Determining the Veracity of Rumours on Twitter

TL;DR

This paper presents a machine learning approach to automatically assess the trustworthiness of rumours on Twitter by analyzing a large dataset of tweets and various trust indicators, improving accuracy over previous methods.

Contribution

The study introduces a comprehensive trustworthiness model using multiple features and demonstrates its effectiveness in real-time rumour verification on Twitter.

Findings

Model outperforms similar studies in accuracy

Identifies key attributes influencing trustworthiness scores

Provides a visual tool for rumour analysis

Abstract

While social networks can provide an ideal platform for up-to-date information from individuals across the world, it has also proved to be a place where rumours fester and accidental or deliberate misinformation often emerges. In this article, we aim to support the task of making sense from social media data, and specifically, seek to build an autonomous message-classifier that filters relevant and trustworthy information from Twitter. For our work, we collected about 100 million public tweets, including users' past tweets, from which we identified 72 rumours (41 true, 31 false). We considered over 80 trustworthiness measures including the authors' profile and past behaviour, the social network connections (graphs), and the content of tweets themselves. We ran modern machine-learning classifiers over those measures to produce trustworthiness scores at various time windows from the outbreak of the rumour. Such time-windows were key as they allowed useful insight into the progression of the rumours. From our findings, we identified that our model was significantly more accurate than similar studies in the literature. We also identified critical attributes of the data that give rise to the trustworthiness scores assigned. Finally we developed a software demonstration that provides a visual user interface to allow the user to examine the analysis.