Causality-based Social Media Analysis for Normal Users Credibility Assessment in a Political Crisis

• Main Authors: Ahmed Abouzeid, Ole.Christoffer Granmo, Christian Webersik, Morten Goodwin
• Format: Article
• Language: English
• Published: FRUCT 2019-11-01
• Series: Proceedings of the XXth Conference of Open Innovations Association FRUCT
• Subjects: fake news; social media analysis; bayesian networks; causality analysis
• Online Access: https://fruct.org/publications/fruct25/files/Abo.pdf

Information trustworthiness assessment on political social media discussions is crucial to maintain the order of society, especially during emergent situations. The polarity nature of political topics and the echo chamber effect by social media platforms allow for a deceptive and a dividing environment. During a political crisis, a vast amount of information is being propagated on social media, that leads up to a high level of polarization and deception by the beneficial parties. The traditional approaches to tackling misinformation on social media usually lack a comprehensive problem definition due to its complication. This paper proposes a probabilistic graphical model as a theoretical view on the problem of normal users credibility on social media during a political crisis, where polarization and deception are keys properties. Such noisy signals dramatically influence any attempts for misinformation detection. Hence, we introduce a causal Bayesian network, inspired by the potential main entities that would be part of the process dynamics. Our methodology examines the problem solution in a causal manner which considers the task of misinformation detection as a question of cause and effect rather than just a classification task. Our causality-based approach provides a practical road map for some sub-problems in real-world scenarios such as individual polariza- tion level, misinformation detection, and sensitivity analysis of the problem. Moreover, it facilitates intervention simulations which would unveil both positive and negative effects on the deception level over the network.