A Hybrid Deep Learning Architecture for Misinformation Detection on Social Media

Social media has grown to become a popular source of news and information for users around the world. However, the strength of fast dissemination of information to users in diverse places also exposes social media platforms, including Twitter, to the spread of misinformation, such as rumors or false information. Automated classification of such news on social media is a challenging task. In this study, we propose a hybrid deep learning model that utilizes a Features-Based model (FB) extracted from two levels: tweet level and user level, combined with pre-trained text embedding models such as Global Vectors for word representation (GloVe) and Universal Sentence Encoders (USE). The models were evaluated on a real-world dataset containing a collection of Twitter rumors and non-rumors. The experimental evaluation results reveal that our hybrid deep-learning model achieves higher accuracy in detecting rumors compared to the baseline learners and previous methods. Further, a hybrid model that combined a features-based model and text embedding model led to improve performance compared to use a single model.

I. Introduction

Social media has grown to become a popular source of general information and news for many consumers around the world. A 2022 survey by Pew Research revealed that approximately 17% of Americans often get news from social media and 33% sometimes get news from social sites, representing a substantial proportion of the population coming across news items for the first time on popular social media networks [1]. Twitter is one of the most popularly used sites for news, ranking behind Facebook as the platform most frequented by adults, especially in the United States, for news [1]. As with other social media platforms, information on Twitter is posted by an individual or organization with no filtering or fact-checking for the content, which can cause a significant negative impact both on individuals and society. The fact that the information originates from individuals or organizations and is not verified or fact-checked makes Twitter and other social media platforms powerful agents of spreading misinformation [2].