A topic-focused trust model for Twitter

Liang Zhao, Ting Hua, Chang-Tien Lu

Abstract

Twitter is a crucial platform to get access to breaking news and timely information. However, due to questionable provenance, uncontrollable broadcasting, and unstructured languages in tweets, Twitter is hardly a trustworthy source of breaking news. In this paper, we propose a novel topic-focused trust model to assess trustworthiness of users and tweets in Twitter. Unlike traditional graph-based trust ranking approaches in the literature, our method is scalable and can consider heterogeneous contextual properties to rate topic-focused tweets and users. We demonstrate the effectiveness of our topic-focused trustworthiness estimation method with extensive experiments using real Twitter data in Latin America.