# PropaInsight: Toward Deeper Understanding of Propaganda in Terms of Techniques, Appeals, and Intent arXiv: https://arxiv.org/abs/2409.18997 ยท HTML: https://mlsanity.com/paper/2409.18997/ ## Key facts - Cited by 9 papers in the map (data through 14 Oct 2026). - Builds on 27 of its 73 references that are in the map. - First posted on arXiv 19 Sep 2024. ## Builds on (most cited first, 27 of 27) - [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023) - [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019) - [Defending Against Neural Fake News](https://mlsanity.com/paper/1905.12616/) (2019) - [MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback](https://mlsanity.com/paper/2309.10691/) (2023) - [FakeNewsNet: A Data Repository with News Content, Social Context and Spatialtemporal Information for Studying Fake News on Social Media](https://mlsanity.com/paper/1809.01286/) (2018) - [A Comprehensive Capability Analysis of GPT-3 and GPT-3.5 Series Models](https://mlsanity.com/paper/2303.10420/) (2023) - [Fine-Grained Analysis of Propaganda in News Articles](https://mlsanity.com/paper/1910.02517/) (2019) - [SemEval-2020 Task 11: Detection of Propaganda Techniques in News Articles](https://mlsanity.com/paper/2009.02696/) (2020) - [If LLM Is the Wizard, Then Code Is the Wand: A Survey on How Code Empowers Large Language Models to Serve as Intelligent Agents](https://mlsanity.com/paper/2401.00812/) (2024) - [A Survey on Computational Propaganda Detection](https://mlsanity.com/paper/2007.08024/) (2020) - [Word Embeddings Are Steers for Language Models](https://mlsanity.com/paper/2305.12798/) (2023) - [LMFlow: An Extensible Toolkit for Finetuning and Inference of Large Foundation Models](https://mlsanity.com/paper/2306.12420/) (2023) - [Persona-DB: Efficient Large Language Model Personalization for Response Prediction with Collaborative Data Refinement](https://mlsanity.com/paper/2402.11060/) (2024) - [Faking Fake News for Real Fake News Detection: Propaganda-loaded Training Data Generation](https://mlsanity.com/paper/2203.05386/) (2022) - [LeTI: Learning to Generate from Textual Interactions](https://mlsanity.com/paper/2305.10314/) (2023) - [Prta: A System to Support the Analysis of Propaganda Techniques in the News](https://mlsanity.com/paper/2005.05854/) (2020) - [Interpretable Propaganda Detection in News Articles](https://mlsanity.com/paper/2108.12802/) (2021) - [EVEDIT: Event-based Knowledge Editing with Deductive Editing Boundaries](https://mlsanity.com/paper/2402.11324/) (2024) - [Russian propaganda on social media during the 2022 invasion of Ukraine](https://mlsanity.com/paper/2211.04154/) (2022) - [Decoding the Silent Majority: Inducing Belief Augmented Social Graph with Large Language Model for Response Forecasting](https://mlsanity.com/paper/2310.13297/) (2023) - [SmartBook: AI-Assisted Situation Report Generation for Intelligence Analysts](https://mlsanity.com/paper/2303.14337/) (2023) - [Measuring the Effect of Influential Messages on Varying Personas](https://mlsanity.com/paper/2305.16470/) (2023) - [Analysing State-Backed Propaganda Websites: a New Dataset and Linguistic Study](https://mlsanity.com/paper/2310.14032/) (2023) - [Large Language Models are Few-Shot Training Example Generators: A Case Study in Fallacy Recognition](https://mlsanity.com/paper/2311.09552/) (2023) - [Neural Architectures for Fine-Grained Propaganda Detection in News](https://mlsanity.com/paper/1909.06162/) (2019) - [Characterizing networks of propaganda on Twitter: a case study](https://mlsanity.com/paper/2005.10004/) (2020) - [A Weibo Dataset for the 2022 Russo-Ukrainian Crisis](https://mlsanity.com/paper/2203.05967/) (2022) ## Built on by (most cited first, 9 of 9) - [Must Read: A Comprehensive Survey of Computational Persuasion](https://mlsanity.com/paper/2505.07775/) (2025) - [CALM: Unleashing the Cross-Lingual Self-Aligning Ability of Language Model Question Answering](https://mlsanity.com/paper/2501.18457/) (2025) - [TRIDENT: Benchmarking LLM Safety in Finance, Medicine, and Law](https://mlsanity.com/paper/2507.21134/) (2025) - [A Review of Incorporating Psychological Theories in LLMs](https://mlsanity.com/paper/2505.00003/) (2025) - [ToxiLab: How Well Do Open-Source LLMs Generate Synthetic Toxicity Data?](https://mlsanity.com/paper/2411.15175/) (2024) - [IntentGrasp: A Comprehensive Benchmark for Intent Understanding](https://mlsanity.com/paper/2605.06832/) (2026) - [SURE: Synergistic Uncertainty-aware Reasoning for Multimodal Emotion Recognition in Conversations](https://mlsanity.com/paper/2604.01916/) (2026) - [LLMs Should Incorporate Explicit Mechanisms for Human Empathy](https://mlsanity.com/paper/2604.10557/) (2026) - [Fine-tuning with Hierarchical Prompting for Robust Propaganda Classification Across Annotation Schemas](https://mlsanity.com/paper/2605.13663/) (2026) ## Abstract (arXiv) 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.