Η έννοια του «Web2.0.» χρησιμοποιήθηκε για πρώτη φορά σε ένα συνέδριο για την ανταλλαγή ιδεών μεταξύ του εκδοτικού οίκου O’ Reilly και του Medialive International. Μέσα από αυτή τη σύσκεψη έγινε φανερό ότι το Web είναι πιο σημαντικό από ποτέ, με εντυπωσιακές νέες εφαρμογές και ιστότοπους, που κάνουν την εμφάνισή τους ολοένα και συχνότερα. Μισό χρόνο μετά, ο όρος Web2.0. έχει ξεκάθαρα λάβει χώρα, με περισσότερες από 9,5 εκατομμύρια αναφορές στη μηχανή αναζήτησης Google. Πιο συγκεκριμένα, το νέο Web αλλάζει επειδή αλλάζει η νοοτροπία των δημιουργών των ιστότοπων, των προγραμματιστών αλλά και των απλών χρηστών. Το Web2.0. είναι περισσότερο δημοκρατικό. Ο ρόλος των ισχυρών, παραδοσιακών δημιουργών και «εκδοτών» περιεχομένου αποδυναμώνεται. Η αλληλεπίδραση των χρηστών με το περιεχόμενο και άλλους χρήστες εντείνεται. Η νέα χρήση των ήδη υπαρχουσών τεχνολογιών και εργαλείων δίνει καινούριες διαστάσεις και προστιθέμενη αξία στο περιεχόμενο. Οι λέξεις «υλικό» και «λογισμικό» περνάνε σε δεύτερη μοίρα ενώ μια νέα, καθολική πλατφόρμα είναι αυτή που αναδεικνύεται. Ο νέος Παγκόσμιος Ιστός που ακούει στο όνομα Web2.0. ενθαρρύνει τη συμμετοχή των χρηστών και την παραγωγή ενός πλουσιότερου, πιο σύγχρονου και δυναμικότερου περιεχομένου. Προσφέρει σε όλους τους χρήστες του το ρόλο του δημιουργού και του εκδότη αφού ταυτόχρονα με τους web developers, και οι απλοί χρήστες είναι σε θέση να δημιουργούν χρησιμοποιώντας τη θέληση και τη φαντασία τους. Παράλληλα με τη διαμόρφωση του περιεχομένου, διαφόρων μορφών, όπως κείμενο, ήχος, εικόνα, βίντεο, στους χρήστες επαφίεται και η κατηγοριοποίηση, η αξιολόγηση και η κατάταξη του περιεχομένου, όπως για παράδειγμα ποια είδηση θεωρείται από αυτούς ως η περισσότερο σημαντική. Το Web2.0 αναφέρεται σε ένα σύνολο νέων δικτυακών υπηρεσιών, οι οποίες επιτρέπουν στους χρήστες να συνεργάζονται και να ανταλλάζουν δεδομένα online, με πιο αποδοτικό τρόπο σε σχέση με αυτόν που προσφέρανε οι παλιότερες υπηρεσίες. Η ειδοποιός διαφορά είναι ότι οι νέες υπηρεσίες παρέχουν στο χρήστη μια εμπειρία που πλησιάζει περισσότερο σε αυτή που έχει όταν εργάζεται στον προσωπικό του υπολογιστή. Με άλλα λόγια, οι εφαρμογές του Web2.0. μοιάζουν με τις εφαρμογές desktop. Επιπλέον, οι νέοι δικτυακοί τόποι είναι κατά κανόνα «δυναμικοί» και περισσότερο αλληλεπιδραστικοί, διαφέροντας από το «στατικό» Web1.0. Το Web2.0. είναι συμβατό με οποιοδήποτε λειτουργικό σύστημα κι αν χρησιμοποιεί ο εκάστοτε χρήστης. Μια εφαρμογή πλοήγησης του Διαδικτύου (web browser) (οποιαδήποτε κι αν είναι αυτή) αρκεί για να συμμετέχει ένα χρήστης στο νέο, πιο ζωντανό και εκπληκτικό Διαδίκτυο. Επιπρόσθετα, το Web2.0. είναι εκτός από πλούσιο και «ελαφρύ». Πολλές από τις εφαρμογές του έχουν σχεδιαστεί για να «τρέχουν» γρήγορα, χωρίς να «βαραίνουν» τους πόρους του συστήματος. Τέλος, το λογισμικό και το υλικό δεν απασχολούν πλέον τους προγραμματιστές στον ίδιο βαθμό με το παρελθόν, αφού το περιεχόμενο, η διαμόρφωση και η αξιοποίησή του είναι τα θέματα στα οποία επικεντρώνεται κυρίως το ενδιαφέρον. Η παρούσα μεταπτυχιακή διπλωματική εργασία μελετά τις αρχές που το Web2.0. πρεσβεύει, τα πρότυπα σχεδιασμού που ακολουθούνται, τις τεχνικές και τεχνολογίες που χρησιμοποιούνται, τις ικανότητες που πρέπει να έχουν οι εταιρείες κατασκευής λογισμικού και εφαρμογών προκειμένου να θεωρούνται ότι ακολουθούν τα πρότυπα του Web2.0. Επιπλέον, παρουσιάζονται οι βασικότερες Web2.0. εφαρμογές, οι οποίες είτε πρόκειται για καινοτόμα στοιχεία, είτε αποτελούν νέες εκδόσεις των ήδη Web1.0. υπαρχουσών εφαρμογών, με τις οποίες και συγκρίνονται. Τελικά, παρουσιάζονται μια σειρά από ιστοτόπους, ελληνικούς και ξένους, στους οποίους γίνεται φανερή η επίδραση και παρουσία του Web2.0., ενώ παράλληλα προτείνεται η χρήση συγκεκριμένωνWeb2.0. στοιχείων και τεχνολογιών ανάλογα με την κατηγορία και το είδος του ιστοτόπου. Ωστόσο, υπάρχει και ένα μεγάλο ποσοστό που αντιμετωπίζει το Web2.0. με επιφυλακτικότητα. Ενώ κάποιοι το θεωρούν μια καινοτομία, κάποιοι άλλοι το θεωρούν μια χωρίς νόημα λέξη, που αποσκοπεί στην επικράτηση στην αγορά και την αύξηση των κερδών, των εφαρμογών και υπηρεσιών που φέρονται ως αντιπρόσωποι του όρου. Η παρούσα εργασία έχει ως σκοπό να παρουσιάσει αντικειμενικά και αμερόληπτα τη νέα γενιά του Διαδικτύου και αφήνει στον αναγνώστη να βγάλει τα δικά του συμπεράσματα για το τι τελικά είναι το Web2.0. και ποια είναι η αξία του. / The concept of “Web2.0” began with a conference brainstorming session between O’ Reilly and MediaLive International. In the year and a half since, the term “Web2.0” had clearly taken hold, with more than 9.5 million citations in Google. In the new generation of Web, users are treated as co-developers. They obtain the role of author and publisher and use their willingness and imagination to add value and create the content of the web. Leverage customer-self service and algorithmic data management are used in order to reach out to the entire web, to the edges and not just the centre. As a result, the new projects can be seen to have a natural architecture of participation. In some cases, the service automatically gets better the more people use it. Moreover, Web2.0 era software is delivered as a service, not as a product. That leads to an end of the software release cycle. Furthermore, the Web2.0 mindset is good at re-use. When commodity components are abundant, developers can create value simply by assembling them in novel or effective ways. The purpose of this master thesis is to analyse the principles that Web2.0. advocate, the techniques and technologies that are used, the core competencies of Web2.0. companies, the design patterns, the new applications and projects. Its target is to recommend which of the Web2.0’ components should be used in each case, depending on the needs, the requirements and the kind of the website or application. However, there’s still a huge amount of disagreement about just what Web2.0 means, with some people decrying it as a meaningless marketing buzzword, and others accepting it as the new conventional wisdom. This thesis presents Web2.0 impartially, letting readers to decide what is Web2.0 and its value.

Every single day, lots of users actively participate in social media sites (e.g., Facebook, YouTube, Last.fm, Flicker, etc.) upload photos, videos, share bookmarks, write blogs and annotate/comment on content provided by others. With the recent proliferation of social media sites, users are overwhelmed by the huge amount of available content. Therefore, organizing and retrieving appropriate multimedia content is becoming an increasingly important and challenging task. This challenging task led a number of research communities to concentrate on social tagging systems (also known as folksonomy) that allow users to freely annotate their media items (e.g., music, images, or video) with any sort of arbitrary words, referred to as tags. Tags assist users to organize their own content, as well as to find relevant content shared by other users. In this thesis, we first analyze how useful a folksonomy is for improving personalized services such as tag recommendation, tag-based search and item annotation. We then propose two new algorithms for social media retrieval and tag recommendation respectively. The first algorithm computes the latent preferences of tags for users from other similar tags, as well as latent annotations of tags for items from other similar items. We then seamlessly map the tags onto items, depending on an individual user’s query, to find the most desirable content relevant to the user’s needs. The second algorithm improves tag-recommendation and item annotation by adapting the Katz measure, a path-ensemble based proximity measure, for the use in social tagging systems. In this algorithm we model folksonomy as a weighted, undirected tripartite graph. We then apply the Katz measure to this graph, and exploit it to provide personalized tag recommendation for individual users. We evaluate our algorithms on two real-world folksonomies collected from Last.fm and CiteULike. The experimental results demonstrate that the proposed algorithms improve the search and the recommendation performance, and obtain significant gains in cold start situations where relatively little information is known about a user or an item

Depuis les années 2000, les technologies du Web permettent aux utilisateurs de prendre part à la production de données : les internautes du Web 2.0 sont les nouveaux capteurs de l’information. Du côté de l’Information Géographique affluent de nombreux jeux de données en provenance de plates-formes de cartographie participative telles qu’OpenStreetMap (OSM) qui a largement impulsé le phénomène de la Géographique Participative (VGI). La communauté OSM représente aujourd’hui plus de deux millions de contributeurs qui alimentent une base de données géospatiales ouverte dont l’objet est de capturer une représentation du territoire mondial. Les éléments cartographiques qui découlent de ce déluge de VGI sont caractérisés par des tags. Les tags permettent une catégorisation simple et rapide du contenu des plates-formes de crowdsourcing qui inondent la toile. Cette approche est cependant un obstacle majeur pour le partage et la réutilisation de ces grands volumes d’information. En effet, ces ensembles de tags, ou folksonomies, sont des modèles de données beaucoup moins expressifs que les ontologies. Nous proposons un méta-modèle pour rapprocher la folksonomie et l’ontologie OSM afin de mieux exploiter la sémantique des données qui en sont issues, tout en préservant la flexibilité intrinsèque à l’utilisation de tags. / Post-2000s web technologies have enabled users to engage in the information production process: Web 2.0 surfers are the new data sensors. Regarding Geographic Information (GI), large crowdsourced datasets emerge from the Volunteered Geographic Information (VGI) phenomenon through platforms such as OpenStreetMap (OSM). The latter involves more than two millions contributors who aim at mapping the world into an open geospatial database. This deluge of VGI consists of spatial features associated with tags describing their attributes which is typical of crowdsourced content categorization. However, this approach is also a major impediment to interoperability with other systems that could benefit from this huge amount of bottom-up data. Indeed, folksonomies are much less expressive data models than ontologies. We address the issue of loose OSM metadata by proposing a model for collaborative ontology engineering in order to semantically lift the data while preserving the flexible nature of the activity of tagging.

Nous nous intéressons dans cette thèse à la problématique de recommandation de tags dans les systèmes de partage et de classification sociale des ressources, dits folksonomies. Les utilisateurs annotent les ressources à partager par des tags librement choisis. Or, la liberté de choix de tags les rends ambigus. Nous proposons une nouvelle approche topologique nommé TLTR (Two Level Tag Recommendation)pour la recommandation de tags. TLTR est basée sur une approche originale de compression des graphes. Le graphe d'une folksonomie est compressé en appliquant une méthode de clustering sur chacune des trois composantes d'une folksonomie, à savoir: l'ensemble des utilisateurs, des ressources et des tags. Nous proposons également une méthode de clustering topologique basée sur une approche centrée graine pour la détection des communautés dans les graphes multiplexes. Une approche topologique classique, en occurrence la méthode Folkrank, est appliquée sur le graphe réduit afin de sélectionner les clusters de tags les plus appropriés. Ces clusters sont ensuite utilisés pour construire un autre graphe contextuel extrait du graphe original représentant la folksonomie. La méthode Folkrank est à nouveau appliquée afin de calculer la liste de tags à recommander. Des expérimentations sur des grandes folksonomies, notamment, des jeux de données extraits du système de partage des références bibliographiques Bibsonomy montrent la pertinence de notre approche. / We focus in this thesis on the problem of tag recommendation in social sharing to classification systems called folksonomies. Users of a folksonomy annotate their resources with freely tags chosen. We propose here a new topological approach for tags recommendation called TLTR (Two Level Tag Recommendation). TLTR (Two Level Tag Recommendation) is based on an original approach of graph compression. The graph of a folksonomy is compressed by a clustering each of the three components, namely the set of users, resources and tags. A topological clustering method based on a seed-centered approach for community detection in multiplex graphs is proposed. A classical topological approach, namely Folkrank, is applied to the reduced graph to select the most appropriate clusters of tags. These clusters are then used to build another contextual graph extracted from the original graph representing the folksonomy. Folkrank method is applied again to compute the list of tags to recommend. Experiments on large folksonomy, including, data extracted from references system Bibsonomy show the relevance of our approach.

Every single day, lots of users actively participate in social media sites (e.g., Facebook, YouTube, Last.fm, Flicker, etc.) upload photos, videos, share bookmarks, write blogs and annotate/comment on content provided by others. With the recent proliferation of social media sites, users are overwhelmed by the huge amount of available content. Therefore, organizing and retrieving appropriate multimedia content is becoming an increasingly important and challenging task. This challenging task led a number of research communities to concentrate on social tagging systems (also known as folksonomy) that allow users to freely annotate their media items (e.g., music, images, or video) with any sort of arbitrary words, referred to as tags. Tags assist users to organize their own content, as well as to find relevant content shared by other users. In this thesis, we first analyze how useful a folksonomy is for improving personalized services such as tag recommendation, tag-based search and item annotation. We then propose two new algorithms for social media retrieval and tag recommendation respectively. The first algorithm computes the latent preferences of tags for users from other similar tags, as well as latent annotations of tags for items from other similar items. We then seamlessly map the tags onto items, depending on an individual user’s query, to find the most desirable content relevant to the user’s needs. The second algorithm improves tag-recommendation and item annotation by adapting the Katz measure, a path-ensemble based proximity measure, for the use in social tagging systems. In this algorithm we model folksonomy as a weighted, undirected tripartite graph. We then apply the Katz measure to this graph, and exploit it to provide personalized tag recommendation for individual users. We evaluate our algorithms on two real-world folksonomies collected from Last.fm and CiteULike. The experimental results demonstrate that the proposed algorithms improve the search and the recommendation performance, and obtain significant gains in cold start situations where relatively little information is known about a user or an item

The Social Web, or Web 2.0, has recently gained popularity because of its low cost and ease of use. Social tagging sites (e.g. Flickr and YouTube) offer new principles for end-users to publish and classify their content (data). Tagging systems contain free-keywords (tags) generated by end-users to annotate and categorise data. Lack of semantics is the main drawback in social tagging due to the use of unstructured vocabulary. Therefore, tagging systems suffer from shortcomings such as low precision, lack of collocation, synonymy, multilinguality, and use of shorthands. Consequently, relevant contents are not visible, and thus not retrievable while searching in tag-based systems. On the other hand, the Semantic Web, so-called Web 3.0, provides a rich semantic infrastructure. Ontologies are the key enabling technology for the Semantic Web. Ontologies can be integrated with the Social Web to overcome the lack of semantics in tagging systems. In the work presented in this thesis, we build an architecture to address a number of tagging systems drawbacks. In particular, we make use of the controlled vocabularies presented by ontologies to improve the information retrieval in tag-based systems. Based on the tags provided by the end-users, we introduce the idea of adding “system tags” from semantic, as well as social, resources. The “system tags” are comprehensive and wide-ranging in comparison with the limited “user tags”. The system tags are used to fill the gap between the user tags and the search terms used for searching in the tag-based systems. We restricted the scope of our work to tackle the following tagging systems shortcomings: - The lack of semantic relations between user tags and search terms (e.g. synonymy, hypernymy), - The lack of translation mediums between user tags and search terms (multilinguality), - The lack of context to define the emergent shorthand writing user tags. To address the first shortcoming, we use the WordNet ontology as a semantic lingual resource from where system tags are extracted. For the second shortcoming, we use the MultiWordNet ontology to recognise the cross-languages linkages between different languages. Finally, to address the third shortcoming, we use tag clusters that are obtained from the Social Web to create a context for defining the meaning of shorthand writing tags. A prototype for our architecture was implemented. In the prototype system, we built our own database to host videos that we imported from real tag-based system (YouTube). The user tags associated with these videos were also imported and stored in the database. For each user tag, our algorithm adds a number of system tags that came from either semantic ontologies (WordNet or MultiWordNet), or from tag clusters that are imported from the Flickr website. Therefore, each system tag added to annotate the imported videos has a relationship with one of the user tags on that video. The relationship might be one of the following: synonymy, hypernymy, similar term, related term, translation, or clustering relation. To evaluate the suitability of our proposed system tags, we developed an online environment where participants submit search terms and retrieve two groups of videos to be evaluated. Each group is produced from one distinct type of tags; user tags or system tags. The videos in the two groups are produced from the same database and are evaluated by the same participants in order to have a consistent and reliable evaluation. Since the user tags are used nowadays for searching the real tag-based systems, we consider its efficiency as a criterion (reference) to which we compare the efficiency of the new system tags. In order to compare the relevancy between the search terms and each group of retrieved videos, we carried out a statistical approach. According to Wilcoxon Signed-Rank test, there was no significant difference between using either system tags or user tags. The findings revealed that the use of the system tags in the search is as efficient as the use of the user tags; both types of tags produce different results, but at the same level of relevance to the submitted search terms.

Ce mémoire porte sur l’analyse documentaire en milieu universitaire. Deux approches générales sont d’abord étudiées : l’approche centrée sur le document (premier chapitre), prédominante dans la tradition bibliothéconomique, et l’approche centrée sur l’usager (deuxième chapitre), influencée par le développement d’outils le plus souvent associés au Web 2.0. L’opposition entre ces deux démarches reflète une dichotomie qui se trouve au cœur de la notion de sujet, c’est-à-dire les dimensions objective et subjective du sujet. Ce mémoire prend par conséquent la forme d’une dissertation dont l’avantage principal est de considérer à la fois d’importants acquis qui appartiennent à la tradition bibliothéconomique, à la fois des développements plus récents ayant un impact important sur l’évolution de l’analyse documentaire en milieu universitaire. Notre hypothèse est que ces deux tendances générales doivent être mises en relief afin d’approfondir la problématique de l’appariement, laquelle définit la difficulté d’accorder le vocabulaire qu’utilise l’usager dans ses recherches documentaires avec celui issu de l’analyse documentaire (métadonnées sujet). Dans le troisième chapitre, nous examinons certaines particularités liées à l’utilisation de la documentation en milieu universitaire dans le but de repérer certaines possibilités et certaines exigences de l’analyse documentaire dans un tel milieu. À partir d’éléments basés sur l’analyse des domaines d’études et sur la démarche analytico-synthétique, il s’agit d’accentuer l’interaction potentielle entre usagers et analystes documentaires sur le plan du vocabulaire utilisé de part et d’autre. / The topic of this dissertation is subject analysis in a university environment. Two major approaches are studied at first: subject analysis centered on the document (first chapter), historically predominant in librarianship, and subject analysis centered on the user (second chapter), mostly influenced by the development of Web 2.0 technologies. The opposition between those two approaches reflects a dichotomy which is at the very heart of the notion of subject, meaning the objective and subjective aspects of the subject. The outline of the dissertation has the distinct advantage of presenting well established practices in the field of librarianship as well as recent developments that do have an impact on subject analysis in a university environment. Our hypothesis is that both major tendencies must be highlighted to study the question of mapping the terminology (subject metadata) that comes from subject analysis with the terminology that users tend to favor while searching for documents. In the third chapter, we examine more closely particularities of the university environment in an effort to look at distinct possibilities and requirements for subject analysis in such an environment. Reinforced by elements taken from domain and facet analysis, the goal is to accentuate the potential interaction between users and indexers on a terminological level.

O crescimento exponencial do uso das mídias sociais na Web está transformando a maneira de como as pessoas tratam as informações, interagem com elas e compartilham conhecimento. Da mesma forma, as organizações estão mudando a maneira de interagir com seus funcionários, parceiros e consumidores. Novas aplicações na Internet têm surgido para proporcionar confiança aos usuários e incentivá-los a interagir e conectá-los uns aos outros e a conteúdos disponibilizados. Essas aplicações podem identificar comportamentos, extrair opiniões e retornar informações de interesse dos usuários e das organizações de maneira a auxiliar a tomada de decisão. Essas aplicações proporcionam grande volume de dados e demandam complexos processos de análise. Essas análises abrem oportunidades para o desenvolvimento de novas soluções que agregam mais valor aos usuários de produtos e serviços disponibilizadas na Web. Empresas e instituições de pesquisa têm desenvolvidos meios para tratar o grande volume de dados e identificar oportunidades de negócio. O uso de modelos que permitem entender esse fenômeno coletivo tem aumentado nos últimos anos por, basicamente, duas razões: a necessidade de descobrir, organizar e representar o conhecimento empírico relacionado a um determinado domínio de interesse e a necessidade de disseminar mecanismos para auxiliar os tomadores de decisão. Nesse contexto, ontologias de domínio têm sido bastante utilizadas como forma de organização e representação do conhecimento. No entanto, são poucos os modelos ou aplicações que extraem, organizam e representam o conhecimento (implícito e explícito) contextualizado de grupos de pessoas que atuam coletivamente para resolver problemas comuns ou produzir algo novo. Este trabalho de pesquisa propõe um modelo de referência para extração da inteligência coletiva (IC) para suporte à tomada de decisão. O modelo foi inicialmente desenvolvido para caso do planejamento estratégico de TI para ser utilizada por órgãos de governo. Como parte do modelo, foi desenvolvida uma inovadora ontologia de domínio denominada ITMPvoc. De seu processo de construção e validação, o modelo extrai a IC que é contextualiza segundo o referencial 5W1H (What, Who, Why, Where, When, How) e aplicada para suporte à decisão em situações específicas. Outras instâncias do modelo para dois casos de uso são também apresentadas. São elas: extração da IC e suporte à decisão para alertas de doenças na agricultura e para alertas sobre adoção de software livre por municípios. Os resultados demonstram que os modelos de extração da IC de comunidades ou organizações humanas podem melhorar os complexos processos de tomada de decisão em colaboração. Verificou-se também que a melhoria do processo de tomada de decisão se dá de duas maneiras. A primeira pela compreensão mais ampla pela comunidade dos conceitos e seus relacionamentos de causa e efeito mapeados pelo referencial 5W1H. A segunda pela composição mais adequada dos componentes What, Who, Why, Where, When e How em função do contexto. Ambas maneiras contribuem para o enriquecimento do conhecimento sobre os domínios considerados. / The exponential growth in the use of social media on the Web is transforming the which people treat information, interact with it, and share knowledge. Similarly, organizations are changing the way they interact with their employees, partners, and consumers. New Internet applications have emerged to provide users with confidence and encourage them to interact and connect to each other and to access contents made available. These applications can identify behaviors, extract opinions, and return information of interest to users and organizations in order to support decision making. These applications provide large amounts of data and require complex analysis processes. These analyzes open opportunities for the development of new solutions that add value to users of products and services available on the Web. Companies and research institutions have developed means to handle the large volume of data and identify business opportunities. The use of models that allow to understand this collective phenomenon has increased in recent years for basically two reasons: the need to discover, organize and represent empirical knowledge related to a particular domain of interest and the need to disseminate mechanisms to support the decision-makers. In this context, domain ontologies have been widely used as a form of organization and representation of the knowledge. However, there are few models or applications that extract, organize, and represent the contextualized (implicit and explicit) knowledge of groups of people who act collectively to solve common problems or produce something new. This research proposes a reference model for extracting the collective intelligence (CI) for decision making support. The model was initially developed for strategic planning of IT to be used by government organizations. As part of the model, an innovative domain ontology called ITMPvoc was developed. From its construction and validation process, the model extracts the CI that is contextualized according to the 5W1H (What, Who, Why, Where, How) framework and it is applied for decision making support in specific situations. Other instances of the model are also presented for two use cases. They are: extraction and decision making support based on CI for (I) early warning disease in agriculture and (ii) early warning in adoption of free software by municipalities. The results demonstrate that the CI extraction model from human communities or organizations can improve complex collaborative decision-making processes. It was also found that the improvement of the decision-making process occurs in two ways. The first is by the community\'s broader understanding of concepts and their cause-and-effect relationships mapped by the 5W1H framework. The second is the most appropriate composition of the What, Who, Why, Where, When, and How components, according to the context. Both ways contribute to the enrichment of the knowledge about the considered domains.

O crescimento exponencial do uso das mídias sociais na Web está transformando a maneira de como as pessoas tratam as informações, interagem com elas e compartilham conhecimento. Da mesma forma, as organizações estão mudando a maneira de interagir com seus funcionários, parceiros e consumidores. Novas aplicações na Internet têm surgido para proporcionar confiança aos usuários e incentivá-los a interagir e conectá-los uns aos outros e a conteúdos disponibilizados. Essas aplicações podem identificar comportamentos, extrair opiniões e retornar informações de interesse dos usuários e das organizações de maneira a auxiliar a tomada de decisão. Essas aplicações proporcionam grande volume de dados e demandam complexos processos de análise. Essas análises abrem oportunidades para o desenvolvimento de novas soluções que agregam mais valor aos usuários de produtos e serviços disponibilizadas na Web. Empresas e instituições de pesquisa têm desenvolvidos meios para tratar o grande volume de dados e identificar oportunidades de negócio. O uso de modelos que permitem entender esse fenômeno coletivo tem aumentado nos últimos anos por, basicamente, duas razões: a necessidade de descobrir, organizar e representar o conhecimento empírico relacionado a um determinado domínio de interesse e a necessidade de disseminar mecanismos para auxiliar os tomadores de decisão. Nesse contexto, ontologias de domínio têm sido bastante utilizadas como forma de organização e representação do conhecimento. No entanto, são poucos os modelos ou aplicações que extraem, organizam e representam o conhecimento (implícito e explícito) contextualizado de grupos de pessoas que atuam coletivamente para resolver problemas comuns ou produzir algo novo. Este trabalho de pesquisa propõe um modelo de referência para extração da inteligência coletiva (IC) para suporte à tomada de decisão. O modelo foi inicialmente desenvolvido para caso do planejamento estratégico de TI para ser utilizada por órgãos de governo. Como parte do modelo, foi desenvolvida uma inovadora ontologia de domínio denominada ITMPvoc. De seu processo de construção e validação, o modelo extrai a IC que é contextualiza segundo o referencial 5W1H (What, Who, Why, Where, When, How) e aplicada para suporte à decisão em situações específicas. Outras instâncias do modelo para dois casos de uso são também apresentadas. São elas: extração da IC e suporte à decisão para alertas de doenças na agricultura e para alertas sobre adoção de software livre por municípios. Os resultados demonstram que os modelos de extração da IC de comunidades ou organizações humanas podem melhorar os complexos processos de tomada de decisão em colaboração. Verificou-se também que a melhoria do processo de tomada de decisão se dá de duas maneiras. A primeira pela compreensão mais ampla pela comunidade dos conceitos e seus relacionamentos de causa e efeito mapeados pelo referencial 5W1H. A segunda pela composição mais adequada dos componentes What, Who, Why, Where, When e How em função do contexto. Ambas maneiras contribuem para o enriquecimento do conhecimento sobre os domínios considerados. / The exponential growth in the use of social media on the Web is transforming the which people treat information, interact with it, and share knowledge. Similarly, organizations are changing the way they interact with their employees, partners, and consumers. New Internet applications have emerged to provide users with confidence and encourage them to interact and connect to each other and to access contents made available. These applications can identify behaviors, extract opinions, and return information of interest to users and organizations in order to support decision making. These applications provide large amounts of data and require complex analysis processes. These analyzes open opportunities for the development of new solutions that add value to users of products and services available on the Web. Companies and research institutions have developed means to handle the large volume of data and identify business opportunities. The use of models that allow to understand this collective phenomenon has increased in recent years for basically two reasons: the need to discover, organize and represent empirical knowledge related to a particular domain of interest and the need to disseminate mechanisms to support the decision-makers. In this context, domain ontologies have been widely used as a form of organization and representation of the knowledge. However, there are few models or applications that extract, organize, and represent the contextualized (implicit and explicit) knowledge of groups of people who act collectively to solve common problems or produce something new. This research proposes a reference model for extracting the collective intelligence (CI) for decision making support. The model was initially developed for strategic planning of IT to be used by government organizations. As part of the model, an innovative domain ontology called ITMPvoc was developed. From its construction and validation process, the model extracts the CI that is contextualized according to the 5W1H (What, Who, Why, Where, How) framework and it is applied for decision making support in specific situations. Other instances of the model are also presented for two use cases. They are: extraction and decision making support based on CI for (I) early warning disease in agriculture and (ii) early warning in adoption of free software by municipalities. The results demonstrate that the CI extraction model from human communities or organizations can improve complex collaborative decision-making processes. It was also found that the improvement of the decision-making process occurs in two ways. The first is by the community\'s broader understanding of concepts and their cause-and-effect relationships mapped by the 5W1H framework. The second is the most appropriate composition of the What, Who, Why, Where, When, and How components, according to the context. Both ways contribute to the enrichment of the knowledge about the considered domains.

Submitted by Maria Medeiros (maria.dilva1@ufcg.edu.br) on 2018-06-05T14:49:44Z No. of bitstreams: 1 ALEX SANDRO DA CUNHA RÊGO - TESE (PPGCC) 2016.pdf: 1783053 bytes, checksum: 4ae3b5d42dde739cfd57afaa25fd7e63 (MD5) / Made available in DSpace on 2018-06-05T14:49:44Z (GMT). No. of bitstreams: 1 ALEX SANDRO DA CUNHA RÊGO - TESE (PPGCC) 2016.pdf: 1783053 bytes, checksum: 4ae3b5d42dde739cfd57afaa25fd7e63 (MD5) Previous issue date: 2016 / As folksonomias têm despontado como ferramentas úteis de gerenciamento online de conteúdo digital. A exemplo dos populares websites Delicious, Flickr e BibSonomy, diariamente os usuários utilizam esses sistemas para efetuar upload de recursos web (e.g., url, fotos, vídeos e referências bibliográficas) e categorizá-los por meio de tags. A ausência de relações semânticas do tipo sinonímia e hiperonímia/hiponímia no espaço de tags das folksonomias reduz a capacidade do usuário de encontrar recursos relevantes. Para mitigar esse problema, muitos trabalhos de pesquisa se apoiam na aplicação de medidas de similaridade para detecção de sinonímia e construção automática de hierarquias de tags por meio de algoritmos heurísticos. Nesta tese de doutorado, o problema de detecção de sinonímia e hiperonímia/hiponímia entre pares de tags é modelado como um problema de classificação em Aprendizado de Máquina. A partir da literatura, várias medidas de similaridade consideradas boas indicadoras de sinonímia e hiperonímia/hiponímia foram identificadas e empregadas como atributos de aprendizagem. A incidência de um severo desbalanceamento e sobreposição de classes motivou a investigação de técnicas de balanceamento para superar ambos os problemas. Resultados experimentais usando dados reais das folksonomias BibSonomy e Delicious mostraram que a abordagem proposta denominada CPDST supera em termos de acurácia o baseline de melhor desempenho nas tarefas de detecção de sinonímia e hiperonímia/hiponímia. Também, aplicou-se a abordagem CPDST no contexto de geração de listas de tags semanticamente relacionadas, com o intuito de prover acesso a recursos adicionais anotados com outros conceitos pertencentes ao domínio da busca. Além da abordagem CPDST, foram propostos dois algoritmos fundamentados no acesso ao WordNet e ConceptNet para sugestão de listas especializadas com tags sinônimas e hipônimas. O resultado de uma avaliação quantitativa demonstrou que a abordagem CPDST provê listas de tags relevantes em relação às listas providas pelos métodos comparados. / Folksonomies have emerged as useful tools for online management of digital content. Popular websites as Delicious, Flickr and BibSonomy are now widespread with thousands of users using them daily to upload digital content (e.g., webpages, photos, videos and bibliographic information) and tagging for later retrieval. The lack of semantic relations such as synonym and hypernym/hyponym in the tag space may diminish the ability of users in finding relevant resources. Many research works in the literature employ similarity measures to detect synonymy and to build hierarchies of tags automatically by means of heuristic algorithms. In this thesis, the problems of synonym and subsumption detection between pairs of tags are cast as a pairwise classification problem. From the literature, several similarity measures that are good indicators of synonymy and subsumption were identified, which are used as learning features. Under this setting, there is a severe class imbalance and class overlapping which motivated us to investigate and employ class imbalance techniques to overcome these problems. A comprehensive set of experiments were conducted on two large real-world datasets of BibSonomy and Delicious systems, showing that the proposed approach named CPDST outperforms the best performing heuristic-based baseline in the tasks of synonym and subsumption detection. CPDST is also applied in the context of tag list generation for providing access to additional resources annotated with other semantically related tags. Besides CPDST approach, two algorithms based on WordNet and ConceptNet accesses are proposed for capturing specifically synonyms and hyponyms. The outcome of an evaluative quantitative analysis showed that CPDST approach yields relevant tag lists in relation to the produced ones by the compared methods.