The Bulletin of National Defence University of Ukraine

  • Home
  • Vol. 20, No. 6, 2025

  • Linguistic and paralinguistic predictors of suicidal behaviour among military personnel and veterans: A review of the literature

  • Received 29.05.2025,
  • Revised 06.11.2025,
  • Accepted 27.11.2025
Download article Download article
Vol. 20, No. 6, 2025
  • linguistic markers; early suicide warning; mental health; post-traumatic stress disorder; thought processes
  • https://doi.org/10.33099/2617-6858-25-20-6-111-121
  • Pages 111-121

The problem of suicide among military personnel and veterans has become particularly acute in the context of military operations in Ukraine. Prolonged deployment in the combat zone, loss of comrades, and a combination of physical and psychological trauma significantly increase the risk of developing depression and suicidal intentions. Traditional methods of psychological diagnosis often do not provide adequate sensitivity, as military personnel often hide their problems due to fear of stigmatisation or unwillingness to seek help. This highlights the need to find innovative approaches, among which the analysis of linguistic and prosodic characteristics as potential predictors of suicide plays a leading role. The aim of the study was to review current scientific approaches to identifying the risk of suicidal behaviour in the military environment by systematising linguistic and prosodic indicators and determining their diagnostic and prognostic value for the development of early suicide warning systems. The work was carried out in the format of a systematic review of scientific literature using methods of analysis, synthesis, induction and generalisation. Publications in psychology, psychiatry, neurobiology, linguistics and related disciplines were reviewed. Particular attention was paid to studies that examined linguistic and vocal markers of depressive and suicidal states in the context of military service and post-service adaptation. It was found that the speech of military personnel at increased risk of suicide is characterised by a number of features: frequent use of categorical statements, preference for first-person singular pronouns, reduced syntactic complexity, a tendency to use negative constructions, and a predominance of negatively coloured vocabulary. Prosodic analysis revealed monotony of voice, reduced volume, slowed tempo, and uniformity of intonation patterns. Combining these indicators with machine learning data can significantly improve the accuracy of risk prediction and create multimodal systems for assessing psycho-emotional state. The results obtained have applied significance for improving approaches to the prevention of suicidal behaviour in the military environment. The use of automated systems for analysing textual and acoustic speech parameters creates the conditions for timely monitoring of the mental state of military personnel and veterans, early detection of crisis trends, and implementation of preventive measures in conditions of limited access to psychological assistance

References

  1. Al-Mosaiwi, M., & Johnstone, T. (2018). In an absolute state: Elevated use of absolutist words is a marker specific to anxiety, depression, and suicidal ideation. Clinical Psychological Science: A Journal of The Association for Psychological Science, 6(4), 529-542. doi: 10.1177/2167702617747074.
  2. Baker, D., & Fortune, S. (2008). Understanding self-harm and suicide websites: A qualitative interview study of young adult website users. Crisis, 29(3), 118-122. doi: 10.1027/0227-5910.29.3.118.
  3. Beck, A.T., Brown, G.K., Steer, R.A., Dahlsgaard, K.K., & Grisham, J.R. (1999). Suicide ideation at its worst point: A predictor of eventual suicide in psychiatric outpatients. Suicide and Life-Threatening Behavior, 29(1), 1-9.
  4. Belouali, A., Gupta, S., Sourirajan, V.Yu.J., Allen, N., Alaoui, A., Dutton, M.A., & Reinhard, M.J. (2021). Acoustic and language analysis of speech for suicidal ideation among US veterans. BioData Mining, 14(1), article number 11. doi: 10.1186/s13040-021-00245-y.
  5. Bojanić, L., Hunt, I.M., Flynn, S., Ibrahim, S., & Turnbull, P. (2025). Exploring suicide-related internet use among suicidal mental health patients in the United Kingdom: Cross-sectional questionnaire study. JMIR Mental Health, 12, article number e70458. doi: 10.2196/70458.
  6. Ceja, Z., van Velzen, L.S., Campos, A.I., Jahanshad, N., Medland, S.E., Edwards, A.C., Schmaal, L., & Rentería, M.E. (2025). Recent breakthroughs in genetic and brain structural correlates of suicidal behaviors: A short review. Biological Psychiatry, 97(8), 775-785. doi: 10.1016/j.biopsych.2024.09.010.
  7. Darby, J.K., Simmons, N., & Berger, P.A. (1984). Speech and voice parameters of depression: A pilot study. Journal of Communication Disorders, 17(2), 75-85. doi: 10.1016/0021-9924(84)90013-3.
  8. Delage, H., & Frauenfelder, U.H. (2019). Syntax and working memory in typically-developing children: Focus on syntactic complexity. Language, Interaction and Acquisition, 10(2), 141-176. doi: 10.1075/lia.18013.del.
  9. Desmet, B., & Hoste, V. (2018). Online suicide prevention through optimised text classification. Information Sciences, 439, 61-78. doi: 10.1016/j.ins.2018.02.014.
  10. Dhelim, S., Chen, L., Ning, H., & Nugent, C. (2023). Artificial intelligence for suicide assessment using audiovisual cues: A review. Artificial Intelligence Review, 56(6), 5591-5618. doi: 10.1007/s10462-022-10290-6.
  11. Du, X., & Sun, Y. (2022). Linguistic features and psychological states: A machine-learning based approach. Frontiers in Psychology, 13, article number 955850. doi: 10.3389/fpsyg.2022.955850.
  12. Fahey, R.A., Boo, J., & Ueda, M. (2020). Covariance in diurnal patterns of suicide-related expressions on Twitter and recorded suicide deaths. Social Science & Medicine, 253, article number 112960. doi: 10.1016/j.socscimed.2020.112960.
  13. Fazakas-DeHoog, L.L., Rnic, K., & Dozois, D.J.A. (2017). A cognitive distortions and deficits model of suicide ideation. Europe’s Journal of Psychology, 13(2), 178-193. doi: 10.5964/ejop.v13i2.1238.
  14. Finnegan, A., Salem, K., & Ainsworth-Moore, L. (2025). “One is too many” preventing self-harm and suicide in military veterans: A quantitative evaluation. BMJ Military Health, 171(3), 213-220. doi: 10.1136/military-2023-002623.
  15. Harris, K.M., McLean, J.P., & Sheffield, J. (2009). Examining suicide-risk individuals who go online for suicide-related purposes. Archives of Suicide Research: Official Journal of the International Academy for Suicide Research, 13(3), 264-276. doi: 10.1080/13811110903044419.
  16. Hawton, K., Lascelles, K., Pitman, A., Gilbert, S., & Silverman, M. (2022). Assessment of suicide risk in mental health practice: Shifting from prediction to therapeutic assessment, formulation, and risk management. The Lancet. Psychiatry, 9(11), 922-928. doi: 10.1016/S2215-0366(22)00232-2.
  17. Herbert, C., Bendig, E., & Rojas, R. (2019). My sadness – our happiness: Writing about positive, negative, and neutral autobiographical life events reveals linguistic markers of self-positivity and individual well-being. Frontiers in Psychology, 9, article number 2522. doi: 10.3389/fpsyg.2018.02522.
  18. Homan, S., et al. (2022). Linguistic features of suicidal thoughts and behaviors: A systematic review. Clinical Psychology Review, 95, article number 102161. doi: 10.1016/j.cpr.2022.102161.
  19. Huang, R., Yi, S., Chen, J., Chan, K.Y., Chan, J.W.Y., Chan, N.Y., Li, S.X., Wing, Y.K., & Li, T.M.H. (2024). Exploring the role of first-person singular pronouns in detecting suicidal ideation: A machine learning analysis of clinical transcripts. Behavioral Sciences, 14(3), 225. doi: 10.3390/bs14030225.
  20. Iyer, R., & Meyer, D. (2022). Detection of suicide risk using vocal characteristics: Systematic review. JMIR Biomedical Engineering, 7(2), article number e42386. doi: 10.2196/42386.
  21. Jager-Hyman, S., Cunningham, A., Wenzel, A., Mattei, S., Brown, G.K., & Beck, A.T. (2014). Cognitive distortions and suicide attempts. Cognitive Therapy and Research, 38(4), 369-374. doi: 10.1007/s10608-014-9613-0.
  22. Khraban, T. (2022). Combat and military-professional stress: The influence of emotions and emotional states on the choice of coping strategies. Insight: The Psychological Dimensions of Society, 8, 71-87. doi: 10.32999/2663-970X/2022-8-6.
  23. Khraban, T. (2024). Developing a well-balanced military identity among female military personnel. Polish Sociological Review, 225(1), 69-82. doi: 10.26412/psr225.04.
  24. Kim, K., Choi, S., Lee, J., & Sea, J. (2019). Differences in linguistic and psychological characteristics between suicide notes and diaries. Journal of General Psychology, 146(4), 391-416. doi: 10.1080/00221309.2019.1590304.
  25. Kroenke, K., & Spitzer, R.L. (2002). The PHQ-9: A new depression diagnostic and severity measure. Psychiatric Annals, 32(9), 509-515. doi: 10.3928/0048-5713-20020901-06.
  26. Lao, C., Lane, J., & Suominen, H. (2022). Analyzing suicide risk from linguistic features in social media: Evaluation study. JMIR Formative Research, 6(8), article number e35563. doi: 10.2196/35563.
  27. Lauderdale, S.A., Schmitt, R., Wuckovich, B., Dalal, N., Desai, H., & Tomlinson, S. (2025). Effectiveness of generative AI-large language models’ recognition of veteran suicide risk: A comparison with human mental health providers using a risk stratification model. Frontiers in Psychiatry, 16, article number 1544951. doi: 10.3389/fpsyt.2025.1544951.
  28. Low, L.S., Maddage, N.C., Lech, M., Sheeber, L.B., & Allen, N.B. (2011). Detection of clinical depression in adolescents’ speech during family interactions. IEEE Transactions on Bio-Medical Engineering, 58(3), 574-586. doi: 10.1109/TBME.2010.2091640.
  29. Mann, J.J. (2013). The serotonergic system in mood disorders and suicidal behaviour. Philosophical Transactions of the Royal Society of London. Series B, Biological Sciences, 368(1615), article number 20120537. doi: 10.1098/rstb.2012.0537.
  30. Mann, J.J., Waternaux, C., Haas, G.L., & Malone, K.M. (1999). Toward a clinical model of suicidal behavior in psychiatric patients. American Journal of Psychiatry, 156(2), 181-189. doi: 10.1176/ajp.156.2.181.
  31. McCoy, T.H., Castro, V.M., Roberson, A.M., Snapper, L.A., & Perlis, R.H. (2016). Improving prediction of suicide and accidental death after discharge from general hospitals with natural language processing. JAMA Psychiatry, 73(10), 1064-1071. doi: 10.1001/jamapsychiatry.2016.2172.
  32. Naifeh, J.A., Ursano, R.J., Shor, R., Mash, H.B., Aliaga, P.A., Fullerton, C.S., Kao, T.C., Sampson, N.A., Kessler, R.C., & Stein, M.B. (2025). Suicidal behavior in US Army Special Operations Forces. JAMA Network Open, 8(8), article number e2527395. doi: 10.1001/jamanetworkopen.2025.27395.
  33. Nock, M.K., Deming, C.A., Fullerton, C.S., Gilman, S.E., Goldenberg, M., Kessler, R.C., McCarroll, J.E., McLaughlin, K.A., Peterson, C., Schoenbaum, M., Stanley, B., & Ursano, R.J. (2013). Suicide among soldiers: A review of psychosocial risk and protective factors. Psychiatry, 76(2), 97-125. doi: 10.1521/psyc.2013.76.2.97.
  34. O’Connor, R.C., & Kirtley, O.J. (2018). The integrated motivational-volitional model of suicidal behaviour. Philosophical Transactions of the Royal Society of London. Series B, Biological Sciences, 373(1754), article number 20170268. doi: 10.1098/rstb.2017.0268.
  35. O’Dea, B., Boonstra, T.W., Larsen, M.E., Nguyen, T., Venkatesh, S., & Christensen, H. (2021). The relationship between linguistic expression in blog content and symptoms of depression, anxiety, and suicidal thoughts: A longitudinal study. PloS One, 16(5), article number e0251787. doi: 10.1371/journal.pone.0251787.
  36. Ozdas, A., Shiavi, R.G., Silverman, S.E., Silverman, M.K., & Wilkes, D.M. (2004). Investigation of vocal jitter and glottal flow spectrum as possible cues for depression and near-term suicidal risk. IEEE Transactions on Bio-Medical Engineering, 51(9), 1530-1540. doi: 10.1109/TBME.2004.827544.
  37. Pearl, L. (2023). Computational cognitive modeling for syntactic acquisition: Approaches that integrate information from multiple places. Journal of Child Language, 50(6), 1353-1373. doi: 10.1017/S0305000923000247.
  38. Pestian, J., Santel, D., Sorter, M., Bayram, U., Connolly, B., Glauser, T., DelBello, M., Tamang, S., & Cohen, K. (2020). A machine learning approach to identifying changes in suicidal language. Suicide & Life-threatening Behavior, 50(5), 939-947. doi: 10.1111/sltb.12642.
  39. Ramírez-Cifuentes, D., Freire, A., Baeza-Yates, R., Puntí, J., Medina-Bravo, P., Velazquez, D.A., Gonfaus, J.M., & Gonzàlez, J. (2020). Detection of suicidal ideation on social media: Multimodal, relational, and behavioral analysis. Journal of Medical Internet Research, 22(7), article number e17758. doi: 10.2196/17758.
  40. Randles, R., Burroughs, H., Green, N., & Finnegan, A. (2025). Prevalence and risk factors of suicide and suicidal ideation in veterans who served in the British Armed Forces: A systematic review. BMJ Military Health, 171(2), 166-172. doi: 10.1136/military-2023-002413.
  41. Satyander, S.K. (2024). Suicidal ideation and cognitive distortions among undergraduate students. Educational Administration: Theory and Practice, 30(5), 11239-11245. doi: 10.53555/kuey.v30i5.4922.
  42. Schafer, K.M., Melia, R., & Joiner, T. (2024). Risk and protective correlates of suicidality in the military health and well-being project. Journal of Affective Disorders, 363, 258-268. doi: 10.1016/j.jad.2024.07.141.
  43. Sierra, G., Andrade-Palos, P., Bel-Enguix, G., Osornio-Arteaga, A., Cabrera-Mora, A., García-Nieto, L., & Sierra-Aparicio, T. (2021). Suicide risk factors: A language analysis approach in social media. Journal of Language and Social Psychology, 41(3), 312-330. doi: 10.1177/0261927X211036171.
  44. Silvestrini, M., & Chen, J.A. (2023). “It’s a sign of weakness”: Masculinity and help-seeking behaviors among male veterans accessing posttraumatic stress disorder care. Psychological Trauma: Theory, Research, Practice and Policy, 15(4), 665-671. doi: 10.1037/tra0001382.
  45. Sloan, D.M. (2005). It’s all about me: Self-Focused attention and depressed mood. Cognitive Therapy and Research, 29(3), 279-288. doi: 10.1007/s10608-005-0511-1.
  46. Sokol, Y., Gromatsky, M., Edwards, E.R., Greene, A.L., Geraci, J.C., Harris, R.E., & Goodman, M. (2021). The deadly gap: Understanding suicide among veterans transitioning out of the military. Psychiatry Research, 300, article number 113875. doi: 10.1016/j.psychres.2021.113875.
  47. Sun, K., Liu, H., & Xiong, W. (2020). The evolutionary pattern of language in scientific writings: A case study of philosophical transactions of royal society (1665-1869). Scientometrics, 126, 1695-1724. doi: 10.1007/s11192-020-03816-8.
  48. Tadesse, M.M., Lin, H., Xu, B., & Yang, L. (2020). Detection of suicide ideation in social media forums using deep learning. Algorithms, 13(1), article number 7. doi: 10.3390/a13010007.
  49. Tausczik, Y.R., & Pennebaker, J.W. (2009). The psychological meaning of words: LIWC and computerized text analysis methods. Journal of Language and Social Psychology, 29(1), 24-54. doi: 10.1177/0261927X09351676.
  50. Tsujii, N., Mikawa, W., Tsujimoto, E., Adachi, T., Niwa, A., Ono, H., & Shirakawa, O. (2017). Reduced left precentral regional responses in patients with major depressive disorder and history of suicide attempts. PloS One, 12(4), article number e0175249. doi: 10.1371/journal.pone.0175249.
  51. Weaverdyck, M.E., Thornton, M.A., & Tamir, D.I. (2021). The representational structure of mental states generalizes across target people and stimulus modalities. NeuroImage, 238, article number 118258. doi: 10.1016/j.neuroimage.2021.118258.
  52. Wenzel, A., & Jager-Hyman, S. (2012). Cognitive therapy for suicidal patients: Current status. The Behavior Therapist, 35(7), 121-130.
  53. Wright-Berryman, J., Cohen, J., Haq, A., Black, D.P., & Pease, J.L. (2023). Virtually screening adults for depression, anxiety, and suicide risk using machine learning and language from an open-ended interview. Frontiers in Psychiatry, 14, article number 1143175. doi: 10.3389/fpsyt.2023.1143175.

Submission

 
Flag Counter