Summary of Gpt Assisted Annotation Of Rhetorical and Linguistic Features For Interpretable Propaganda Technique Detection in News Text, by Kyle Hamilton et al.
GPT Assisted Annotation of Rhetorical and Linguistic Features for Interpretable Propaganda Technique Detection in News Text
by Kyle Hamilton, Luca Longo, Bojan Bozic
First submitted to arxiv on: 16 Jul 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI)
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 The proposed study addresses the limitation of current machine learning approaches for detecting propaganda techniques by developing an interpretable model that utilizes a set of codified rhetorical and linguistic features. These features, identified in literature related to persuasion, are used to annotate an existing dataset labeled with propaganda techniques. To facilitate efficient human annotation, RhetAnn, a web application, was designed to minimize the mental effort required. A small annotated dataset is then used to fine-tune GPT-3.5, a generative large language model (LLM), which is optimized for financial cost and classification accuracy. The study demonstrates that combining human-annotated examples with GPT can be an effective strategy for scaling annotation at a fraction of the traditional cost. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The research proposes a new approach to detect propaganda techniques in text using machine learning. By creating a set of features that can be used to annotate texts, the model becomes more interpretable and easier to understand. This study also develops a web application called RhetAnn to help humans annotate natural language sentences with these features. The results show that combining human-annotated examples with GPT can be an effective way to scale annotation while reducing costs. |
Keywords
» Artificial intelligence » Classification » Gpt » Large language model » Machine learning
