PropaInsight: Toward Deeper Understanding of Propaganda in Terms of Techniques, Appeals, and Intent

TL;DR

This paper introduces propainsight, a comprehensive framework for analyzing propaganda by its techniques, appeals, and intent, supported by a new dataset, propagaze, which enhances model performance and generalizability in propaganda detection.

Contribution

The paper presents a novel conceptual framework and dataset for propaganda analysis, improving understanding of motives and impacts beyond existing technique-focused approaches.

Findings

Fine-tuned Llama-7B-Chat outperforms GPT-4-Turbo in technique and appeal analysis.

Propagaze dataset significantly boosts model performance in data-sparse and cross-domain scenarios.

Training with propagaze enhances propaganda detection accuracy and generalizability.

Abstract

Propaganda plays a critical role in shaping public opinion and fueling disinformation. While existing research primarily focuses on identifying propaganda techniques, it lacks the ability to capture the broader motives and the impacts of such content. To address these challenges, we introduce propainsight, a conceptual framework grounded in foundational social science research, which systematically dissects propaganda into techniques, arousal appeals, and underlying intent. propainsight offers a more granular understanding of how propaganda operates across different contexts. Additionally, we present propagaze, a novel dataset that combines human-annotated data with high-quality synthetic data generated through a meticulously designed pipeline. Our experiments show that off-the-shelf LLMs struggle with propaganda analysis, but training with propagaze significantly improves performance. Fine-tuned Llama-7B-Chat achieves 203.4% higher text span IoU in technique identification and 66.2% higher BertScore in appeal analysis compared to 1-shot GPT-4-Turbo. Moreover, propagaze complements limited human-annotated data in data-sparse and cross-domain scenarios, showing its potential for comprehensive and generalizable propaganda analysis.