Proceedings/Recueil Des Communications Année : 2024

Fake News Detection Using Large Language Models and Sentiment Analysis

Résumé

Spreading false information (i.e. fake news) has increased with the recent rise of social media. This is a serious threat facing our modern society. To help combating this problem, this paper introduces a novel approach by combining large language models (LLMs) with sentiment analysis. LLMs like BERT (Bidirectional Encoder Representations from Transformers) are adept at identifying linguistic patterns indicative of misinformation, leveraging their vast data corpus. Sentiment analysis adds another layer by analyzing user behavior. The integration of these two concepts offers robust detection and mitigation of fake news, improving accuracy and efficiency. Our extensive experimental analysis shows promising results, demonstrating the importance of this multifaceted approach in combating misinformation and fostering a more informed society.

Fichier non déposé

Dates et versions

hal-04945786 , version 1 (13-02-2025)

Identifiants

Citer

Wissam Bouaraki, Asma Saibi, Yasmine Guerbai, Abdenour Hadid. Fake News Detection Using Large Language Models and Sentiment Analysis. 2024 2nd International Conference on Foundation and Large Language Models (FLLM), Nov 2024, Dubai, United Arab Emirates. IEEE, pp.15-20, 2024, ⟨10.1109/FLLM63129.2024.10852453⟩. ⟨hal-04945786⟩

Collections

135 Consultations
0 Téléchargements

Altmetric

Partager

  • More