Rumors detection on X using pre-trained language models

With the rapid proliferation of internet technology, social media platforms, particularly microblogging sites like X (ex Twitter), have emerged as essential channels for news dissemination. However, the widespread dissemination of fake news and rumors has largely overshadowed this growth, primarily due to the absence of stringent oversight. While early research strategies employed traditional machine learning to address this challenge, the sheer volume of data in recent times has made deep learning methods increasingly relevant.In this study, we introduce a retrospective rumor detection model that harnesses the capabilities of fine-tuned pre-trained language models. Our primary model achieved an F1-score of 92.14%. For comparison, we also developed a model that combines a pre-trained language model with a Logistic Regression classifier, obtaining an F1-score of 91.94%. In another model, we evaluated combined pre-trained language models for feature extraction with a Multi-Layer Perceptron (MLP) for classification and registered an F1-score of 92.28%. Intriguingly, our results underscore the potential of straightforward classifiers that leverage rich vectors from pre-trained language models, showing they can rival or even outperform complex neural architectures in rumor detection tasks. This revelation points towards a more efficient and less resource-intensive strategy to tackle online misinformation.

I. Introduction

In recent decades, the information landscape has seen an unprecedented transformation. Microblogging platforms, such as X, have emerged as dominant players in this new era. These platforms allow users to share succinct, real-time updates, reaching a global audience within seconds. Their rapid dissemination capability, coupled with their accessibility, has positioned them as invaluable sources of information for many, rivaling traditional news outlets [1], [2].