Depress-HybridNet: A Linguistic-Behavioral Hybrid Framework for Early and Accurate Depression Detection on Social Media
DOI:
https://doi.org/10.62411/faith.3048-3719-266Keywords:
BERT, Computational Psychiatry, Deep Learning Processing, Depression Detection, Ethical AI, Hybrid ModelAbstract
Depression remains one of the most serious mental health challenges worldwide and is often underdiagnosed due to social stigma and limited access to medical services. With the proliferation of social media as a medium for self-expression, these platforms provide new opportunities for early detection of depressive symptoms through digital footprints. However, most prior research has primarily focused on linguistic features derived from text, overlooking behavioral dynamics that also reflect psychological states. To address this gap, we propose Depress-HybridNet, a hybrid deep learning framework that integrates linguistic embeddings with behavioral activity patterns. The architecture combines a BERT-BiLSTM encoder for linguistic feature extraction, a multi-layer perceptron for behavioral feature encoding, and an adaptive attention-based fusion mechanism to integrate multimodal signals optimally. Experiments conducted on the publicly available Kaggle Depression Dataset demonstrate that Depress-HybridNet consistently outperforms strong baselines, including fine-tuned BERT, achieving state-of-the-art results (F1 = 0.92, AUC = 0.93). A further ablation study highlights the critical role of behavioral features and the attention fusion layer in improving performance. In addition, clinical validation by licensed psychologists confirmed a high degree of consistency between the model’s predictions and expert judgment, underscoring its real-world applicability. These findings underscore the importance of modelling depression as a multifaceted phenomenon, rather than a purely linguistic task, and establish a reproducible benchmark for future research.
Downloads
References
World Health Organization, “Depressive disorder (depression),” who.int, 2023. https://www.who.int/news-room/fact-sheets/detail/depressive-disorder-(depression)%0A
M. Sadeghi et al., “Harnessing multimodal approaches for depression detection using large language models and facial expressions,” npj Ment. Heal. Res., vol. 3, no. 1, p. 66, Dec. 2024, doi: 10.1038/s44184-024-00112-8.
O. Ahmed, E. I. Walsh, A. Dawel, K. Alateeq, D. A. Espinoza Oyarce, and N. Cherbuin, “Social media use, mental health and sleep: A systematic review with meta-analyses,” J. Affect. Disord., vol. 367, pp. 701–712, Dec. 2024, doi: 10.1016/j.jad.2024.08.193.
F. Alhamed, J. Ive, and L. Specia, “Classifying Social Media Users before and after Depression Diagnosis via Their Language Usage: A Dataset and Study,” in Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), 2024, pp. 3250–3260. [Online]. Available: https://aclanthology.org/2024.lrec-main.289.pdf
W. Marx et al., “Clinical guidelines for the use of lifestyle-based mental health care in major depressive disorder: World Federation of Societies for Biological Psychiatry (WFSBP) and Australasian Society of Lifestyle Medicine (ASLM) taskforce,” World J. Biol. Psychiatry, vol. 24, no. 5, pp. 333–386, May 2023, doi: 10.1080/15622975.2022.2112074.
Johns Hopkins Children’s Center, “Johns Hopkins Children’s Center Study Shows More Than Just Social Media Use May Be Causing Depression in Young Adults,” hopkinsmedicine.org, 2024. https://www.hopkinsmedicine.org/news/newsroom/news-releases/2024/05/johns-hopkins-childrens-center-study-shows-more-than-just-social-media-use-may-be-causing-depression-in-young-adults
F. Karim, A. Oyewande, L. F. Abdalla, R. Chaudhry Ehsanullah, and S. Khan, “Social Media Use and Its Connection to Mental Health: A Systematic Review,” Cureus, Jun. 2020, doi: 10.7759/cureus.8627.
L. S. Khoo, M. K. Lim, C. Y. Chong, and R. McNaney, “Machine Learning for Multimodal Mental Health Detection: A Systematic Review of Passive Sensing Approaches,” Sensors, vol. 24, no. 2, p. 348, Jan. 2024, doi: 10.3390/s24020348.
M. K. Jagadeesh et al., “Optical Spectroscopy of Classical Be Stars in Old Open Clusters,” arXiv. Mar. 15, 2024. [Online]. Available: http://arxiv.org/abs/2403.10660
T. Pedersen, “Screening Twitter Users for Depression and PTSD with Lexical Decision Lists,” in Proceedings of the 2nd Workshop on Computational Linguistics and Clinical Psychology: From Linguistic Signal to Clinical Reality, 2015, pp. 46–53. doi: 10.3115/v1/W15-1206.
S. Chancellor and M. De Choudhury, “Methods in predictive techniques for mental health status on social media: a critical review,” npj Digit. Med., vol. 3, no. 1, p. 43, Mar. 2020, doi: 10.1038/s41746-020-0233-7.
M. M. Aldarwish and H. F. Ahmad, “Predicting Depression Levels Using Social Media Posts,” in 2017 IEEE 13th International Symposium on Autonomous Decentralized System (ISADS), Mar. 2017, pp. 277–280. doi: 10.1109/ISADS.2017.41.
S. Ghosh and T. Anwar, “Depression Intensity Estimation via Social Media: A Deep Learning Approach,” IEEE Trans. Comput. Soc. Syst., vol. 8, no. 6, pp. 1465–1474, Dec. 2021, doi: 10.1109/TCSS.2021.3084154.
M. O’Reilly, “Social media and adolescent mental health: the good, the bad and the ugly,” J. Ment. Heal., vol. 29, no. 2, pp. 200–206, Mar. 2020, doi: 10.1080/09638237.2020.1714007.
R. Plackett, J. Sheringham, and J. Dykxhoorn, “The Longitudinal Impact of Social Media Use on UK Adolescents’ Mental Health: Longitudinal Observational Study,” J. Med. Internet Res., vol. 25, p. e43213, Mar. 2023, doi: 10.2196/43213.
M. De Choudhury, M. Gamon, S. Counts, and E. Horvitz, “Predicting Depression via Social Media,” Proc. Int. AAAI Conf. Web Soc. Media, vol. 7, no. 1, pp. 128–137, Aug. 2021, doi: 10.1609/icwsm.v7i1.14432.
C.-Y. Poon et al., “Directional associations among real-time activity, sleep, mood, and daytime symptoms in major depressive disorder using actigraphy and ecological momentary assessment,” Behav. Res. Ther., vol. 173, p. 104464, Feb. 2024, doi: 10.1016/j.brat.2023.104464.
A. Malhotra and R. Jindal, “Multimodal Deep Learning based Framework for Detecting Depression and Suicidal Behaviour by Affective Analysis of Social Media Posts,” EAI Endorsed Trans. Pervasive Heal. Technol., vol. 6, no. 21, p. e1, Jan. 2020, doi: 10.4108/eai.13-7-2018.164259.
A. Pathirana et al., “A Reinforcement Learning-Based Approach for Promoting Mental Health Using Multimodal Emotion Recognition,” J. Futur. Artif. Intell. Technol., vol. 1, no. 2, pp. 124–142, Sep. 2024, doi: 10.62411/faith.2024-22.
S. Chandra Guntuku, D. Preotiuc-Pietro, J. C. Eichstaedt, and L. H. Ungar, “What Twitter Profile and Posted Images Reveal about Depression and Anxiety,” Proc. Int. AAAI Conf. Web Soc. Media, vol. 13, pp. 236–246, Jul. 2019, doi: 10.1609/icwsm.v13i01.3225.
X. Xu et al., “Mental-LLM : Leveraging Large Language Models for Mental Health Prediction via Online Text Data,” Proc. ACM Interactive, Mobile, Wearable Ubiquitous Technol., vol. 8, no. 1, pp. 1–32, Mar. 2024, doi: 10.1145/3643540.
Z. Zhang et al., “Multimodal Sensing for Depression Risk Detection: Integrating Audio, Video, and Text Data,” Sensors, vol. 24, no. 12, p. 3714, Jun. 2024, doi: 10.3390/s24123714.
S. W. Kelley and C. M. Gillan, “Using language in social media posts to study the network dynamics of depression longitudinally,” Nat. Commun., vol. 13, no. 1, p. 870, Feb. 2022, doi: 10.1038/s41467-022-28513-3.
S. Steinsbekk, J. Nesi, and L. Wichstrøm, “Social media behaviors and symptoms of anxiety and depression. A four-wave cohort study from age 10–16 years.,” Comput. Human Behav., vol. 147, p. 107859, Oct. 2023, doi: 10.1016/j.chb.2023.107859.
D.-E. Lițan, “Mental health in the ‘era’ of artificial intelligence: technostress and the perceived impact on anxiety and depressive disorders—an SEM analysis,” Front. Psychol., vol. 16, Jun. 2025, doi: 10.3389/fpsyg.2025.1600013.
S. J. Masoumi and B. Farhadi, “Applications and efficacy of artificial intelligence in depression: A narrative review,” J. Nurs. Reports Clin. Pract., vol. 3, no. 6, pp. 574–581, Nov. 2025, doi: 10.32598/JNRCP.2502.1229.
R. Dehbozorgi et al., “The application of artificial intelligence in the field of mental health: a systematic review,” BMC Psychiatry, vol. 25, no. 1, p. 132, Feb. 2025, doi: 10.1186/s12888-025-06483-2.
D. Benrimoh et al., “Development of the treatment prediction model in the artificial intelligence in depression – medication enhancement study,” npj Ment. Heal. Res., vol. 4, no. 1, p. 26, Jun. 2025, doi: 10.1038/s44184-025-00136-8.
C. Lin et al., “SenseMood: Depression Detection on Social Media,” in Proceedings of the 2020 International Conference on Multimedia Retrieval, Jun. 2020, pp. 407–411. doi: 10.1145/3372278.3391932.
Möbius, “The Depression Dataset,” Kaggle, 2021. https://www.kaggle.com/datasets/arashnic/the-depression-dataset
I. Trulson et al., “Cell-Free DNA in Plasma and Serum Indicates Disease Severity and Prognosis in Blunt Trauma Patients,” Diagnostics, vol. 13, no. 6, p. 1150, Mar. 2023, doi: 10.3390/diagnostics13061150.
H. Islam, S. Das, T. Ali, T. Bose, O. Prakash, and P. Kumar, “A Frequency Reconfigurable MIMO Antenna with Bandstop Filter Decoupling Network for Cognitive Communication,” Sensors, vol. 22, no. 18, p. 6937, Sep. 2022, doi: 10.3390/s22186937.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Johnson Bisi Oluwagbemi, Ayobami Emmanuel Mesioye, Racheal Shade Akinbo
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
