A Proposed Method for Predicting User Disinformation Forwarding Behavior

Abstract

At present, social network sites (SNSs) have become the major channels by which disinformation is released and disseminated. Without the effective control of disinformation on social media, a serious threat to social stability may occur. Different from traditional media, forwarding has become the key approach to propagating information on social media. Therefore, if the users who will forward the disinformation are identified in advance, they can be prevented from forwarding the disinformation and the harmful effects of disinformation will be minimized. To identify the users who will forward the disinformation, we should predict the probability of an individual forwarding disinformation. We propose a novel method to predict the disinformation forwarding probability of individuals on a social network. The proposed method extracts the features that affect individual disinformation forwarding, especially extracting features related to the susceptibility of users to disinformation. With combining bootstrap sampling and expectation-maximization (EM) algorithm to learn unobserved features, the proposed method utilizes both observed and unobserved features to predict the disinformation forwarding probability of individuals. Using data from “Weibo,” which is the largest social media platform in China, we demonstrate the effectiveness of the proposed method.