A user modeling and recommendation system by means of social networks

---

Tezin Türü: Yüksek Lisans

Tezin Yürütüldüğü Kurum: Orta Doğu Teknik Üniversitesi, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümü, Türkiye

Tezin Onay Tarihi: 2014

Öğrenci: ALİ KARAKAYA

Danışman: FEHİME NİHAN ÇİÇEKLİ

Özet:

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.