técnicas de PLN pode auxiliar a categorização de textos, abrindo reais possibilidades para o aprimoramento do modelo apresentado / Although Information Retrieval and Filtering tasks have always used basic Natural Language Processing (NLP) techniques for supporting document structuring, there is still space for more sophisticated NLP techniques which justify their cost when compared to the traditional approaches. This research aims to investigate some evidences that justify the hypothesis on which the use of linguistic-based methods is feasible and can bring on relevant contributions to this area. In this work noun phrases of a text are used as descriptors whose evidence is calculated by statistical methods. Filters are then induced to classify the retrieved documents by measuring their implicit relevance presupposed by an user profile. The increase of precision (efficacy) in IR systems as a consequence of the use of NLP techniques for text classification in the filtering task is an evidence of how this approach can be further explored

In our daily life, time is of the essence. People do not have time to browse through hundreds of thousands of digital items every day to find the right item for them. This is where a recommendation system shines. Tigerhall is a company that distributes podcasts, ebooks and events to subscribers. They are expanding their digital content warehouse which leads to more data for the users to filter. To make it easier for users to find the right podcast or the most exciting e-book or event, a recommendation system has been implemented. A recommender system can be implemented in many different ways. There are content-based filtering methods that can be used that focus on information about the items and try to find relevant items based on that. Another alternative is to use collaboration filtering methods that use information about what the consumer has previously consumed in correlation with what other users have consumed to find relevant items. In this project, a hybrid recommender system that uses a k-nearest neighbors algorithm alongside a matrix factorization algorithm has been implemented. The k-nearest neighbors algorithm performed well despite the sparse data while the matrix factorization algorithm performs worse. The matrix factorization algorithm performed well when the user has consumed plenty of items.

In dieser Arbeit versuche ich, den neuronalen Code, d. h. die Art und Weise, wie die Nervenzellen des Gehirns Informationen in ihrer Aktivität übertragen und verarbeiten, besser zu verstehen, indem ich die Kodierung von Stimuli in neuronalen Systemen untersuche. Zu diesem Zweck analysiere ich die Veränderungen in der Dynamik von neuronalen Standardmodellen, die im Rahmen der statistischen Physik entwickelt wurden, in Bezug auf Veränder- ungen der Parameter und der Konnektivität bei Vorhandensein bzw. Fehlen eines Reizes. Ich verwende informationstheoretische Maße, um die Fähigkeit neuronaler Populationen, empfangene Informationen durch ihren Output zu übertragen, zu quantifizieren. Die vorgestellten Ergebnisse bauen auf einer Vielzahl früherer Studien über unverbundene und rekurrente neuronale Pop- ulationen auf. Einige dieser Studien heben zwei neuronale Code-Kandidaten hervor, die unterschiedliche Profile der Informationsfilterung aufweisen: einen Integrationscode, der als Tiefpass-Informationsfilter fungiert, und einen Synchroniecode, der als Bandpassfilter fungiert. Das Ziel der vorliegenden Arbeit ist es, die Ergebnisse dieser Studien auf Netzwerke mit einem höheren Konnektivitätsgrad, wie er im Kortex beobachtet wird, auszuweiten. / In this thesis I attempt to better understand the neural code, or the way in which the nerve cells of the brain transmit and process information in their activity, through the investigation of stimulus encoding in neural systems. To this end, I analyze changes in the dynamics of standard neuronal models, de- veloped in the framework of statistical physics, to variations in parameters and connectivity in the presence versus the absence of a stimulus. In conjunction, information theoretical measures are utilized to quantify the ability of neu- ronal populations to transmit received information through their output. The presented results build upon a multitude of previous studies of both uncon- nected and recurrent neural populations. Some of these studies highlight two neural code candidates that have distinct information filtering profiles: an in- tegration code that acts as a low-pass information filter and a synchrony code that acts as a bandpass filter. In the following, synaptic connectivity is added in diverse ways in order to extend results of these studies to networks with a higher level of connectivity, as observed in the cortex.

Les médias sociaux occupent un rôle grandissant dans de nombreux domaines de notre vie quotidienne. Parmi d'autres, les réseaux sociaux tels que Facebook, Twitter, LinkedIn et Google+ dont la popularité a explosé ces dernières années, attirent des millions d'utilisateurs qui se communiquent, publient et partagent des informations et contenus à un rythme sans précédent. Outre les avantages reconnus, les réseaux sociaux ont également soulevé des problèmes divers. Nous sommes particulièrement intéressés par deux problèmes spécifiques : surcharge d'information et cloisonnement de données. Ces deux problèmes empêchent les utilisateurs d'exploiter pleinement et efficacement la richesse des informations poussées sur les réseaux sociaux. Les utilisateurs ont des difficultés pour filtrer tous les contenus reus, pour découvrir de nouveaux contenus au-delà de leurs réseaux personnels, et surtout pour partager les contenus intéressants avec leurs différents groupes d'intérêt. Pour aider les utilisateurs à surmonter ces difficultés, nous proposons une Approche centrée sur utilisateur et basée groupe pour filtrer et partager des données sociales. Cette nouvelle approche a un double objectif : (1) permettre aux utilisateurs d'agréger leurs données sociales en provenance de différents réseaux sociaux, d'en extraire des contenus de leur intérêt et (2) organiser et partager les contenus au sein de différents groupes. Les membres d'un groupe sont en outre en mesure de choisir quelle partie de leurs données à partager avec le groupe et définir collectivement les sujets d’intérêt de ce dernier. Pour implémenter l'approche proposée, nous spécifions une architecture de système comprenant plusieurs modules extensibles, et nous développons un prototype fonctionnel basé Web, appelé SoCoSys. Les résultats expérimentaux, obtenus des deux tests différents, valident les valeurs ajoutées de notre approche. / The social media have played an increasingly important role in many areas of our every day life. Among others, social network sites such as Facebook, LinkedIn, Twitter and Google+ have recently exploded in popularity by attracting millions of users, who communicate with each other, share and publish information and contents at an unprecedented rate. Besides the recognized advantages, social network sites have also raised various issues and challenges. We are particularly interested in two of them, information overload and "walled gardens". These two problems prevent the users from fully and efficiently exploiting thewealth of information available on social network sites. The users have difficulties to filter all incoming contents, to discover additional contents from outside of their friend circles, and importantly to share interesting contents with their different groups of interest. For helping the users to overcome such difficulties, we propose a User-centered and group- based approach for social data filtering and sharing. This novel approach has a twofold purpose : (1) allow the users to aggregate their social data from different social network sites, and to extract from those data the contents of their interest, and (2) organize and share the contents within different groups. The members of a group are moreover able to choose which part of their social data to share with the group, and collectively define its topics of interest. To achieve the proposed approach, we define a modular system architecture including a number of extensible modules, and accordingly build a working Web-based prototype, called SoCoSys. The experimental results, obtained from the two different tests, confirm the added values of our approach.

M. Tech. (Department of Information Communication Technology, Faculty of Applied and Computer Sciences), Vaal University of Technology. / Too many options on the internet are the reason for the information overload problem to obtain relevant information. A recommender system is a technique that filters information from large sets of data and recommends the most relevant ones based on people‟s preferences. Collaborative and content-based techniques are the core techniques used to implement a recommender system. A combined use of both collaborative and content-based techniques called hybrid techniques provide relatively good recommendations by avoiding common problems arising from each technique. In this research, a proactive University Library Book Recommender System has been proposed in which hybrid filtering is used for enhanced and more accurate recommendations. The prototype designed was able to recommend the highest ten books for each user. We evaluated the accuracy of the results using Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE). A measure value of 0.84904 MAE and 0.9579 RMSE found by our system shows that the combined use of both techniques gives an improved prediction accuracy for the University Library Book Recommender System.

The philosophical and empirical study reported here developed from the observation that information science has had no comprehensive understanding of nonuse of information. Without such an understanding, information workers may use the words "nonuse of information" while referring to very different phenomena. This lack of understanding makes the job of the information professional difficult. For example, the model presented here reduces hundreds of theories of information behavior to a conceptually manageable taxonomy of six conditions that lead to nonuse of information. The six conditions include: 1) intrinsic somatic conditions, 2) socio-environmental barriers, 3) authoritarian controls, 4) threshold knowledge shortfall, 5) attention shortfall, and 6) information filtering. This dissertation explains and provides examples of each condition. The study of a novel area that had no prior theory or model required a novel methodology. Thus, for this study, I adopted the pragmatism formulated by Charles Sanders Peirce, a method of evaluating concepts by their practical consequences. This pragmatism applied in two ways to the study of nonuse of information. First, because nonuse of information is a behavior, pragmatism helped me to limit the psychologic implications of the study to behavior, rather than to expand the discussion to psychodynamics or cognition, for example. I justified this limiting on the basis that behavior reflects the use or nonuse of information, and behavior is more observable than other aspects of psychology, such as cognition. Second, Peirce's concept of pragmatism supported another of his contributions to philosophical inquiry, retroduction, sometimes referred to as abduction. To study nonuse of information through retroduction, I created a fivestep "definition heuristic," based on the writings of Spradley and McCurdy. I then created a nine-step "retroduction heuristic" based on the system of logic identified and termed "retroductive" or "abductive" by Peirce. I used this heuristic to identify examples of nonuse of information and applied the examples to a second corpus of research reports that contained examples of compelled nonuse of information. The taxonomy of this study resulted from this second application and represents a descriptive model of compelled nonuse of information. / text