Social Media Rumor Refuter Feature Analysis and Crowd Identification Based on XGBoost and NLP

One prominent dark side of online information behavior is the spreading of rumors. The feature analysis and crowd identification of social media rumor refuters based on machine learning methods can shed light on the rumor refutation process. This paper analyzed the association between user features and rumor refuting behavior in five main rumor categories: economics, society, disaster, politics, and military. Natural language processing (NLP) techniques are applied to quantify the user’s sentiment tendency and recent interests. Then, those results were combined with other personalized features to train an XGBoost classification model, and potential refuters can be identified. Information from 58,807 Sina Weibo users (including their 646,877 microblogs) for the five anti-rumor microblog categories was collected for model training and feature analysis. The results revealed that there were significant differences between rumor stiflers and refuters, as well as between refuters for different categories. Refuters tended to be more active on social media and a large proportion of them gathered in more developed regions. Tweeting history was a vital reference as well, and refuters showed higher interest in topics related with the rumor refuting message. Meanwhile, features such as gender, age, user labels and sentiment tendency also varied between refuters considering categories.