Master of Science / Department of Computing and Information Sciences / Doina Caragea / The idea of socializing with other people of different backgrounds and cultures excites the web surfers. Today, there are hundreds of Social Networking sites on the web with millions of users connected with relationships such as "friend", "follow", "fan", forming a huge graph structure. The amount of data associated with the users in these Social Networking sites has resulted in opportunities for interesting data mining problems including friendship link and interest predictions, tag recommendations among others. In this work, we consider the friendship link prediction problem and study a topic modeling approach to this problem. Topic models are among the most effective approaches to latent topic analysis and mining of text data. In particular, Probabilistic Topic models are based upon the idea that documents can be seen as mixtures of topics and topics can be seen as mixtures of words. Latent Dirichlet Allocation (LDA) is one such probabilistic model which is generative in nature and is used for collections of discrete data such as text corpora. For our link prediction problem, users in the dataset are treated as "documents" and their interests as the document contents. The topic probabilities obtained by modeling users and interests using LDA provide an explicit representation for each user. User pairs are treated as examples and are represented using a feature vector constructed from the topic probabilities obtained with LDA. This vector will only capture information contained in the interests expressed by the users. Another important source of information that is relevant to the link prediction task is given by the graph structure of the social network. Our assumption is that a user "A" might be a friend of user "B" if a) users "A" and "B" have common or similar interests b) users "A" and "B" have some common friends. While capturing similarity between interests is taken care by the topic modeling technique, we use the graph structure to find common friends. In the past, the graph structure underlying the network has proven to be a trustworthy source of information for predicting friendship links. We present a comparison of predictions from feature sets constructed using topic probabilities and the link graph separately, with a feature set constructed using both topic probabilities and link graph.

Master of Science / Department of Computing and Information Sciences / Doina Caragea / William H. Hsu / An ontology can be seen as an explicit description of the concepts and relationships that exist in a domain. In this thesis, we address the problem of building an interests' ontology and using the same to construct features for predicting both potential friendship relations between users in the social network Live Journal, and users' interests. Previous work has shown that the accuracy of predicting friendship links in this network is very low if simply interests common to two users are used as features and no network graph features are considered. Thus, our goal is to organize users' interests into an ontology (specifically, a concept hierarchy) and to use the semantics captured by this ontology to improve the performance of learning algorithms at the task of predicting if two users can be friends. To achieve this goal, we have designed and implemented a hybrid clustering algorithm, which combines hierarchical agglomerative and divisive clustering paradigms, and automatically builds the interests' ontology. We have explored the use of this ontology to construct interest-based features and shown that the resulting features improve the performance of various classifiers for predicting friendships in the Live Journal social network. We have also shown that using the interests' ontology, one can address the problem of predicting the interests of Live Journal users, a task that in absence of the ontology is not feasible otherwise as there is an overwhelming number of interests.