Science of Emotion and Sensibility (감성과학)

Korean Society for Emotion and Sensibility (한국감성과학회)
권호 표지
DOI QR코드

DOI QR Code

Predicting Mental Health based on Jungian Psychological Typology using Machine Learning Methods

기계학습 방법을 이용한 심리 유형 기반 정신병리 예측

  • Sangin Lee ;
  • Jongwan Kim
  • 이상인 (전북대학교 심리학과) ;
  • 김종완 (전북대학교 심리학과)
  • Received : 2024.04.04
  • Accepted : 2024.07.02
  • Published : 2024.09.30
Download PDF
⟨ Previous Next ⟩

Abstract

This study aimed to predict psychopathology based on personality measures via supervised machine learning methodology. We implemented the Singer-Loomis Type Deployment Inventory (SLTDI) for psychological typology and the Korean version of the Revised Symptom Checklist 90 (KSCL-95) for psychopathology. A total of 521 Korean adults from across the country participated in the online survey. Statistical analyses including correlation, k-means cluster analysis, classification, and regression-based decoding were performed. Results revealed four differentiated clusters on the spectrum of clinical severity. Moreover, SLTDI could distinguish between hypothesis-driven and data-driven clusters by chance. KSCL-95's three subcategories, as well as its validity, were accurately classified. Regression-based decoding results showed that their typology data significantly predicted social desirability, depression, anxiety, obsessive-compulsive disorder, PTSD, schizophrenia, stress vulnerability, and interpersonal sensitivity significantly. Overall, these findings suggest that personality tests could be utilized to screen for the severity of psychopathology and to implement prevention and early intervention strategies.

본 연구는 성격이 정신병리를 예측하는 가를 지도식 기계학습 방법론을 통해 확인해보고자 하였다. 이를 위해, 한국판 싱어루미스 심리 유형 검사(K-SLTDI) 제 2판과, KSCL-95 검사를 사용하여 전국의 총 521명의 성인을 대상으로 비대면 설문조사를 실시하였다. 예측 분석을 위하여 군집분석, 분류분석, 회귀기반 디코딩을 수행하였다. 그 결과 정신병리의 심각도를 반영하는 4개의 군집을 확인하였다. 또한, 한국판 싱어루미스 심리 유형 검사로 정신병리 수준에 대한 가설 기반 및 데이터 기반 심각도가 반영된 군집을 예측할 수 있었으며, 이는 전체 KSCL-95 및 3개의 상위 범주, 그리고 타당도에 대해 모두 정확하게 분류되었다. 회귀기반 디코딩 결과는 SLTDI 유형검사는 전체 검사 데이터를 활용하였을 때 임상수준을 유의미하게 예측할 수 있었으며, KSCL-95의 22가지 하위 범주 중 긍정왜곡, 우울, 불안, 강박, PTSD, 정신증, 스트레스 취약성, 대인민감, 낮은 조절을 유의수준에서 개별적으로 예측하였다. 이러한 연구 결과는 성격 검사가 정신병리의 심각도에 대한 선별 도구로 활용될 수 있고 예방 및 조기 개입 전략을 구현하는 데 활용될 수 있음을 시사한다.

Keywords

Acknowledgement

이 논문은 한국연구재단 4단계 BK21사업(전북대학교 심리학과)의 지원을 받아 연구되었음(No.4199990714213).

References

  1. American Psychiatric Association. (2013). Diagnostic and statistical manual of mental disorders. 5th ed. (DSM-V). American Psychiatric Publishing, Washington DC. 
  2. Beebe, J. (1988). Comment on Soren Ekstrom's paper. Journal of Analytical Psychology, 33, 345-350. 
  3. Bisbee, C., Mullaly, R., & Osmond, H. (1982). Type and psychiatric illness. Research in Psychological Type, 5(1), 49-68. 
  4. Chmielewski, M., Bagby, R. M., Markon, K., Ring, A. J. Ryder, A. G. (2014). Openness to experience, intellect, schizotypal personality disorder, and psychoticism: Resolving the controversy. Journal of Personality Disorders, 28(4), 483-499. 
  5. Chung, D. (2017) The big five social system traits as the source of personality traits, MBTI, social styles, personality disorders, and cultures. Open Journal of Social Sciences, 5, 269-295. 
  6. Cox, B. J., McWilliams, L. A., Enns, M. W., & Clara, I. P. (2004). Broad and specific personality dimensions associated with major depression in a nationally representative sample. Comprehensive Psychiatry, 45(4), 246-253. 
  7. De Clercq, B., & De Fruyt, F. (2003). Personality disorder symptoms in adolescence: A five-factor model perspective. Journal of Personality Disorders, 17, 269-292. 
  8. De Fruyt, F., De Bolle, M., McCrae, R. R., Terracciano, A., & Costa, P. T. (2009). Assessing the universal structure of personality in early adolescence: The NEO-PI-R and NEO-PI-3 in 24 cultures. Assessment, 16, 301-311. 
  9. DeNisi, A. S., & Shaw, J. B. (1977). Investigation of the uses of self-reports of abilities. Journal of Applied Psychology, 62(5), 641-644. 
  10. Derogatis, L. R., & Unger, R. (2010). Symptom Checklist-90-revised. Corsini Encycl. Psychol., 1-2. 
  11. De Waal, M. W. M., Arnold, I. A., Eekhof, J. A. H., & Van Hemert, A. M. (2004). Somatoform disorders in general practice: Prevalence, functional impairment and comorbidity with anxiety and depressive disorders. British Journal of Psychiatry, 184(6), 470-476. 
  12. Di, Z., Gong, X., Shi, J., Ahmed, H. O., & Nandi, A. K. (2019). Internet addiction disorder detection of Chinese college students using several personality questionnaire data and support vector machine. Addictive Behaviors Reports, 10, 100200. 
  13. Dinga, R., Marquand, A. F., Veltman, D. J., Beekman, A. T., Schoevers, R. A., van Hemert, A. M., ... & Schmaal, L. (2018). Predicting the naturalistic course of depression from a wide range of clinical, psychological, and biological data: A machine learning approach. Translational Psychiatry, 8(1), 241. 
  14. DordiNejad, F. G., & Shiran, M. A. G. (2011). Personality traits and drug usage among addicts. Literacy Information and Computer Education Journal, 2(2), 402-405. 
  15. Ekstrom, S. R. (1988). Jung's typology and DSM-III personality disorders: A comparison of classification. Journal of Analytical Psychology, 33, 329-344. 
  16. Fiske, S. T., & Taylor, S. E. (1991). Social cognition. Mcgraw-Hill Book Company. 
  17. Goh, E. (2017). Understanding and treatment of somatic symptom disorder - According to diagnostic criteria from DSM-V. The Korean Journal of Stress Research, 25(4), 213-219. 
  18. Goh, E. (2020). Application of machine learning algorithm to predict happiness of elementary 3rd graders in Korea. The Journal of Learner-Centered Curriculum and Instruction, 20(3), 1113-1128. 
  19. Grover, S., Aneja, J., Sharma, A., Malhotra, R., Varma, S., Basu, D., & Avasthi, A. (2015). Do the various categories of somatoform disorders differ from each other in symptom profile and psychological correlates. The International Journal of Social Psychiatry, 61(2), 148-156. 
  20. Han S. G. (2015). Doing social sciences in the age of big data: Rethinking analytical strategy in the changing data environment. Korean Journal of Sociology, 49(2), 161-192 
  21. Han, Y. O., & Heo, J. E. (2009). A study on the relationship of MMPI and MBTI attitude scale on the university counseling setting. Korean Journal of Youth Studies, 16(1), 225-250. 
  22. Harkness, K. L., Bagby, R. M., Joffe, R. T., & Levitt, A. (2002). Major depression, chronic minor depression, and the five-factor model of personality. European Journal of Personality, 16, 271-281. 
  23. Haynes, J. D., & Rees, G. (2006). Decoding mental states from brain activity in humans. Nature Reviews Neuroscience, 7(7), 523-534. 
  24. Hong, K. (2020). A predictive model for suicidal ideation of adolescents using random forests machine learning algorithm. Korean Journal of Social Welfare, 72(3), 157-180. 
  25. Hong, K. (2021). Machine learning-based prediction of depression levels: Developing a model for male and female senior citizens. Korean Journal of Social Welfare Research, 70, 145-172. 
  26. Hong, T. H., Hwang, S., & Kim, Y. (2018). Replication of a validation study on the Korean version of the personality inventory for DSM-5 (K-PID-5). Korean Journal of Clinical Psychology, 37(4), 558-572. 
  27. Hyphantis, T., Goulia, P., & Carvalho, A. F. (2013). Personality traits, defense mechanisms and hostility features associated with somatic symptom severity in both health and disease. Journal of psychosomatic research, 75(4), 362-369. 
  28. Janowsky, D. S. (2001). Introversion and extroversion: Implications for depression and suicidality. Current Psychiatry Reports, 3, 444-450. 
  29. Janowsky, D. S., Hong, E., Morter, S., & Howe, L. (2002). Myers Briggs Type Indicator personality profiles in unipolar depressed patients. World Journal of Biological Psychiatry, 26, 18-27. 
  30. Janowsky, D. S., Hong, L., Morter, S., & Howe, L. (1999a). Underlying personality differences between alcohol/substnce-use disorder patients with and without an affective disorder. Alcohol and Alcoholism, 34(3), 370-377. 
  31. Janowsky, D. S., Morter, S., & Hong, L. (2000). Relationship of myers briggs type indicator personality characteristics to suicidality in affective disorder patients. Journal of Psychiatric Research, 36(1), 33-39. 
  32. Janowsky, D. S., Morter, S., Hong, L., & Howe, L. (1999b). Myers briggs type indicator and tridimensional personality questionnaire differences between bipolar patients and unipolar depressed patients. Bipolar Disorder, 1(2), 98-108. 
  33. Jeong, M., Lee, S., Lee, Y., Kim, J. (2024) Predicting nonsuicidal self-injurious thought and behavior using multivariate analysis. Korean Journal of Counseling and Psychotherapy, 36(2), 639-658 
  34. Jho, H. (2018). Exploration of predictive model for learning outcomes of students in the e-learning environment by using machine learning. The Journal of Learner-Centered Curriculum and Instruction, 18(21), 553-572. 
  35. Jung, C. G. (1971). Collected works of C.G. Jung, volume 6: Psychological types. eds. G. Adler and R. F. C. Hull (Princeton University Press), 988. 
  36. Kameda, D. M., & Nyland, J. L. (2003). Relationship between psychological type and sensitivity to anxiety. Perceptual and Motor Skills, 97(3), 789-793. 
  37. Kang, W. (2022). Big Five personality traits predict illegal drug use in young people. Acta Psychologica, 231, 103794. 
  38. Kim, D., Kim, E., & Park, Y. C. (2021). Relationship between the temperament and character inventory temperament, characteristics, and personality psychopathology in the Minnesota Multiphasic Personality Inventory-2-Restructured Form. Anxiety and Mood, 17(1), 28-33. 
  39. Kim, H. (2019). Depression change trajectory and predictors among male and female elderly. Korean Journal of Gerontological Social Welfare, 74(1), 91-114. 
  40. Kim, H., & Kim, J. (2022). Affective responses to ASMR using multidimensional scaling and classification. Science of Emotion and Sensibility, 25(3), 47-62. 
  41. Kim, J. T., & Kim, Y. R. (2005). A study on the relationship between personality type and personality disorder. Psychological Type & Human Development (PTHD), 12, 1-20. 
  42. Kim, S. A., Shin, M. S., & Rhi, B. Y. (1997) A revision of the Korean version of Jungian type survey / the Gray-Wheelwrights Test. Shim-Song Yon-Gu, 12(1), 22-79. 
  43. Kim, Y. (2019). An inquiry for the predictive variables on the demand for the private tutoring utilizing machine learning approaches. The Journal of Economics and Finance of Education, 28(3), 29-52. 
  44. Kim, Y., Kim, M., & Lee, G. (2019). Analysis on the factors predicting reading activities of high school students. The Journal of Economics and Finance of Education, 28(4), 137-156. 
  45. Ko, E., Kang, H., Kim, Y., & Jeong S. (2017). A Case study of a machine-learning approach in differential diagnosis of schizophrenia : The predictive capacity of WAIS-IV. J Korean Neuropsychiatr Assoc, 56(3), 103-110. 
  46. Kohlmann, S., Gierk, B., Murray, A. M., Scholl, A., Lehmann, M., & Lowe, B. (2016). Base rates of depressive symptoms in patients with coronary heart disease: An individual symptom analysis. PLoS One, 11(5), e0156167 
  47. Kwag, M., Park, H., Kim, E., Cheon, S., Sang, W. (2010). Emotional characteristics in MBTI personality type and MMPI-A scale of science gifted. Journal of Gifted/Talented Education, 20(3), 767-788. 
  48. Kwon, S. (2015). Implementation guidelines of Korean-symptom check List95 (KSCL95). 5-26. Jung Ang Juk Sung. Seoul Korea. 
  49. Lee, C. (2020) Performance analysis of machine learning algorithms using data related to smartphone addiction of elementary school students. Journal of Korean Practical Arts Education, 33(4), 103-119 
  50. Lee, C., Na, W. Y., & Yi, H. S. (2020). Longitudinal prediction of student academic performance using a recurrent neural network. Journal of Educational Evaluation, 33(1), 161-189. 
  51. Lee, D., Kim, K., Moon, S., & Kwon., G. H. (2019). Analysis of influence factors of internet, smart phone addiction prevention education: Focusing on decision tree analysis. Korean Journal of Policy Analysis and Evaluation, 29(4), 241-270. 
  52. Lee, E., Song, Y., Kim, J. & Oh, S. (2020). An exploratory study on determinants predicting the dropout rate of 4-year universities using random forest: Focusing on the institutional level factors. Journal of Educational Technology, 36(1), 191-219. 
  53. Lee, G. M. (2018). Artificial intelligence: From turing test to deep learning. Life & Power Press Co., Ltd.
  54. Lee, H., Auh, Q., Jung, K., Chun, Y., & Hong, J. (2008). Personality type test(MBTI) of the Korean bruxism patients. Journal of Oral Medicine and Pain, 33(1), 41-48. 
  55. Lee, J., Kim, D., & Jo, I. (2020). Exploration of predictive model for learning achievement of behavior log using machine learning in video-based learning environment. Journal of Korean Association of Computer Education, 23(2), 53-64. 
  56. Lee, S., & Kim, J. (2024). Testing the bipolar assumption of singer-loomis type deployment inventory for korean adults using classification and multidimensional scaling. Frontiers in Psychology, 14, 1249185. 
  57. Lee, S., Han, Y., Kim, H., Lee, H., Park, J., Choi, G., Park, D., Choi, J., Kim, M., & Seo, D. (2019). Development and validation of multi-dimensional personality inventory in preliminary study: Integrating bright and dark sides of personality. Korean Journal of Clinical Psychology, 38(3), 318-334. 
  58. Leiknes, K. A., Finset, A., Moum, T., & Sandanger, I. (2007). Current somatoform disorders in Norway: Prevalence, risk factors and comorbidity with anxiety, depression and musculoskeletal disorders. Social Psychiatry and Psychiatric Epidemiology, 42, 698-710. 
  59. Lester, D. (2021). Depression, suicidal ideation and the big five personality traits. Aust. J. Psychiatry Behav. Sci, 7(1), 1-4. 
  60. Lim, S., Choi, M., Yun, J., Yoon, W., & Kim, G. (2023). Machine learning-based drug consumption risk prediction and drug type classification using the NEO-FFI-R test. In Proceedings of KIIT Conference (pp. 421-426). 
  61. Lim, S., Kim, T., & Park, J. (2008). MBTI personality types and MMPI clinical characteristics profiles of clients at college counseling centers. Korea Journal of Youth Counseling, 16(2), 91-104. 
  62. Mabe, P. A., & West, S. G. (1982). Validity of self-evaluation of ability: A review and meta-analysis. Journal of Applied Psychology, 67(3), 280-296. 
  63. Meier, C. A. (1986). Psychological types and individuation; A plea for a more scientific approach in Jungian psychology. Soul and body, The lapis press, Santa Monica San Francisco. 
  64. Millon, T., & Kotik, D. (1985). The relationship of depression to disorders of personality. Handbook of depression, 700-744. 
  65. Otis, G. D., & Louks, J. L. (1997). Rebelliousness and psychological distress in a sample of introverted veterans. Journal of Psychological Type, 40, 20-30. 
  66. Park, C., & Kim, J. (2023). Predicting relationship between instagram use and psychological variables during COVID-19 quarantine using multivariate techniques. Science of Emotion & Sensibility, 26(4), 3-14. 
  67. Pak, D., Hwang, M., Lee, M., Woo, S., Hahn, S., Lee, Y. J., Hwang, J. (2020). Application of text-classification based machine learning in predicting psychiatric diagnosis. Korean Journal of Biological Psychiatry, 27(1), 18-26. 
  68. Park, H. (2011). Personality type test (MBTI) of Korean college students with symptoms of temporomandibular disorders. Journal of Oral Medicine and Pain, 36(1), 25-37. 
  69. Park, H. (2013). A preliminary study of the singer-loomis type deployment inventory for the Korean version. Shim-Song Yon-Gu, 28, 139-153. 
  70. Park, J., & Lim, S. (2002). A study of the relation between the reffered problem types and personality types of student clients in university. Psychological Type & Human Development (PTHD), 9, 15-29. 
  71. Park, K., & Kim, M. S. (1995). One study of psychological types and psychological dysfunction in the scales of MMPI and 16PF. Korean Journal of Clinical Psychology, 14(1), 201-217. 
  72. Park, K., Kim, M. S., & Kang M. H. (1997). The study on the clinical symptom of psychological type. Korean Journal of Counseling and Psychotherapy, 9(1), 209-225. 
  73. Paulhus, D. L., Lysy, D. C., & Yik, M. S. (1998). Self-report measures of intelligence: Are they useful as proxy IQ tests?. Journal of Personality, 66(4), 525-554. 
  74. Quenk, A. T. (1984). Psychological types and psychotherapy. Center for Applications of Psychological Type. 
  75. Rhi., B. Y., Yeon, B. K., Chang, H. I., Yoo, J. H., Kim, Z. S.(1988). A statistical survey on the relationship between psychological types and neurotic symptoms. Shim-Song Yon-Gu, 3(2), 63-106. 
  76. Saklofske, D. H., Kelly, I. W., & Janzen, B. L. (1995). Neuroticism, depression, and depression proneness. Personality and Individual Differences, 18(1), 27-31. 
  77. Seo, B.-S., Suh, E.-K., & Kim, T.-H. (2020). A study on the prediction model of the elderly depression. The Journal of Industrial Distribution & Business, 11(7), 29-40. 
  78. Shull, A. (2014). Rumination mediates the impact of personality on the development of depression during the transition to college (Doctoral dissertation). 
  79. Sim H. S., & Lee S. M. (1996). A study of the relationship between psychological function and psychological dysfunction. Journal of the Korea Academy of Psychological Type, 3(1), 1-15. 
  80. Spencer, M., Wagner, R. K., & Petscher, Y. (2019). The reading comprehension and vocabulary knowledge of children with poor reading comprehension despite adequate decoding: Evidence from a regression-based matching approach. Journal of Educational Psychology, 111(1), 1-14 
  81. Spinhoven, P., Batelaan, N., Rhebergen, D., van Balkom, A., Schoevers, R., & Penninx, B. W. (2016). Prediction of 6-yr symptom course trajectories of anxiety disorders by diagnostic, clinical and psychological variables. Journal of Anxiety Disorders, 44, 92-101. 
  82. Widiger, T. A. (2011). The DSM-5 dimensional model of personality disorder: Rationale and empirical support. Journal of Personality Disorders, 25(2), 222-234. 
  83. Yeum D. (2024). Predicting and analyzing elementary students' suicidal ideation using machine learning. Children's Light, 119(1), 35-61. 
  84. Zhou, M., Li, F., Wang, Y., Chen, S., & Wang, K. (2020). Compensatory social networking site use, family support, and depression among college freshman: Three-wave panel study. Journal of Medical Internet Research, 22(9), e18458.