Summary of Diverse: a Dataset Of Youtube Video Comment Stances with a Data Programming Model, by Iain J. Cruickshank et al.
DIVERSE: A Dataset of YouTube Video Comment Stances with a Data Programming Model
by Iain J. Cruickshank, Amir Soofi, Lynnette Hui Xian Ng
First submitted to arxiv on: 5 Mar 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 This paper addresses the dearth of data on public opinions toward online military recruitment by introducing the DIVERSE dataset, comprising all comments from the U.S. Army’s official YouTube Channel videos. A state-of-the-art weak supervision approach is employed to label the stance of each comment using large language models. The findings show that the U.S. Army’s videos attracted a significant number of comments post-2021, with the stance distribution balanced among supportive, oppositional, and neutral comments, leaning slightly toward oppositional versus supportive ones. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper is about understanding what people think when they see military recruitment online. It’s hard to know how people feel because there isn’t much data on it. To solve this problem, researchers created a special dataset called DIVERSE that has all the comments from the U.S. Army’s YouTube videos. They used powerful computer models to figure out what each comment was saying about the video and the U.S. Army. The results show that people have been talking more about the U.S. Army on YouTube since 2021, and most of those comments are neutral or negative. |
