Summary of Depression Detection on Social Media with Large Language Models, by Xiaochong Lan et al.
Depression Detection on Social Media with Large Language Models
by Xiaochong Lan, Yiming Cheng, Li Sheng, Chen Gao, Yong Li
First submitted to arxiv on: 16 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 The proposed DORIS system aims to detect depression through analyzing social media posts, addressing two key challenges: requiring medical knowledge and achieving both high accuracy and explainability. The system combines large language models (LLMs) with medical knowledge, annotating high-risk texts for diagnostic criteria and retrieving texts with emotional intensity and summarizing critical information from mood records. To address the second challenge, LLMs are combined with traditional classifiers to integrate medical knowledge-guided features and provide explanation results. Experimental results show that DORIS outperforms the current best baseline by 0.036 in AUPRC. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary DORIS is a new way to detect depression on social media. Right now, many people don’t get the help they need because they’re afraid of being judged or don’t know how to ask for help. The goal is to use special language models to look at social media posts and figure out if someone might be depressed. This requires understanding medical knowledge and getting accurate results. The system also needs to explain why it thinks someone is depressed, so doctors can understand the reasoning. After testing on real datasets, DORIS performed better than the current best method. |
