Topic-Driven SocialRank: Personalized search result ranking by identifying similar, credible users in a social network

A Social Network Service (SNS) is a type of popular, lifestyle Web service to connect a user with friends, and a user's interest in Web search can affect her friends who have similar interests. If these users' preferences can be tracked, we can show more relevant information following a user's interests. In this paper, we propose the Topic-Driven SocialRank algorithm to show interest-driven search results with relevant Web content from friends using social contacts online by identifying similar, credible users. Our assumption is that credible users issue more relevant information. We observe that a user has certain common interest with her similar friends in the SN, and focus on identifying similar users who have high credibility and sharing their search experiences. Experimental validation shows that our method significantly outperforms the baseline method. Our method is potentially effective to find more relevant search results by implicit help of familiar, credible users. (C) 2013 Elsevier B.V. All rights reserved.