In this paper we present a novel user profile formalization, which allows describingthe user attributes as well as history of user access for personalized, adaptive and interactiveexperience while we believe that our approach is applicable to different semantic applicationswe illustrate our solution in the context of online and onsite museums and exhibits visit. Weargue that a generic structure will allow incorporation of multiple dimensions of user attributesand characteristics as well as allowing different abstraction levels for profile formalization andpresentations. In order to construct such profile structures we extend and enrich existingmetadata vocabularies for cultural heritage to contain keywords pertaining to usage attributesand user related keywords. By extending metadata vocabularies we allow improvedmatchmaking between extended user profile contents and cultural heritage contents. Thisextension creates the possibility of further personalization of access to cultural heritageavailable through online and onsite digital libraries.

User profiles are vastly utilized to alleviate the increasing problem of so called information overload. Many important issues of Semantic Web like trust, privacy, matching and ranking have a certain degree of vagueness and involve truth degrees that one requires to present and reason about. In this ground, profiles tend to be useful and allow incorporation of these uncertain attributes in the form of weights into profiled materials. In order to interpret and reason about these uncertain values, we have constructed a fuzzy confidence model, through which these values could be collectively analyzed and interpreted as collective experience confidence of users. We analyze this model within a scenario, comprising weighted user profiles of a semantically enabled cultural heritage knowledge platform. Initial simulation results have shown the benefits of our mechanism for alleviating problem of sparse and empty profiles.

With the ever increasing importance of social net- working sites and services, socially intelligent agents who are responsible for gathering, managing and maintaining knowledge surrounding individual users are of increasing interest to both computing research communities as well as industries. For these agents to be able to fully capture and manage the knowledge about a user’s interaction with these social sites and services, a social user model needs to be introduced. A social user model is defined as a generic user model (model capable of capturing generic information related to a user), plus social dimensions of users (models capturing social aspects of user such as activities and social contexts). While existing models capture a proportion of such information, they fail to model and present ones of the most important dimensions of social connectivity: trust and privacy. To this end, in this paper, we introduce an ontological model of social user, composed by a generic user model component, which imports existing well-known user model structures, a social model, which contains social dimensions, and trust, reputation and privacy become the pivotal concepts gluing the whole ontological knowledge models together.

Abstract Within this paper we introduce an adaptive framework for semi- tofully-automatic discovery, acquisition and mining of topic style interest profilesfrom openly accessible social web communities. To do such, we build an adaptivetaxonomy search tree from target domain (domain towards which we are gatheringand processing profiles for), starting with generic concepts at root moving down tospecific-level instances at leaves, then we utilize one of proposed Quest schemesto read the concept labels from the tree and crawl the source social networkrepositories for profiles containing matching and related topics. Using machinelearning techniques, cached profiles are then mined in two consecutive steps,utilizing a clusterer and a classifier in order to assign and predict correct profilesto their corresponding clustered corpus, which are retrieved later on by an ontology-based recommender to suggest and recommend the community members with theitems of their similar interest. Focusing on increasingly important digital culturalheritage context, using a set of profiles acquired from an openly accessible socialnetwork, we test the accuracy and adaptivity of framework. We will show that a tradeoff between schemes proposed can lead to adaptive discovery of highly relevant profiles.

Social Networks have dominated growth and popularity of the Web to an extent which has never been witnessed before. Such popularity puts forward issue of trust to the participants of Social Networks. Collaborative Filtering Recommenders have been among many systems which have begun taking full advantage of Social Trust phenomena for generating more accurate predictions. For analyzing the evolution of constructed networks of trust, we utilize Collaborative Filtering enhanced with T-index as an estimate of a user's trustworthiness to identify and select neighbors in an effective manner. Our empirical evaluation demonstrates how T-index improves the Trust Network structure by generating connections to more trustworthy users. We also show that exploiting T-index results in better prediction accuracy and coverage of recommendations collected along few edges that connect users on a network.

Information overload has become an increasingly common problem in today’s large scale internet applications. Collaborative filtering(CF) recommendation systems have emerged   as a popular solution to this problem by taking advantage of underlying social networks. Traditional CF recommenders suffer from lack of scalability[18] while decentralized recommendation systems (DHT-based, Gossip-based etc.) have promised to alleviate this problem. Thus, in this paper we propose a decentralized approach to CF recommender sys  tems that takes advantage of the popular P2P T-Man algorithm to create and maintain an overlay network capable of generating predictions based on only local information. We       analyze our approaches performance in terms of prediction accuracy and item-coverage function of neighborhood size as well as number of T-Man rounds. We show our system       achieves better accuracy than previous approaches while implementing a highly scalable, decentralized paradigm. We also show our system is able to generate predictions for a       large fraction of users, which is comparable with the centralized approaches.

Collaborative filtering (CF) recommenders are subject to numerous shortcomings such as centralized processing, vulnerability to shilling attacks, and most important of all privacy. To overcome these obstacles, researchers proposed for utilization of interpersonal trust between users, to alleviate many of these crucial shortcomings. Till now, attention has been mainly paid to strong points about trust-aware recommenders such as alleviating profile sparsity or calculation cost efficiency, while least attention has been paid on investigating the notion of privacy surrounding the disclosure of individual ratings and most importantly protection of trust computation across social networks forming the backbone of these systems. To contribute to addressing problem of privacy in trust-aware recommenders, within this paper, first we introduce a framework for enabling privacy-preserving trust-aware recommendation generation. While trust mechanism aims at elevating recommenders accuracy, to preserve privacy, accuracy of the system needs to be decreased. Since within this context, privacy and accuracy are conflicting goals we show that a Pareto set can be found as an optimal setting for both privacy-preserving and trust-enabling mechanisms. We show that this Pareto set, when used as the configuration for measuring the accuracy of base collaborative filtering engine, yields an optimized tradeoff between conflicting goals of privacy and accuracy. We prove this concept along with applicability of our framework by experimenting with accuracy and privacy factors, and we show through experiment how such optimal set can be inferred.

E-commerce Web sites owe much of their popularity to consumer reviews provided together with productdescriptions. On-line customers spend hours and hours going through heaps of textual reviews to buildconfidence in products they are planning to buy. At the same time, popular products have thousands of user-generated reviews. Current approaches to present them to the user or recommend an individual review for aproduct are based on the helpfulness or usefulness of each review. In this paper we look at the top-k reviewsin a ranking to give a good summary to the user with each review complementing the others. To this endwe use Latent Dirichlet Allocation to detect latent topics within reviews and make use of the assigned starrating for the product as an indicator of the polarity expressed towards the product and the latent topicswithin the review. We present a framework to cover different ranking strategies based on the user’s need:Summarizing all reviews; focus on a particular latent topic; or focus on positive, negative or neutral aspects.We evaluated the system using manually annotated review data from a commercial review Web site.

While the focus of trust research has been mainly on defining and modeling various notions of social trust, less attention has been given to modeling opinion trust. When speaking of social trust mainly homophily (similarity) has been the most successful metric for learning trustworthy links, specially in social web applications such as collaborative filtering recommendation systems. While pure homophily such as Pearson coefficient correlation and its variations, have been favorable to finding taste distances between individuals based on their rated items, they are not necessarily useful in finding opinion distances between individuals discussing a trending topic, e. g. Arab spring. At the same time text mining techniques, such as vector-based techniques, are not capable of capturing important factors such as saliency or polarity which are possible with topical models for detecting, analyzing and suggesting aspects of people mentioning those tags or topics. Thus, in this paper we are proposing to model opinion distances using probabilistic information divergence as a metric for measuring the distances between people's opinion contributing to a discussion in a social network. To acquire feature sets from topics discussed in a discussion we use a very successful topic modeling technique, namely Latent Dirichlet Allocation (LDA). We use the distributions resulting to model topics for generating social networks of group and individual users. Using a Twitter dataset we show that learned graphs exhibit properties of real-world like networks.