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.


A Graph-based core model and a hybrid recommender system for TV users
Taşcı, Arda; Çiçekli, Fehime Nihan; Department of Computer Engineering (2015)
This thesis proposes a core model to represent user profiles in a graph-based environment which can be the base of different recommender system approaches as well as other cutting edge applications for TV domain. The proposed graph-based core model is explained in detail with node types, properties and edge weight metrics. The capabilities of this core model are described in detail. Moreover, in this thesis, a hybrid recommender system based on this core model is presented with its design, development and e...
Social media and word-of-mouth dispersion : factors affecting likelihood of diffusion
Kursun, Zuhal Sinem; Yılmaz, Cengiz; Department of Business Administration (2013)
This study aims to analyse the factors behind electronic word-of-mouth participation on social network sites, especially on Twitter. For this purpose, the general drivers behind such activity is classified, and other sub-factors were categorised under these drivers were categorised as influencers and determinants. Both individual and environmental factors were studied for a comprehensive analysis about factors increasing or decreasing the likelihood of diffusion of word-of-mouth messages. Besides the hypoth...
Investigating networked learning in corporate context: an embedded design mixed method study examining online knowledge sharing and collaboration via social network analysis
Tufan, Didem; Yıldırım, İbrahim Soner; Günel Kılıç, Banu; Department of Computer Education and Instructional Technology (2016)
This study, implementing an Embedded Mixed Method Design incorporating Social Network Analysis (SNA), aimed to explore how employees participated and communicated in a networked learning environment within corporate context by investigating employees’ discussions on an online wall platform. For this aim, Learning Management System logs of an e-learning company is used. They included self-organizing social groups, in an informal learning environment. The wall platform data from two social groups, including 5...
Utilization of social networking websites in education: a case of facebook
Tınmaz, Hasan; Çağıltay, Kürşat; Department of Computer Education and Instructional Technology (2011)
The aim of this study is to seek fundamental uses and gratifications of a social networking website, Facebook as a case, and the possible advantages and the challenges of utilization of Facebook for instructional activities. The research study encompassed four main steps; the analysis of uses & gratifications of Facebook, the analysis of Facebook utilization possibilities for instruction, the interviewing for two preceding steps, and the realization and analysis of a course on Facebook. In the study both qu...
A Hypergraph based framework for representing aggregated user profiles, employing it for a recommender system and personalized search through a hypernetwork method
Tarakçı, Hilal; Manguoğlu, Murat; Çiçekli, Fehime Nihan; Department of Computer Engineering (2017)
In this thesis, we present a hypergraph based user modeling framework to aggregate partial profiles of the individual and obtain a complete, semantically enriched, multi-domain user model. We also show that the constructed user model can be used to support different personalization services including recommendation. We evaluated the user model against datasets consisting of user's social accounts including Facebook, Twitter, LinkedIn and Stack Overflow. The evaluation results confirmed that the proposed use...
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.