AUTHOR=Padalko Halyna , Chomko Vasyl , Chumachenko Dmytro 

TITLE=A novel approach to fake news classification using LSTM-based deep learning models

JOURNAL=Frontiers in Big Data

VOLUME=Volume 6 - 2023

YEAR=2024

URL=https://www.frontiersin.org/journals/big-data/articles/10.3389/fdata.2023.1320800

DOI=10.3389/fdata.2023.1320800

ISSN=2624-909X

ABSTRACT=In the era of rapid information dissemination, distinguishing genuine news from fabricated narratives has become a significant challenge. The proliferation of fake news, especially on digital platforms, necessitates the development of advanced tools for accurate detection and classification. This study was initiated to address the challenge of fake news detection, emphasizing the potential of deep learning models, specifically the BiLSTM and attention-based BiLSTM architectures. The research utilized these models, integrating an attention mechanism to weigh the significance of different parts of the input data. Benchmarking against existing models from the literature revealed the superior efficacy of the proposed architectures. The attention-based BiLSTM, in particular, demonstrated remarkable proficiency, outperforming other models in terms of accuracy 97,66% and other key metrics. The study underscores the potential of integrating advanced deep learning techniques, especially attention mechanisms, in fake news detection. The proposed models set new standards in the field, offering practical tools for combating misinformation and upholding the integrity of information in the digital age.