Summary of Hierarchical Multi-label Classification Of Online Vaccine Concerns, by Chloe Qinyu Zhu et al.
Hierarchical Multi-Label Classification of Online Vaccine Concerns
by Chloe Qinyu Zhu, Rickard Stureborg, Bhuwan Dhingra
First submitted to arxiv on: 1 Feb 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
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 research paper explores the task of detecting vaccine concerns in online discourse using large language models (LLMs) in a zero-shot setting without the need for expensive training datasets. The study aims to identify longitudinal trends in vaccine concerns and misinformation, which can inform public health efforts and resource allocation. By analyzing different prompting strategies, the researchers found that classifying concerns over multiple passes through the LLM achieved the best results. Specifically, using GPT-4 and a boolean question approach led to an overall F1 score of 78.7%, outperforming crowdworker accuracy and expert annotations on the VaxConcerns dataset. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This research helps us understand how people are talking about vaccines online and what they’re worried about. The scientists used special computer models to look at lots of text and figure out when someone is expressing a concern about a vaccine. They found that if you ask these models questions multiple times, it works really well! This can help health professionals keep track of what’s going on and make sure people have the right information. |
Keywords
* Artificial intelligence * Discourse * F1 score * Gpt * Prompting * Zero shot
