Towards a news authenticity predictor (NAP AI)

The rapid spread of misinformation on social media has emerged as a major societal issue. Over 40% of British social media news-sharers admitted they had shared inaccurate or fake news. The extensive distribution of false information causes public trust deterioration while modifying public opinions and potentially destabilizing social and political systems. There are profound challenges due to this hard-to-detect, hard-to-stop reality and the financials and societal implications are remarkable. As an attempt to limit the challenges created from misinformation this paper introduces some preliminary work on detection of fake news and verification of their reliability based on online content. Large language models (LLMs) are being used along with natural language processing (NLP) techniques to evaluate news articles through their linguistic and contextual characteristics. Several models are compared on how they can typically identify typical indicators of misinformation through the analysis of extensive verified datasets to develop an ability to classify content as authentic or fabricated. This work has been through thorough testing to determine its operational effectiveness and dependability after completion. We present a relatively easy-to-use tool which enables a wide range of people also for those without a background in computer science to easily verify news accuracy before sharing or trusting it. This work could help to stop false information from spreading while promoting fact-based discussions and improving digital literacy skills. The research demonstrates how technology fights the fake news crisis to create an informed digital environment which supports public conversation protection and information integrity in the modern digital age.

© 2026 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license.