Fake news detection in Dravidian languages using transfer learning with adaptive finetuning

• Published in: Engineering applications of artificial intelligence 2023-11, Vol.126, p.106877, Article 106877
• Main Authors: Raja, Eduri, Soni, Badal, Borgohain, Samir Kumar
• Format: Article
• Language: English
• Subjects: Dravidian languages; Fake news; Low-resource languages; Transfer learning; Transformers
• ISSN: 0952-1976; 1873-6769
• DOI: 10.1016/j.engappai.2023.106877

Fake news has become a major challenge for online platforms and society as a whole, with potentially harmful consequences for individuals and organizations. While there has been a lot of research on detecting fake news in high-resource languages, very little attention has been paid to low-resource languages. Due to a lack of corpora and annotated data, the classification of fake news in low-resource languages remains in its infancy. In this research, we present a novel transfer learning strategy for detecting fake news in Dravidian languages. We introduced a Dravidian_Fake a new dataset for fake news classification in Dravidian languages, and we created multilingual datasets by combining the English ISOT with the Dravidian_Fake datasets. We fine-tuned the mBERT and XLM-R pretrained transformer models with adaptive learning using English and Dravidian language fake news datasets. The classification model is evaluated using transfer learning, and the suggested model outperforms current approaches and provides a viable solution for sentence-level fake news classification in a resource-constrained environment. Experimental results on a Dravidian fake news dataset of low-resource languages demonstrate the efficacy of our approach in detecting fake news with an average accuracy of 93.31 percent in multilingual transfer learning. •In four Dravidian languages: Telugu, Tamil, Kannada, and Malayalam, we propose a new dataset for detecting fake news.•Dravidian_Fake: This is the first Dravidian languages dataset for detecting fake news. This dataset consists of around 26,000 news articles in four Dravidian languages.•For fine-tuning the pretrained transformer model we used a novel adaptive learning method.