Paper #3

Deep Learning and Transformers Accuracy in Rumor Detection on Social Media

Long Yu, Jiarui Dai, Jiaqi Dai and Yanan Wang

Abstract: The increasing popularity of social media platforms has revolutionized how news and information are shared. While these social platforms facilitate rapid dissemination, they also provide fertile ground for the proliferation of rumors and unverified information. False information spreads as quickly as accurate news, often influencing public opinion and decision-making processes. Identifying rumors early is critical to limiting their potential harm and mitigating negative consequences. This study evaluates the practical application and scalability of transformer-based models, specifically GPT-2, in detecting rumors on social media platforms alongside traditional deep learning (DL) models. We explore various deep learning models such as Long Short-Term Memory (LSTM), Convolutional Neural Networks (CNN), ALBERT, and GPT-2. Performance was assessed using standard evaluation metrics, including accuracy, precision, recall, F1-score, and analysis of Receiver Operating Characteristic (ROC) curves. The comparative results reveal that transformer-based approaches significantly outperform traditional DL models in detecting rumors with higher accuracy and reliability. Among the evaluated models, GPT-2 achieved the highest scores across all performance metrics, demonstrating exceptional capability in identifying and predicting rumor-laden content. This study introduces key innovations, including a direct comparative analysis of transformer-based and traditional DL models, highlighting GPT-2’s advanced attention mechanisms that capture nuanced linguistic and contextual features. Additionally, it underscores GPT-2’s scalability for real-world misinformation mitigation and critically examines dataset biases and adaptability challenges. Future advancements, such as multimodal approaches integrating text, images, and videos, as well as hybrid models combining transformers with traditional DL techniques, are proposed to enhance detection accuracy and efficiency. These findings underline the transformative potential of advanced AI techniques in combating misinformation on social media platforms. The research emphasizes the potential for scalable and practical implementation of GPT-2-based tools in mitigating false information dissemination, contributing to a more reliable and resilient digital ecosystem. This work advances the understanding of AI's role in mitigating the spread of false information.

Keywords: Deep Learning (DL); GPT-2 Model; Rumor Detection; Social Media Misinformation; Transformer-Based Models.