A Progressive Step Towards Automated Fact-Checking by Detecting Context in Diverse Languages: A Prototype for Bangla Facebook Posts

Mahbuba Shefa, Tasnuva Ferdous, Afzal Azeem Chowdhary, Md Jannatul Joy, Tanjila Kanij, Md Al Mamun

2025

Abstract

Fact-Checking has become a critical tool in combating misinformation, particularly on platforms like Face-book, where the rapid spread of false information poses significant challenges. Much work has been done on languages like English but not on low-resource languages like Bangla. To address this gap, we explored the application of classic ML models, RNNs, and BanglaBERT on a small dataset of Bangla Facebook textual posts to understand its context. Surprisingly, BanglaBERT underperformed compared to traditional approaches like models based on TF-IDF embeddings, highlighting the challenges of working with limited data and insufficient fine-tuning. To support fact-checkers, we developed the “Automated Context Detector,” which is developed with NLP and machine learning that automates repetitive tasks, allowing experts to focus on critical decisions. Our results demonstrate the feasibility of using machine learning for context detection in Bangla social media posts, providing a framework adaptable to similar linguistic and cultural settings.

Paper Citation

in Harvard Style

Shefa M., Ferdous T., Chowdhary A., Joy M., Kanij T. and Al Mamun M. (2025). A Progressive Step Towards Automated Fact-Checking by Detecting Context in Diverse Languages: A Prototype for Bangla Facebook Posts. In Proceedings of the 20th International Conference on Evaluation of Novel Approaches to Software Engineering - Volume 1: ENASE; ISBN 978-989-758-742-9, SciTePress, pages 684-691. DOI: 10.5220/0013430000003928

in Bibtex Style

@conference{enase25,
author={Mahbuba Shefa and Tasnuva Ferdous and Afzal Chowdhary and Md Joy and Tanjila Kanij and Md Al Mamun},
title={A Progressive Step Towards Automated Fact-Checking by Detecting Context in Diverse Languages: A Prototype for Bangla Facebook Posts},
booktitle={Proceedings of the 20th International Conference on Evaluation of Novel Approaches to Software Engineering - Volume 1: ENASE},
year={2025},
pages={684-691},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013430000003928},
isbn={978-989-758-742-9},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 20th International Conference on Evaluation of Novel Approaches to Software Engineering - Volume 1: ENASE
TI - A Progressive Step Towards Automated Fact-Checking by Detecting Context in Diverse Languages: A Prototype for Bangla Facebook Posts
SN - 978-989-758-742-9
AU - Shefa M.
AU - Ferdous T.
AU - Chowdhary A.
AU - Joy M.
AU - Kanij T.
AU - Al Mamun M.
PY - 2025
SP - 684
EP - 691
DO - 10.5220/0013430000003928
PB - SciTePress