A Micro-interaction Tool for Online Text Analysis

Abstract

With the constant increase of new technologies and mobile device usage for content consumption, also more misinformation, fake news, and questionable content have been published in many ways and forms all over the Internet. This is undoubtedly a current problem because the public’s knowledge and the respective opinions on several global matters are being easily persuaded and distorted. The circulation of fake news and malicious content is not new, but its visibility and impact increased with the emergence of social networks and online social media. There is so much misinformation spread around, that people no longer know what to believe. The line between journalism and other content has blurred, making it important for all writers, regardless of their platform, to check their facts. Unlike the conventional verification process, which requires checking information before it is published, fact-checking is dedicated to post-hoc checking, or in other words, verifying statements and alleged facts after they have been published. Many techniques and mechanisms have been studied for fake news detection and fact-checking, most of them using the synergy between Machine Learning (ML) and Artificial Intelligence (AI) algorithms with Human sensibility, sense, and emotion. Hence, this paper presents a micro-interaction tool for online text analysis focused on malicious content reporting. The system conceptual design and architecture are also presented in detail and finally, the implementation and preliminary validation of the proposed tool are described including primary system evaluation results.

This work is funded by FCT/MCTES through national funds and when applicable co-funded EU funds under the project UIDB/EEA/50008/2020.