DocNet: Semantic Structure in Inductive Bias Detection Models

TL;DR

DocNet is a low-resource, inductive document embedding model that detects political bias by analyzing semantic structures in news articles, achieving comparable performance to resource-intensive models.

Contribution

It introduces DocNet, a novel semantic structure-based bias detection model that operates without pre-trained language models, suitable for low-resource settings.

Findings

Semantic structures of opposing political news are significantly similar.

DocNet achieves comparable bias detection performance to pre-trained models.

The model reduces resource dependency in bias detection tasks.

Abstract

News will be biased so long as people have opinions. As social media becomes the primary entry point for news and partisan differences increase, it is increasingly important for informed citizens to be able to recognize bias. If people are aware of the biases of the news they consume, they will be able to take action to avoid polarizing echo chambers. In this paper, we explore an often overlooked aspect of bias detection in media: the semantic structure of news articles. We present DocNet, a novel, inductive, and low-resource document embedding and political bias detection model. We also demonstrate that the semantic structure of news articles from opposing political sides, as represented in document-level graph embeddings, have significant similarities. DocNet bypasses the need for pre-trained language models, reducing resource dependency while achieving comparable performance. It can be used to advance political bias detection in low-resource environments. Our code and data are made available at: https://anonymous.4open.science/r/DocNet/