Modeling Multi-level Context for Informational Bias Detection by Contrastive Learning and Sentential Graph Network

TL;DR

This paper presents MultiCTX, a novel model that integrates multi-level context using contrastive learning and graph networks to improve sentence-level informational bias detection in news articles.

Contribution

It introduces a multi-level context modeling approach combining contrastive learning and sentence graphs, advancing bias detection accuracy over existing methods.

Findings

MultiCTX significantly outperforms state-of-the-art models.

Contrastive learning and sentence graphs effectively incorporate context.

The model improves bias detection in news articles.

Abstract

Informational bias is widely present in news articles. It refers to providing one-sided, selective or suggestive information of specific aspects of certain entity to guide a specific interpretation, thereby biasing the reader's opinion. Sentence-level informational bias detection is a very challenging task in a way that such bias can only be revealed together with the context, examples include collecting information from various sources or analyzing the entire article in combination with the background. In this paper, we integrate three levels of context to detect the sentence-level informational bias in English news articles: adjacent sentences, whole article, and articles from other news outlets describing the same event. Our model, MultiCTX (Multi-level ConTeXt), uses contrastive learning and sentence graphs together with Graph Attention Network (GAT) to encode these three degrees of context at different stages by tactically composing contrastive triplets and constructing sentence graphs within events. Our experiments proved that contrastive learning together with sentence graphs effectively incorporates context in varying degrees and significantly outperforms the current SOTA model sentence-wise in informational bias detection.