A User modeling and recommendation system by means of social networks

Karakaya, Ali
In this thesis, it is aimed to design a system which builds user profiles to model users’ preferences by tracking the activities of the users on social networks. Specifically, Facebook and Twitter are considered as the social networks. The extracted user profiles are used in a recommendation system application. The user data collected from the social networks is enriched with the concepts in Freebase which is an online and public library, and then the enriched data is used to create vector-based and graph-based user models. Content-based, collaborative and hybrid recommendation algorithms that are implemented in this thesis utilize the created user profiles. The suggestions generated by the recommender system are presented to subjects through a survey to evaluate the performance of the user models. Results show that the recommender system using the semantically enriched user profiles provides a high rate of correct suggestions to the users.
Citation Formats
A. Karakaya, “A User modeling and recommendation system by means of social networks,” M.S. - Master of Science, Middle East Technical University, 2014.