Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{193551,
        author = {Harsh Gupta and Arohi Sanon and Prof. Dr. Sanjeev Thakur},
        title = {Cross-Lingual Fake News Detection Using Transformer-Based Deep Learning: An English-Hindi Approach},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {10},
        pages = {2239-2248},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=193551},
        abstract = {The exponential growth of online misinformation across diverse linguistic communities necessitates robust multilingual detection mechanisms. This study presents a transformer-based deep learning system for automated fake news detection in English and Hindi languages. We develop and evaluate a fine-tuned XLM RoBERTa model trained on 60,000 synthesized news articles equally distributed across both languages. Our architecture combines pre-trained multilingual representations with a custom three-layer classification network incorporating batch normalization and progressive dropout regularization. Experimental results demonstrate exceptional performance, achieving 100% validation accuracy with perfect precision, recall, and F1-scores across all five training epochs. The model successfully handles cross script processing (Latin and Devanagari) while maintaining inference speeds suitable for real-time deployment. We implement a web-based interface demonstrating practical applicability for content moderation and media literacy applications. Our findings indicate that transfer learning from massively multilingual pre trained transformers enables effective misinformation detection across typologically distinct languages, providing a scalable foundation for expanding to additional linguistic communities facing similar challenges.},
        keywords = {Misinformation detection, multilingual transformers, XLM RoBERTa, cross lingual NLP, Hindi natural language processing, deep learning, content moderation},
        month = {March},
        }