Rumor Stance Classification in Online Social Networks: A Survey on the State-of-the-Art, Prospects, and Future Challenges

The emergence of the Internet as a ubiquitous technology has facilitated the rapid evolution of social media as the leading virtual platform for communication, content sharing, and information dissemination. In spite of revolutionizing the way news used to be delivered to people, this technology has also brought along with itself inevitable demerits. One such drawback is the spread of rumors facilitated by social media platforms which may provoke doubt and fear upon people. Therefore, the need to debunk rumors before their wide spread has become essential all the more. Over the years, many studies have been conducted to develop effective rumor verification systems. One aspect of such studies focuses on rumor stance classification, which concerns the task of utilizing users' viewpoints about a rumorous post to better predict the veracity of a rumor. Relying on users' stances in rumor verification task has gained great importance, for it has shown significant improvements in the model performances. In this paper, we conduct a comprehensive literature review on rumor stance classification in complex social networks. In particular, we present a thorough description of the approaches and mark the top performances. Moreover, we introduce multiple datasets available for this purpose and highlight their limitations. Finally, some challenges and future directions are discussed to stimulate further relevant research efforts.