TROPIC - Trustworthiness Rating of Online Publishers through online Interactions Calculation
Manuel Pratelli, Fabio Saracco, Marinella Petrocchi
TL;DR
The paper addresses the high cost and limited coverage of traditional trustworthiness ratings for online news publishers. It introduces TROPIC, a tool that infers publisher trustworthiness from social media interactions by analyzing online discussions, leveraging a base-knowledge, News Engagement Communities (NECs), and users' propensity to share low-quality information. It includes an interactive UI to guide annotation and a backend that computes scores with confidence, enabling targeted expansion of the knowledge base. The implementation is containerized (Angular/FastAPI/Docker) with a demo version, and relies on NEC extraction via the bicm library to scale trust assessments to previously unlabelled publishers.
Abstract
Existing methods for assessing the trustworthiness of news publishers face high costs and scalability issues. The tool presented in this paper supports the efforts of specialized organizations by providing a solution that, starting from an online discussion, provides (i) trustworthiness ratings for previously unclassified news publishers and (ii) an interactive platform to guide annotation efforts and improve the robustness of the ratings. The system implements a novel framework for assessing the trustworthiness of online news publishers based on user interactions on social media platforms.