FishBiasLens: Integrating Large Language Models and Visual Analytics for Bias Detection
Dany Mauro Diaz Espino - Fundação Getulio Vargas, Rio de Janeiro, Brazil. Fundação Getulio Vargas, Rio de Janeiro, Brazil
Felipe Moreno-Vera - FGV, Rio de Janeiro, Brazil. FGV, Rio de Janeiro, Brazil
Juanpablo Andrew Heredia - Getulio Vargas Foundation, Rio de Janeiro, Brazil. Getulio Vargas Foundation, Rio de Janeiro, Brazil
Fabrício Venturim - Getulio Vargas Foundation, Rio de Janeiro, Brazil. Getulio Vargas Foundation, Rio de Janeiro, Brazil
Jorge Poco - Getúlio Vargas Foundation, Rio de Janeiro, Brazil. Getúlio Vargas Foundation, Rio de Janeiro, Brazil
Room: Bayshore II
2024-10-13T12:30:00ZGMT-0600Change your timezone on the schedule page
2024-10-13T12:30:00Z
Abstract
Identifying unreliable sources is crucial for preventing misinformation and making informed decisions. CatchNet, the Oceanus Knowledge Graph, contains biased perspectives that threaten its credibility. We use Large Language Models (LLMs) and interactive visualization systems to identify these biases. By analyzing police reports and using GPT-3.5 to extract information from articles, we establish the ground truth for our analysis. Our visual analytics system detects anomalies, revealing unreliable news sources such as The News Buoy and biased analysts such as Harvey Janus and Junior Shurdlu.