Summary of Propainsight: Toward Deeper Understanding Of Propaganda in Terms Of Techniques, Appeals, and Intent, by Jiateng Liu et al.
PropaInsight: Toward Deeper Understanding of Propaganda in Terms of Techniques, Appeals, and Intent
by Jiateng Liu, Lin Ai, Zizhou Liu, Payam Karisani, Zheng Hui, May Fung, Preslav Nakov, Julia Hirschberg, Heng Ji
First submitted to arxiv on: 19 Sep 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI); Social and Information Networks (cs.SI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary A novel conceptual framework called propainsight is introduced to better understand the motives and impacts of propaganda. It systematically dissects propaganda into techniques, arousal appeals, and underlying intent, offering a more granular understanding of how it operates across different contexts. A new dataset called propagaze combines human-annotated data with synthetic data generated through a designed pipeline. Off-the-shelf language models struggle with propaganda analysis, but training with propagaze significantly improves performance. Fine-tuned Llama-7B-Chat achieves better results in technique identification and appeal analysis compared to 1-shot GPT-4-Turbo. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Propaganda is important because it can shape what people think and believe. This research creates a new way to understand propaganda by breaking it down into smaller parts like techniques, appeals, and motivations. They also create a big dataset with real and fake data mixed together that helps machines learn about propaganda better. The results show that regular language models aren’t very good at understanding propaganda, but if you train them on this special dataset, they can do much better. |
Keywords
» Artificial intelligence » 1 shot » Gpt » Llama » Synthetic data
