Natural language processing of youth speech predicts psychopathology across adolescence – Nature Mental Health

1. Green, J. G. et al. Childhood adversities and adult psychopathology in the National Comorbidity Survey Replication (NCS-R) I: associations with first onset of DSM-IV disorders. Arch. Gen. Psychiatry 67, 113 (2010).

   Article  PubMed  PubMed Central  Google Scholar 

2. Nelson, C. A. & Gabard-Durnam, L. Early adversity and critical periods: neurodevelopmental consequences of violating the expectable environment. Trends Neurosci. 43, 133–143 (2020).

   Article  PubMed  PubMed Central  Google Scholar 

3. Wade, M., Wright, L. & Finegold, K. E. The effects of early life adversity on children’s mental health and cognitive functioning. Transl. Psychiatry 12, 1–12 (2022).

   Article  Google Scholar 

4. Cahill, S., Hager, R. & Shryane, N. Patterns of resilient functioning in early life: identifying distinct groups and associated factors. Dev. Psychopathol. 36, 1789–1809 (2024).

   Article  PubMed  Google Scholar 

5. Masten, A. S. Ordinary magic: resilience processes in development. Am. Psychol. 56, 227–238 (2001).

   Article  PubMed  Google Scholar 

6. Amelio, P. et al. Evaluating the development and well-being assessment (DAWBA) in pediatric anxiety and depression. Child Adolesc. Psychiatry Ment. Health 18, 12 (2024).

   Article  PubMed  PubMed Central  Google Scholar 

7. Jordans, M. J. D. & Kohrt, B. A. Scaling up mental health care and psychosocial support in low-resource settings: a roadmap to impact. Epidemiol. Psychiatr. Sci. 29, e189 (2020).

   Article  PubMed  PubMed Central  Google Scholar 

8. Pennebaker, J. W., Mehl, M. R. & Niederhoffer, K. G. Psychological aspects of natural language use: our words, our selves. Annu. Rev. Psychol. 54, 547–577 (2003).

   Article  PubMed  Google Scholar 

9. Pennebaker, J. W. & King, L. A. Linguistic styles: language use as an individual difference. J. Pers. Soc. Psychol. 77, 1296–1312 (1999).

   Article  PubMed  Google Scholar 

10. Chung, C. & Pennebaker, J. Social Communication (Psychology Press, 2007).

11. Rude, S., Gortner, E.-M. & Pennebaker, J. Language use of depressed and depression-vulnerable college students. Cogn. Emot. 18, 1121–1133 (2004).

    Article  Google Scholar 

12. Argaman, O. Linguistic markers and emotional intensity. J. Psycholinguist. Res. 39, 89–99 (2010).

    Article  PubMed  Google Scholar 

13. Guntuku, S. C., Yaden, D. B., Kern, M. L., Ungar, L. H. & Eichstaedt, J. C. Detecting depression and mental illness on social media: an integrative review. Curr. Opin. Behav. Sci.18, 43–49 (2017).

    Article  Google Scholar 

14. Liu, T. et al. Head versus heart: social media reveals differential language of loneliness from depression. npj Ment. Health Res. 1, 16 (2022).

    Article  PubMed  PubMed Central  Google Scholar 

15. Brockmeyer, T. et al. Me, myself, and I: self-referent word use as an indicator of self-focused attention in relation to depression and anxiety. Front. Psychol. 6, 1564 (2015).

    Article  PubMed  PubMed Central  Google Scholar 

16. Edwards, T. & Holtzman, N. S. A meta-analysis of correlations between depression and first person singular pronoun use. J. Res. Pers. 68, 63–68 (2017).

    Article  Google Scholar 

17. Beech, A. et al. Using natural language processing to identify patterns associated with depression, anxiety, and stress symptoms during the COVID-19 pandemic. J. Affect. Disord. 376, 113–121 (2025).

    Article  PubMed  PubMed Central  Google Scholar 

18. Eichstaedt, J. C. et al. Facebook language predicts depression in medical records. Proc. Natl Acad. Sci. USA 115, 11203–11208 (2018).

    Article  PubMed  PubMed Central  Google Scholar 

19. Atkins, D. C., Steyvers, M., Imel, Z. E. & Smyth, P. Scaling up the evaluation of psychotherapy: evaluating motivational interviewing fidelity via statistical text classification. Implement. Sci. 9, 49 (2014).

    Article  PubMed  PubMed Central  Google Scholar 

20. Flemotomos, N. et al. Automated quality assessment of cognitive behavioral therapy sessions through highly contextualized language representations. PLoS ONE 16, e0258639 (2021).

    Article  PubMed  PubMed Central  Google Scholar 

21. Goldberg, S. B. et al. Machine learning and natural language processing in psychotherapy research: alliance as example use case. J. Couns. Psychol. 67, 438–448 (2020).

    Article  PubMed  PubMed Central  Google Scholar 

22. Malins, S. et al. Developing an automated assessment of in-session patient activation for psychological therapy: codevelopment approach. JMIR Med. Inform. 10, e38168 (2022).

    Article  PubMed  PubMed Central  Google Scholar 

23. Ewbank, M. P. et al. Quantifying the association between psychotherapy content and clinical outcomes using deep learning. JAMA Psychiatry 77, 35–43 (2020).

    Article  PubMed  PubMed Central  Google Scholar 

24. Nook, E. C., Hull, T. D., Nock, M. K. & Somerville, L. H. Linguistic measures of psychological distance track symptom levels and treatment outcomes in a large set of psychotherapy transcripts. Proc. Natl Acad. Sci. USA 119, e2114737119 (2022).

    Article  PubMed  PubMed Central  Google Scholar 

25. He, Q., Veldkamp, B. P., Glas, C. A. W. & de Vries, T. Automated assessment of patients’ self-narratives for posttraumatic stress disorder screening using natural language processing and text mining. Assessment 24, 157–172 (2017).

    Article  PubMed  Google Scholar 

26. Schultebraucks, K., Yadav, V., Shalev, A. Y., Bonanno, G. A. & Galatzer-Levy, I. R. Deep learning-based classification of posttraumatic stress disorder and depression following trauma utilizing visual and auditory markers of arousal and mood. Psychol. Med. 52, 957–967 (2022).

    Article  PubMed  Google Scholar 

27. Son, Y. et al. World Trade Center responders in their own words: predicting PTSD symptom trajectories with AI-based language analyses of interviews. Psychol. Med. 53, 918–926 (2023).

    Article  PubMed  Google Scholar 

28. Pestian, J. P. et al. A controlled trial using natural language processing to examine the language of suicidal adolescents in the emergency department. Suicide Life Threat. Behav. 46, 154–159 (2016).

    Article  PubMed  Google Scholar 

29. Venek, V., Scherer, S., Morency, L.-P., Rizzo, A. S. & Pestian, J. Adolescent suicidal risk assessment in clinician–patient interaction. IEEE Trans. Affect. Comput. 8, 204–215 (2017).

    Article  Google Scholar 

30. Weintraub, M. J., Posta, F., Ichinose, M. C., Arevian, A. C. & Miklowitz, D. J. Word usage in spontaneous speech as a predictor of depressive symptoms among youth at high risk for mood disorders. J. Affect. Disord. 323, 675–678 (2023).

    Article  PubMed  Google Scholar 

31. Asarnow, J. R., Goldstein, M. J., Tompson, M. & Guthrie, D. One-year outcomes of depressive disorders in child psychiatric in-patients: evaluation of the prognostic power of a brief measure of expressed emotion. J. Child Psychol. Psychiatry 34, 129–137 (1993).

    Article  PubMed  Google Scholar 

32. Burkhouse, K. L., Uhrlass, D. J., Stone, L. B., Knopik, V. S. & Gibb, B. E. Expressed emotion-criticism and risk of depression onset in children. J. Clin. Child Adolesc. Psychol. 41, 771–777 (2012).

    Article  PubMed  PubMed Central  Google Scholar 

33. Levis, M., Westgate, C. L., Gui, J., Watts, B. V. & Shiner, B. Natural language processing of clinical mental health notes may add predictive value to existing suicide risk models. Psychol. Med. 51, 1382–1391 (2021).

    Article  PubMed  Google Scholar 

34. Antonacci, C. et al. Frontolimbic connectivity and threat-related psychopathology: a data-driven test of models of early adversity. Dev. Psychobiol. 67, e70080 (2025).

    Article  PubMed  Google Scholar 

35. Hou, J., Mortel, L., Popma, A., Smit, D. & van Wingen, G. Predicting the onset of mental health problems in adolescents. Psychol. Med. 55, e128 (2025).

    Article  PubMed  PubMed Central  Google Scholar 

36. Bufano, P., Laurino, M., Said, S., Tognetti, A. & Menicucci, D. Digital phenotyping for monitoring mental disorders: systematic review. J. Med. Internet Res. 25, e46778 (2023).

    Article  PubMed  PubMed Central  Google Scholar 

37. Kliamovich, D. et al. Leveraging distributed brain signal at rest to predict internalizing symptoms in youth. Biol. Psychiatry Cogn. Neurosci. Neuroimaging 10, 58–67 (2025).

    PubMed  Google Scholar 

38. Danese, A. & Widom, C. S. Objective and subjective experiences of child maltreatment and their relationships with psychopathology. Nat. Hum. Behav. 4, 811–818 (2020).

    Article  PubMed  Google Scholar 

39. Hill, E. D. et al. Prediction of mental health risk in adolescents. Nat. Med. 31, 1840–1846 (2025).

    Article  PubMed  PubMed Central  Google Scholar 

40. Vandewouw, M. M. et al. Using deep learning to predict internalizing problems from brain structure in youth. Transl. Psychiatry 15, 326 (2025).

    Article  PubMed  PubMed Central  Google Scholar 

41. Chng, S. Y. et al. Ethical considerations in AI for child health and recommendations for child-centered medical AI. npj Digit. Med. 8, 152 (2025).

    Article  PubMed  PubMed Central  Google Scholar 

42. Fusar-Poli, P. et al. Ethical considerations for precision psychiatry: a roadmap for research and clinical practice. Eur. Neuropsychopharmacol. 63, 17–34 (2022).

    Article  PubMed  Google Scholar 

43. Ribbe, D. in Measurement of Stress, Trauma, and Adaptation (ed. Stamm, B. H.) 386–387 (Sidran, 1996).

44. Rudolph, K. D. et al. Toward an interpersonal life-stress model of depression: the developmental context of stress generation. Dev. Psychopathol. 12, 215–234 (2000).

    Article  PubMed  Google Scholar 

45. Achenbach, T. M. & Rescorla, L. A. Manual for the ASEBA School-Age Forms and Profiles: An Integrated System of Multi-Informant Assessment (ASEBA, 2001).

46. Ridge, N. W., Warren, J. S., Burlingame, G. M., Wells, M. G. & Tumblin, K. M. Reliability and validity of the youth outcome questionnaire self-report. J. Clin. Psychol. 65, 1115–1126 (2009).

    Article  PubMed  Google Scholar 

47. Kaufman, J. & Schweder, A. E. in Comprehensive Handbook of Psychological Assessment, Vol. 2: Personality Assessment 247–255 (Wiley, 2004).

48. Copeland, W., Shanahan, L., Costello, E. J. & Angold, A. Cumulative prevalence of psychiatric disorders by young adulthood: a prospective cohort analysis from the Great Smoky Mountains Study. J. Am. Acad. Child Adolesc. Psychiatry 50, 252–261 (2011).

    Article  PubMed  PubMed Central  Google Scholar 

49. Radford, A. et al. Robust speech recognition via large-scale weak supervision. In Proc. 40th International Conference on Machine Learning (eds Krause, A. et al.) 28492–28518 (PMLR, 2023).

50. Baevski, A., Zhou, Y., Mohamed, A. & Auli, M. wav2vec 2.0: a framework for self-supervised learning of speech representations. In Advances in Neural Information Processing Systems 12449–12460 (Curran Associates, 2020).

51. pyannote/speaker-diarization-3.1. Hugging Face www.huggingface.co/pyannote/speaker-diarization-3.1 (2024).

52. Seedat, S. et al. Cross-national associations between gender and mental disorders in the WHO World Mental Health Surveys. Arch. Gen. Psychiatry 66, 785–795 (2009).

    Article  PubMed  PubMed Central  Google Scholar 

53. Solmi, M. et al. Age at onset of mental disorders worldwide: large-scale meta-analysis of 192 epidemiological studies. Mol. Psychiatry 27, 281–295 (2022).

    Article  PubMed  Google Scholar 

54. Boyd, R. L., Ashokkumar, A., Seraj, S. & Pennebaker, J. W. The Development and Psychometric Properties of LIWC-22 (Univ. Texas at Austin, 2022); https://doi.org/10.13140/RG.2.2.23890.43205

55. Salton, G. & Buckley, C. Term-weighting approaches in automatic text retrieval. Inf. Proc. Manag. 24, 513–523 (1988).

    Article  Google Scholar 

56. Blei, D. M., Ng, A. Y. & Jordan, M. I. Latent dirichlet allocation. J. Mach. Learn. Res. 3, 993–1022 (2003).

    Google Scholar 

57. Schwartz, H. A. et al. DLATK: differential language analysis toolkit. In Proc. 2017 Conference on Empirical Methods in Natural Language Processing: System Demonstrations (eds Specia, L. et al.) 55–60 (Association for Computational Linguistics, 2017); https://doi.org/10.18653/v1/D17-2010

58. McCallum, A. K. MALLET a machine learning for language toolkit. Sci. Res. https://www.scirp.org/reference/referencespapers?referenceid=490739 (2002).

59. Eichstaedt, J. C. et al. Closed- and open-vocabulary approaches to text analysis: a review, quantitative comparison, and recommendations. Psychol. Methods 26, 398–427 (2021).

    Article  PubMed  Google Scholar 

60. Schwartz, H. A. et al. Personality, gender, and age in the language of social media: the open-vocabulary approach. PLoS ONE 8, e73791 (2013).

    Article  PubMed  PubMed Central  Google Scholar 

61. Argamon, S., Koppel, M., Pennebaker, J. W. & Schler, J. Mining the blogosphere: age, gender and the varieties of self-expression. First Monday https://doi.org/10.5210/fm.v12i9.2003 (2007).

    Article  Google Scholar 

62. Huertas-García, Á., Martín, A., Huertas-Tato, J. & Camacho, D. Exploring dimensionality reduction techniques in multilingual transformers. Cogn. Comput. 15, 590–612 (2023).

    Article  Google Scholar 

63. Kern, M. L. et al. Gaining insights from social media language: methodologies and challenges. Psychol. Methods 21, 507–525 (2016).

    Article  PubMed  Google Scholar 

64. Liu, Y. et al. RoBERTa: a robustly optimized BERT pretraining approach. Preprint at https://arxiv.org/abs/1907.11692 (2019).

65. RoBERTa. Hugging Face https://huggingface.co/docs/transformers/en/model_doc/roberta (2020).

66. López-Otal, M. et al. Linguistic interpretability of transformer-based language models: a systematic review. Preprint at https://arxiv.org/abs/2504.08001v1 (2025).

67. Vaswani, A. et al. Attention is all you need. Preprint at https://arxiv.org/abs/1706.03762 (2023).

Download references