Research Article

Modeling Co-Existing Mental Health Risks in Social Media via Multi-Label Learning and LLM

Volume: 13 Number: 3 September 7, 2026
EN TR

Modeling Co-Existing Mental Health Risks in Social Media via Multi-Label Learning and LLM

Abstract

Mental health risk detection from user-generated social media text has become increasingly important as psychiatric conditions such as depression, anxiety, and suicidal ideation continue to rise. However, most existing computational studies operationalize the problem using single-label datasets, implicitly assuming mutually exclusive conditions and thereby under-modeling clinically prevalent comorbidity. To better align modeling assumptions with real-world mental health phenomena, we formulate social-media-based risk identification as a multi-label text classification problem, enabling the simultaneous prediction of co-existing risks within a single post. We construct a hybrid corpus by integrating AIMH/SWMH and the Sentiment Analysis for Mental Health dataset, and by adding neutral/positive samples from Sentiment140 to strengthen healthy-content representation. Multi-label annotations are generated via Meta Llama-3-70B-Instruct using deterministic zero-shot prompting (temperature=0); a manual audit of 1,000 randomly sampled instances yields 94% agreement with the LLM-generated labels. We then benchmark multiple transformer-based encoders under a unified multi-label training protocol and report macro/micro F1 performance, highlighting the feasibility of transformer-based multi-label learning for modeling overlapping mental health risks at scale in social media.

Keywords

References

  1. [1] World Health Organization, "Mental Health Atlas 2024", World Health Organization, Geneva, (2025).
  2. [2] Canbay P., "Predicting discriminative personality profile of haters from digital texts", Knowledge-Based Systems, 2024, 287: 111460.
  3. [3] Zhang T., Schoene A.M., Ji S., Ananiadou S., "Natural language processing applied to mental illness detection: A narrative review", NPJ Digital Medicine, 2022, 5(1): 46.
  4. [4] Montejo-Raez A., Molina-Gonzalez M.D., Jimenez-Zafra S.M., Garcia-Cumbreras M.A., Garcia-Lopez L.J., "A survey on detecting mental disorders with natural language processing: Literature review, trends and challenges", Computer Science Review, 2024, 53: 100654.
  5. [5] Platona R.I., Căiţă G.A., Voiţă-Mekeres F., Peia A.O., Enătescu R.V., "The impact of psychiatric comorbidities associated with depression: A literature review", Medicine and Pharmacy Reports, 2024, 97(2): 143.
  6. [6] Ji S., Li X., Huang Z., Cambria E., "Suicidal ideation and mental disorder detection with attentive relation networks", Neural Computing and Applications, 2021, 34(13): 10309-10319.
  7. [7] Ezerceli Ö., Dehkharghani R., "Mental disorder and suicidal ideation detection from social media using deep neural networks", Journal of Computational Social Science, 2024, 7(3): 2277-2307.
  8. [8] Go A., Bhayani R., Huang L., "Twitter sentiment classification using distant supervision", CS224N Project Report, Stanford University, 2009, 1: 1-12.

Details

Primary Language

English

Subjects

Engineering Design

Journal Section

Research Article

Publication Date

September 7, 2026

Submission Date

February 10, 2026

Acceptance Date

April 14, 2026

Published in Issue

Year 2026 Volume: 13 Number: 3

APA
Özer, Z., Kenger, E., Gözükara, G., & Canbay, P. (2026). Modeling Co-Existing Mental Health Risks in Social Media via Multi-Label Learning and LLM. El-Cezeri, 13(3), 383-392. https://doi.org/10.31202/ecjse.1885302
AMA
1.Özer Z, Kenger E, Gözükara G, Canbay P. Modeling Co-Existing Mental Health Risks in Social Media via Multi-Label Learning and LLM. El-Cezeri Journal of Science and Engineering. 2026;13(3):383-392. doi:10.31202/ecjse.1885302
Chicago
Özer, Zehra, Emre Kenger, Görkem Gözükara, and Pelin Canbay. 2026. “Modeling Co-Existing Mental Health Risks in Social Media via Multi-Label Learning and LLM”. El-Cezeri 13 (3): 383-92. https://doi.org/10.31202/ecjse.1885302.
EndNote
Özer Z, Kenger E, Gözükara G, Canbay P (September 1, 2026) Modeling Co-Existing Mental Health Risks in Social Media via Multi-Label Learning and LLM. El-Cezeri 13 3 383–392.
IEEE
[1]Z. Özer, E. Kenger, G. Gözükara, and P. Canbay, “Modeling Co-Existing Mental Health Risks in Social Media via Multi-Label Learning and LLM”, El-Cezeri Journal of Science and Engineering, vol. 13, no. 3, pp. 383–392, Sept. 2026, doi: 10.31202/ecjse.1885302.
ISNAD
Özer, Zehra - Kenger, Emre - Gözükara, Görkem - Canbay, Pelin. “Modeling Co-Existing Mental Health Risks in Social Media via Multi-Label Learning and LLM”. El-Cezeri 13/3 (September 1, 2026): 383-392. https://doi.org/10.31202/ecjse.1885302.
JAMA
1.Özer Z, Kenger E, Gözükara G, Canbay P. Modeling Co-Existing Mental Health Risks in Social Media via Multi-Label Learning and LLM. El-Cezeri Journal of Science and Engineering. 2026;13:383–392.
MLA
Özer, Zehra, et al. “Modeling Co-Existing Mental Health Risks in Social Media via Multi-Label Learning and LLM”. El-Cezeri, vol. 13, no. 3, Sept. 2026, pp. 383-92, doi:10.31202/ecjse.1885302.
Vancouver
1.Zehra Özer, Emre Kenger, Görkem Gözükara, Pelin Canbay. Modeling Co-Existing Mental Health Risks in Social Media via Multi-Label Learning and LLM. El-Cezeri Journal of Science and Engineering. 2026 Sep. 1;13(3):383-92. doi:10.31202/ecjse.1885302
Creative Commons License El-Cezeri is licensed to the public under a Creative Commons Attribution 4.0 license.
88x31.png