Social Media and Microblogs Credibility: Identification, Theory Driven Framework, and Recommendation

Social media microblogs are extensively used to get news and other information. It brings the real challenge to distinguish that what particular information is credible. Especially when user authenticity is hidden, due to the microblog’s anonymity feature. Low credibility content creates an imbalance in society. Therefore many research studies are conducted to assess automatic microblog’s credibility but the majority of them offer different concepts of credibility and the problem seems unresolved. Credibility is multi-disciplinary, hence there is no generalized or accepted credibility concept with all its necessary and detailed constructs/components. Therefore, it is necessary to understand the complete anatomy of information credibility from different disciplines. It is accomplished here through an in-depth and organized study of all the problem dimensions for the identification of comprehensive and necessary credibility constructs. The framework is also proposed based on the identified constructs. It adheres to these constructs and presents their inter-relationships. It is believed that the framework would provide the necessary building blocks for implementing an effective automatic credibility assessment system. The framework is generic to social media and specifically implemented for microblogs. It is completely transformed up to features level, in the context of microblogs. Regarding automatic credibility assessment, it is proposed after detailed analysis that the attempt should be made for hybrid models combining feature-based and graph-based approaches. It is observed that quite a few surveys in the literature focus on some limited aspects of microblogs credibility but no literature survey and fundamental study exists that consolidates the work done. To understand the broader domain of credibility and consolidate the work in this area that can lead us to a suitable framework, we explored the existing literature from different disciplines for the said objectives. We categorized them along various dimensions, developed taxonomy, identified gaps and challenges, proposed a solution, developed a theory-driven framework with its transformation to microblogs, and suggested key areas of research.

Abstract licence: CC BY-NC-ND

A person counts once a day per paper. We keep no cookie and no address: a reader is a hash that changes every day. Any month under five reads shows no number.