Summary of Mental Disorder Classification Via Temporal Representation Of Text, by Raja Kumar et al.
Mental Disorder Classification via Temporal Representation of Text
by Raja Kumar, Kishan Maharaj, Ashita Saxena, Pushpak Bhattacharyya
First submitted to arxiv on: 15 Jun 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI); Social and Information Networks (cs.SI)
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 A novel framework is proposed to improve mental disorder prediction from social media posts using language models. The current approach splits long sequences into chunks, losing inter-post dependencies and time variant information. This paper addresses these limitations by compressing sequences into a series of numbers for temporal representation. The framework outperforms the state-of-the-art in three mental conditions (depression, self-harm, and anorexia) with a 5% absolute improvement in F1 score. Empirical results highlight the importance of temporal properties in textual data and demonstrate the possibility of inter-domain data usage. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Mental health professionals are scarce globally, making it crucial to develop new approaches for mental disorder prediction. Researchers have tried using language models to predict mental disorders from social media posts but this approach has limitations. The current method breaks down long sequences into shorter pieces, losing important information about how the posts relate to each other and how they change over time. This paper presents a new way of representing these sequences that takes into account their temporal properties. The results show that this approach is better at predicting mental disorders than previous methods. |
Keywords
» Artificial intelligence » F1 score
