IndiTag: An Online Media Bias Analysis System Using Fine-Grained Bias Indicators
Luyang Lin, Lingzhi Wang, Jinsong Guo, Jing Li, Kam-Fai Wong
TL;DR
IndiTag addresses the need for accessible, timely bias analysis in online media by combining an offline, LLM-driven bias-indicator vector database with an online, explainable analysis interface. It introduces fine-grained bias indicators and a strict clustering refinement to improve robustness, and supports descriptor–text mapping for sentence-level interpretability. Evaluations across four diverse political-bias datasets show IndiTag generalizes without fine-tuning and outperforms or matches strong baselines, with ablations highlighting the contributions of clustering and the indicator framework. The system facilitates media literacy and accountability through visualizations, notes, and downloadable results, and is released as an open-source online tool for end users.
Abstract
In the age of information overload and polarized discourse, understanding media bias has become imperative for informed decision-making and fostering a balanced public discourse. However, without the experts' analysis, it is hard for the readers to distinguish bias from the news articles. This paper presents IndiTag, an innovative online media bias analysis system that leverages fine-grained bias indicators to dissect and distinguish bias in digital content. IndiTag offers a novel approach by incorporating large language models, bias indicators, and vector database to detect and interpret bias automatically. Complemented by a user-friendly interface facilitating automated bias analysis for readers, IndiTag offers a comprehensive platform for in-depth bias examination. We demonstrate the efficacy and versatility of IndiTag through experiments on four datasets encompassing news articles from diverse platforms. Furthermore, we discuss potential applications of IndiTag in fostering media literacy, facilitating fact-checking initiatives, and enhancing the transparency and accountability of digital media platforms. IndiTag stands as a valuable tool in the pursuit of fostering a more informed, discerning, and inclusive public discourse in the digital age. We release an online system for end users and the source code is available at https://github.com/lylin0/IndiTag.