Applicability of AI in identifying early signs of depression and anxiety
through digital behaviours and language patterns in teens

Aadvitiya Gulati

doi:10.46609/IJSSER.2026.v11i09.039

Title: Applicability of AI in identifying early signs of depression and anxiety through digital behaviours and language patterns in teens
Authors: Aadvitiya Gulati
Journal: International Journal of Social Science and Economic Research (IJSSER) ISSN: 2455-8834 Volume: 11 Issue: 9 Publication Date: September 2026 DOI: 10.46609/IJSSER.2026.v11i09.039
\|\| \|\|
Aadvitiya Gulati Modern School Barakhamba Road, New Delhi
MLA 8 Gulati, Aadvitiya. "Applicability of AI in identifying early signs of depression and anxiety through digital behaviours and language patterns in teens." Int. j. of Social Science and Economic Research, vol. 11, no. 9, Sept. 2026, pp. 5116-5128, doi.org/10.46609/IJSSER.2026.v11i09.039. Accessed Sept. 2026. APA 6 Gulati, A. (2026, September). Applicability of AI in identifying early signs of depression and anxiety through digital behaviours and language patterns in teens. Int. j. of Social Science and Economic Research, 11(9), 5116-5128. Retrieved from https://doi.org/10.46609/IJSSER.2026.v11i09.039 Chicago Gulati, Aadvitiya. "Applicability of AI in identifying early signs of depression and anxiety through digital behaviours and language patterns in teens." Int. j. of Social Science and Economic Research 11, no. 9 (September 2026), 5116-5128. Accessed September, 2026. https://doi.org/10.46609/IJSSER.2026.v11i09.039.
References [1] . Zhang, P., Li, B., Miao, X., Meng, X., Yuan, H., Yan, W., & Peng, K. (2022). Early Screening of adolescents at Risk for Depression: An efficient Machine-Learning-Based identification and Subgroup Discovery system. SSRN Electronic Journal. https://doi.org/10.2139/ssrn.4117348 [2] . Brady, T., Sbai, J., Wallace-Hanlon, S., Harter, C., Kaminska, K., Fischer, M. D. S., Decheva, M., Monteiro, A. R. V., Wiedemann, A., Pralat, R., Muschialli, L., Fonagy, P., Suckling, J., & Moore, A. (2026). The Use of Artificial intelligence Tools in the prediction and identification of mental health disorders in children and Young People: A Systematic Review and Meta-Analysis. SSRN Electronic Journal. https://doi.org/10.2139/ssrn.6846681 [3] . Beames, J. R., Han, J., Shvetcov, A., Zheng, W. Y., Slade, A., Dabash, O., Rosenberg, J., O’Dea, B., Kasturi, S., Hoon, L., Whitton, A. E., Christensen, H., & Newby, J. M. (2024). Use of smartphone sensor data in detecting and predicting depression and anxiety in young people (12–25 years): A scoping review. Heliyon, 10(15), e35472. https://doi.org/10.1016/j.heliyon.2024.e35472 [4] . Tabares, M. T., Álvarez, C. V., Salcedo, J. B., & Rendón, S. M. (2024). Anxiety in young people: Analysis from a machine learning model. Acta Psychologica, 248, 104410. https://doi.org/10.1016/j.actpsy.2024.104410 [5] . Mardini, M. T., Khalil, G. E., Bai, C., DivaKaran, A. M., & Ray, J. M. (2024). Identifying adolescent depression and anxiety through Real-World data and social Determinants of Health: Machine Learning model development and validation. JMIR Mental Health, 12, e66665. https://doi.org/10.2196/66665 [6] . Shen, Y. (2023). High School Emotional Well-Being: Identifying factors and creating a working model for prediction. SSRN Electronic Journal. https://doi.org/10.2139/ssrn.4556247 [7] . Mardini, M. T., Khalil, G. E., Bai, C., DivaKaran, A. M., & Ray, J. M. (2024). Identifying adolescent depression and anxiety through Real-World data and social Determinants of Health: Machine Learning model development and validation. JMIR Mental Health, 12, e66665. https://doi.org/10.2196/66665 [8] . MacLeod, L., Suruliraj, B., Gall, D., Bessenyei, K., Hamm, S., Romkey, I., Bagnell, A., Mattheisen, M., Muthukumaraswamy, V., Orji, R., & Meier, S. (2021). A mobile sensing app to monitor youth mental health: Observational pilot study. JMIR Mhealth and Uhealth, 9(10), e20638. https://doi.org/10.2196/20638 [9] . Leijse, M. M. L., Hansen, A., Semeijn, I. K., Breuning, E., Staaks, J. P. C., Van Der Pol, T. M., Stams, G. J. M., Popma, A., & Van Dam, L. (2026). A multilevel meta-analysis of passive smartphone sensing of adolescent mental health. Npj Digital Medicine, 9(1). https://doi.org/10.1038/s41746-026-02706-2 [10] . Weiß, M., Gutzeit, J., Pryss, R., Romanos, M., Deserno, L., & Hein, G. (2024). Common and differential variables of anxiety and depression in adolescence: a nation-wide smartphone-based survey. Child and Adolescent Psychiatry and Mental Health, 18(1), 103. https://doi.org/10.1186/s13034-024-00793-1 [11] . Kadirvelu, B., Bel, T. B., Freccero, A., Di Simplico, M., Nicholls, D., & Faisal, A. A. (2025). Digital Phenotyping for Adolescent Mental Health: Feasibility Study using machine Learning to predict mental health risk from active and passive smartphone data. Journal of Medical Internet Research, 28, e72501. https://doi.org/10.2196/72501 [12] . Li, Y., Lin, Y., Wu, H., Yang, L., Zhu, L., Sun, X., Dong, S., Wang, W., Yang, L., Yan, B., & Lu, C. (2025). Changes in smartphone dependence and depressive and anxiety symptoms among Chinese adolescents. BMC Medicine, 23(1), 523. https://doi.org/10.1186/s12916-025-04372-9 [13] . Pennant, M. E., Loucas, C. E., Whittington, C., Creswell, C., Fonagy, P., Fuggle, P., Kelvin, R., Naqvi, S., Stockton, S., & Kendall, T. (2015). Computerised therapies for anxiety and depression in children and young people: A systematic review and meta-analysis. Behaviour Research and Therapy, 67, 1–18. https://doi.org/10.1016/j.brat.2015.01.009 [14] . Välimäki, M., Anttila, K., Anttila, M., & Lahti, M. (2017). Web-Based Interventions Supporting Adolescents and Young People with Depressive Symptoms: Systematic Review and Meta-Analysis. JMIR Mhealth and Uhealth, 5(12), e180. https://doi.org/10.2196/mhealth.8624 [15] . Schniering, C. A., Einstein, D., Kirkman, J. J. L., & Rapee, R. M. (2022). Online treatment of adolescents with comorbid anxiety and depression: A randomized controlled trial. Journal of Affective Disorders, 311, 88–94. https://doi.org/10.1016/j.jad.2022.05.072 [16] . Topooco, N., Byléhn, S., Nysäter, E. D., Holmlund, J., Lindegaard, J., Johansson, S., Åberg, L., Nordgren, L. B., Zetterqvist, M., & Andersson, G. (2019). Evaluating the efficacy of Internet-Delivered Cognitive Behavioral therapy blended with synchronous chat sessions to treat adolescent depression: randomized controlled trial. Journal of Medical Internet Research, 21(11), e13393. https://doi.org/10.2196/13393 [17] . Osborn, T. L., Rodriguez, M., Wasil, A. R., Venturo-Conerly, K. E., Gan, J., Alemu, R. G., Roe, E., G, S. A., Otieno, B. H., Wasanga, C. M., Shingleton, R., & Weisz, J. R. (2020). Single-session digital intervention for adolescent depression, anxiety, and well-being: Outcomes of a randomized controlled trial with Kenyan adolescents. Journal of Consulting and Clinical Psychology, 88(7), 657–668. https://doi.org/10.1037/ccp0000505 [18] . Kuberka, P., Johnston, M. H., Shafran, R., Pike, K., & Yardley, L. (2025). Digital Interventions for Anxiety and Depressive Symptoms in Adolescence: Systematic review. Journal of Adolescent Health, 77(3), 388–404. https://doi.org/10.1016/j.jadohealth.2025.05.021 [19] . Wang, H., Yao, J., Jia, S., Chen, W., Guan, Y., Liu, J., Liao, M., Hu, E., & Zhang, Q. (2026). Comparative efficacy of digital health interventions for depression and anxiety symptoms in adolescents and young adults: a systematic review and bayesian network meta-analysis. Child and Adolescent Psychiatry and Mental Health, 20(1), 25. https://doi.org/10.1186/s13034-026-01042-3
ABSTRACT: Early identification of depression in adolescents remains one of the most pressing challenges in global public health, given the condition’s rising prevalence and its long-term impact on development, education, and overall wellbeing. Despite growing awareness, most existing screening approaches rely on broad, one-size-fits-all models that treat the adolescent population as a single, homogeneous group. This overlooks the reality that risk factors for depression can vary considerably across subgroups defined by demographic, social, behavioural, or clinical characteristics. As a result, few current methods offer targeted or subgroup-specific estimates of depression risk, limiting their precision and practical usefulness in real-world screening contexts. The present study seeks to address this gap by identifying the specific characteristics that place adolescents at elevated risk of depression, rather than relying solely on generalized risk indicators. Building on these characteristics, the study aims to define meaningful subgroups within the adolescent population and construct subgroup-specific predictive models. These models are designed and optimized to more accurately detect adolescents who are currently experiencing a high risk of depression, taking into account the distinct patterns and risk profiles present within each subgroup. By moving beyond generalized screening tools toward more tailored, subgroup-based approaches, this study aims to improve early detection efforts and ultimately support more effective, timely mental health interventions for at-risk youth. The analysis found several strong predictors of anxiety, including parental education level, alcohol use, and social security status. Anxiety was also linked to personal and family histories of mental illness, along with related factors like a family or personal history of depression. These findings suggest that mental health interventions should account for social and family circumstances, not just clinical ones. The authors recommend using larger samples in future research to make the models more reliable. Overall, the study shows that AI can be a useful tool for early anxiety detection in young people and emphasizes the need to consider multiple, interconnected factors when assessing and treating this condition.

IJSSER is Member of