PUB
  • Home
  • Sources
  • Search
  • About

Depression Detection with Novel Large Language Model Methods

Alan Lu, Phillip Koehn
International Journal of Computer Science and Information Technology, (2024), Vol.4, No.1, pp.262-269
Published: September 13, 2024
DOI: 10.62051/ijcsit.v4n1.32
PDF: Download Full Text PDF
Abstract

Recent advancements in machine learning and natural language processing have shown significant potential in aiding mental health diagnostics. In this paper, we specifically provide novel approaches to depression identification using large language models (LLMs). First, we employ the LLM2Vec architecture for text-only classification. Additionally, we explore the potential of multimodal LLMs by incorporating text, audio, and visual inputs, aiming to enhance diagnostic accuracy through a more comprehensive analysis of multimodal data. Our results demonstrate that text-only models perform well above baseline performances, while multimodal data shows promise for achieving a more nuanced understanding of a patient’s mental state. This work lays the groundwork for future research in developing more robust and effective tools for mental health assessment using LLMs.

Keywords: Machine Learning, Multimodal analysis, Large Language Models, Depression Detection
APA Citation: Alan Lu, Phillip Koehn (2024). Depression Detection with Novel Large Language Model Methods. International Journal of Computer Science and Information Technology, 4(1), 262-269. https://doi.org/10.62051/ijcsit.v4n1.32

References

  1. National Institute of Mental Health. “Mental Illness.” National Institute of Mental Health, U.S. Department of Health and Human Services, 2023, https://www.nimh.nih.gov/health/statistics/ mental-illness. Accessed 4 Aug. 2024.
  2. Depression and Bipolar Support Alliance. “Depression Statistics.” Depression and Bipolar Support Alliance, 2024, www.dbsalliance.org/education/depression/statistics. Accessed 4 Aug. 2024.
  3. National Institute of Mental Health. “Suicide.” National Institute of Mental Health, U.S. Department of Health and Human Services, 2024, https://www.nimh.nih.gov/health/statistics/suicide. Accessed 4 Aug. 2024.
  4. Depression and Bipolar Support Alliance. “Suicide Statistics.” Depression and Bipolar Support Alliance, https://www.dbsalliance.org/crisis/suicide-prevention-information/suicide-statistics. Accessed 4 Aug. 2024.
  5. Thornicroft, Graham, et al. “Undertreatment of People with Major Depressive Disorder in 21 Countries.” The British Journal of Psychiatry, vol. 210, no. 2, 2017, pp. 119-124. PubMed, https: //pubmed.ncbi.nlm.nih.gov/27908899. Accessed 6 Aug. 2024.
  6. Islam, Md. Rafiqul, et al. “Depression Detection from Social Network Data Using Machine Learning Techniques.” 2018, https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6111060/. Accessed 7 Aug. 2024.
  7. Kim, Jina, et al. “A Deep Learning Model for Detecting Mental Illness from User Content on Social
  8. Media.” Scientific Reports, vol. 10, no. 11846, 2020, https://www.ncbi.nlm.nih.gov/pmc/articles/ PMC7367301/. Accessed 7 Aug. 2024.
  9. AlSagri, Hatoon, and Mourad Ykhlef. “Machine Learning-Based Approach for Depression Detection in Twitter Using Content and Activity Features.” arXiv, 2020, arxiv.org/pdf/2003.04763. Accessed 12 Aug. 2024.
  10. Reece, Andrew G., and Christopher M. Danforth. “Instagram Photos Reveal Predictive Markers of Depression.” EPJ Data Science, vol. 6, no. 1, 2017, article 15, https://epjdatascience.springeropen. com/articles/10.1140/epjds/s13688-017-0110-z. Accessed 12 Aug. 2024.
  11. Lan, Xiaochong, et al. “Depression Detection on Social Media with Large Language Models.” arXiv, 2024, https://arxiv.org/html/2403.10750v1. Accessed 12 Aug. 2024.
  12. Hadzic, Besim, et al. “Enhancing Early Depression Detection with AI: A Comparative Use of NLP Models.” SICE Journal of Control, Measurement, and System Integration, vol. 17, no. 1, 2024, pp. 135–143, https://www.tandfonline.com/doi/full/10.1080/18824889.2024.2342624. Accessed 14 Aug. 2024.
  13. Baltruˇsaitis, Tadas, et al. “OpenFace: an open source facial behavior analysis toolkit.” Proceedings of the Winter Conference on Applications of Computer Vision. 2016, https://www.cl.cam.ac.uk/research/rainbow/projects/openface/wacv2016.pdf. Accessed 14 Aug. 2024.
  14. BehnamGhader, Parishad, et al. “LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders.” arXiv, 2024, https://arxiv.org/html/2404.05961v1. Accessed 15 Aug. 2024.
© 2026 PUB · Seek truth with rigour