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

Zongmin Li,Shihang Wang,Qi Zhang,Yuhong Wang

doi:10.3390/app10144711

Zongmin Li, Shihang Wang + Show 2 more

Open Access

https://doi.org/10.3390/app10144711

Copy DOI

Abstract

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.

Highlights

Because of the widespread popularity of social networks and mobile devices, users are able to immediately exchange information and ideas or access news reports through social media feeds such as Twitter, Facebook, or Sina Weibo [1]
This paper extended the scope of current studies, instead of studying the general features of retweeters or the opposite group, rumor spreaders, it focused on refuters and specified them with five main rumor categories that can affect social stability
The purpose of the current study was to determine the association between user features and their refuting behaviors and so as to identify the rumor refuters, and deal with the dark side of online information behavior by accelerating the rumor refutation information dissemination

Summary

Introduction

Because of the widespread popularity of social networks and mobile devices, users are able to immediately exchange information and ideas or access news reports through social media feeds such as Twitter, Facebook, or Sina Weibo [1]. Due to a general lack of control, incorrect, exaggerated, or distorted information can be circulated throughout the networks [2]. This kind of information is defined as a rumor [3]. Rumors have been found to affect a country’s public opinion [5], lead to economic losses [6], and even cause political consequences [7].

Objectives

Results

Discussion

Conclusion