Summary of A Benchmark For Cross-domain Argumentative Stance Classification on Social Media, by Jiaqing Yuan et al.
A Benchmark for Cross-Domain Argumentative Stance Classification on Social Media
by Jiaqing Yuan, Ruijie Xi, Munindar P. Singh
First submitted to arxiv on: 11 Oct 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 approach addresses challenges in argumentative stance classification by leveraging platform rules, expert-curated content, and large language models to generate a multidomain benchmark. The method produces 4,498 topical claims and 30,961 arguments across 21 domains from three sources. It is evaluated in fully supervised, zero-shot, and few-shot settings, highlighting strengths and limitations of different methodologies. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps us better understand how people argue about certain topics. Currently, it’s hard to find examples of arguments from many different areas, like politics or science. To fix this, the researchers came up with a new way to create a big collection of argumentative sentences that covers many subjects. They used rules and guidelines from online platforms, expert-approved content, and special computer models to generate these sentences without needing human help. The resulting dataset is tested in different ways, showing what works well and what doesn’t. |
Keywords
» Artificial intelligence » Classification » Few shot » Supervised » Zero shot
