NLP‐Based Approach to Multilingual Fake News Detection through Social Media in Low‐Resource Languages: A Review

Manuscript submitted October 17, 2025; accepted January 30, 2026; published April 28, 2026

Abstract—Especially in multilingual and impoverished language situations, the quick proliferation of false news on social media jeopardizes social stability. Emphasizing difficulties specific to low-resource environments, this paper offers a thorough examination of current Natural Language Processing (NLP) techniques for fake news detection across several languages. It examines prominent techniques, including named entity recognition, sentiment analysis, and text categorization, highlighting their uses, advantages, and drawbacks. Particularly focused on advanced methods like transfer learning, multilingual embeddings, and cross-lingual models all of which attempt to get around the scarcity of labeled data and the complexity of linguistic variety. The article also draws attention to deficiencies in present techniques and stresses the need for flexible models able to handle developing disinformation problems. The research provides ideas to help in the creation of strong, inclusive, and efficient tools for reducing the world-wide spread of false information by combining present progress with gaps.

keywords—fake news detection, low-resource languages, multilingual Natural Language Processing (NLP), social media misinformation

Cite: Sibgha Munir, Haris Munir,"NLP‐Based Approach to Multilingual Fake News Detection through Social Media in Low‐Resource Languages: A Review," Journal of Advances in Artificial Intelligence, vol. 4, no. 2, pp. 76-93, 2026. doi: 10.18178/JAAI.2026.4.2.76-93

Copyright © 2026 by the authors. This 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 (CC BY 4.0).