Personalized recommender system based on friendship strength in social network services

详细信息    查看全文

• 作者：Young-Duk Seo^a ; ^{seoyoungd@korea.ac.kr" class="auth_mail" title="E-mail the corresponding author} ; Young-Gab Kim^b ; ^{always.gabi@gmail.com" class="auth_mail" title="E-mail the corresponding author} ; ^{alwaysgabi@sejong.ac.kr" class="auth_mail" title="E-mail the corresponding author} ; Euijong Lee^a ; ^{kongjjagae@korea.ac.kr" class="auth_mail" title="E-mail the corresponding author} ; Doo-Kwon Baik^a ; ^{baikdk@korea.ac.kr" class="auth_mail" title="E-mail the corresponding author}
• 关键词：Personalized recommender system ; Social network services ; Friendship strength ; Social behavior ; Collaborative filtering (CF)
• 刊名：Expert Systems with Applications
• 出版年：2017
• 出版时间：1 March 2017
• 年：2017
• 卷：69
• 期：Complete
• 页码：135-148
• 全文大小：2036 K

文摘

The rapid growth of social network services has produced a considerable amount of data, called big social data. Big social data are helpful for improving personalized recommender systems because these enormous data have various characteristics. Therefore, many personalized recommender systems based on big social data have been proposed, in particular models that use people relationship information. However, most existing studies have provided recommendations on special purpose and single-domain SNS that have a set of users with similar tastes, such as MovieLens and Last.fm; nonetheless, they have considered closeness relation. In this paper, we introduce an appropriate measure to calculate the closeness between users in a social circle, namely, the friendship strength. Further, we propose a friendship strength-based personalized recommender system that recommends topics or interests users might have in order to analyze big social data, using Twitter in particular. The proposed measure provides precise recommendations in multi-domain environments that have various topics. We evaluated the proposed system using one month's Twitter data based on various evaluation metrics. Our experimental results show that our personalized recommender system outperforms the baseline systems, and friendship strength is of great importance in personalized recommendation.