Summary of Evaluating Large Language Models For Anxiety and Depression Classification Using Counseling and Psychotherapy Transcripts, by Junwei Sun et al.
Evaluating Large Language Models for Anxiety and Depression Classification using Counseling and Psychotherapy Transcripts
by Junwei Sun, Siqi Ma, Yiran Fan, Peter Washington
First submitted to arxiv on: 18 Jul 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Computers and Society (cs.CY); Emerging Technologies (cs.ET); 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 The paper evaluates the effectiveness of various machine learning approaches in classifying anxiety and depression from long conversational transcripts. The authors fine-tune established transformer models like BERT, RoBERTa, and Longformer as well as more recent large language models like Mistral-7B. They also compare these methods to traditional support vector machines with feature engineering and GPT models through prompting. Despite the state-of-the-art models’ reputation for excellence, the study finds that they do not significantly improve classification outcomes compared to traditional machine learning approaches. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper looks at how good different computer programs are at telling apart anxiety and depression from long talks. The authors try out many types of AI models on this task. They find that even the best AI models don’t really help with classifying these emotions any better than old-fashioned ways of doing it. |
Keywords
» Artificial intelligence » Bert » Classification » Feature engineering » Gpt » Machine learning » Prompting » Transformer
