A fact-checking tool based on Artificial Intelligence to fight disinformation on Telegram

Abstract

This article develops an automatic detection model based on natural learning by designing a useful tool for disinformation monitoring in Telegram that avoids the algorithmic bias of artificial intelligence. It is of relevance the monitoring of online platforms and messaging applications such as WhatsApp and Telegram because they have become tools for circumventing traditional verification controls, and, therefore, for conveying disinformation content. The goal of this work is to contribute with early warning mechanisms that allow early combatting of disinformation (prebunking), especially in media ecosystems prone to the dissemination of false content such as pre-election periods, wars or energy crises. The methodology used applies a systematic and structured approach that allows the design and development of the tool, as well as its subsequent evaluation and optimisation. The main result is the creation of an Artificial Intelligence model capable of detecting disinformation in Telegram, and which also allows the integration of these solutions in the information verification workflow through a friendly and easy-to-use interface, thus contributing to the field of fact-checking. The findings reveal lines of future research, including the adaptation of the tool for other platforms and the integration of new features.