Fine-grained Narrative Classification in Biased News Articles

TL;DR

This paper introduces INDI-PROP, a detailed dataset and novel multi-level classification methods for analyzing propaganda in Indian biased news articles, focusing on ideological bias, narrative frames, and persuasive techniques.

Contribution

It presents the first fine-grained, hierarchical dataset for propaganda analysis in Indian news media and proposes GPT-4o-mini guided reasoning frameworks for bias, narrative, and persuasive technique classification.

Findings

Significant improvement over baseline models in classification accuracy.

Effective multi-hop reasoning frameworks for hierarchical propaganda analysis.

Comprehensive dataset covering ideological bias, narratives, and persuasive techniques.

Abstract

Narratives are the cognitive and emotional scaffolds of propaganda. They organize isolated persuasive techniques into coherent stories that justify actions, attribute blame, and evoke identification with ideological camps. In this paper, we propose a novel fine-grained narrative classification in biased news articles. We also explore article-bias classification as the precursor task to narrative classification and fine-grained persuasive technique identification. We develop INDI-PROP, the first ideologically grounded fine-grained narrative dataset with multi-level annotation for analyzing propaganda in Indian news media. Our dataset INDI-PROP comprises 1,266 articles focusing on two polarizing socio-political events in recent times: CAA and the Farmers' protest. Each article is annotated at three hierarchical levels: (i) ideological article-bias (pro-government, pro-opposition, neutral), (ii) event-specific fine-grained narrative frames anchored in ideological polarity and communicative intent, and (iii) persuasive techniques. We propose FANTA and TPTC, two GPT-4o-mini guided multi-hop prompt-based reasoning frameworks for the bias, narrative, and persuasive technique classification. FANTA leverages multi-layered communicative phenomena by integrating information extraction and contextual framing for hierarchical reasoning. On the other hand, TPTC adopts systematic decomposition of persuasive cues via a two-stage approach. Our evaluation suggests substantial improvement over underlying baselines in each case.