An In-depth Analysis of Transformer Models for Enhanced Performance in Fake News Detection

The internet has revolutionized global communication, connecting the entire world. However, a significant challenge it faces is the rampant spread of fake news. Transformer models have transformed Natural Language Processing (NLP). This study aims to assess the effectiveness of various transformer m...

Full description

Saved in:
Bibliographic Details
Published in2024 5th International Conference on Image Processing and Capsule Networks (ICIPCN) pp. 158 - 165
Main Authors Kumar, Shailender, Malhotra, Naman, Garg, Naman, Shakil, Md Asjad
Format Conference Proceeding
LanguageEnglish
Published IEEE 03.07.2024
Subjects
Deep Learning
Fake News
Image processing
Large language models
Machine Learning
Natural language processing
Reliability
Semantics
Training
Transformers
Online AccessGet full text
DOI10.1109/ICIPCN63822.2024.00034

Cover

More Information
Summary:The internet has revolutionized global communication, connecting the entire world. However, a significant challenge it faces is the rampant spread of fake news. Transformer models have transformed Natural Language Processing (NLP). This study aims to assess the effectiveness of various transformer models in identifying false information using the LIAR benchmark datasets, which are sourced from credible fact-checking and claim verification platforms. Additionally, this study proposes a modified transformer model to enhance the efficiency in detecting the fake news. By integrating advanced NLP techniques, this research improves the accuracy and reliability of fake news detection, addressing a critical issue in this digital era.
DOI:10.1109/ICIPCN63822.2024.00034