“Decision Tree” as a Tool for Analyzing the Psychodiagnostics Data Latent Connections

Abstract

Background. Machine learning methods turn to be an effective tool for data processing and provide ample opportunities for analyzing the results of psychodiagnostics. At the same time, they have a number of advantages over traditional correlation, factor, regression analysis and allow for a systemic analysis of latent relationships between psychological indicators. Search, analysis, and interpretation of latent indirect relationships between features is one of the key problems in modern psychology. In this regard, the "decision tree" method provides wide opportunities for researchers.

Objective. To demonstrate the capabilities of the "decision tree" method in the processing of multidimensional psychodiagnostics data using specific examples.

Study Participants. The study involved different groups of respondents for processing of heterogeneous original psychodiagnostics data: parents of preschoolers (496 mothers), 83 pre-adolescent schoolchildren (aged 11-12), 79 adolescent schoolchildren (aged 14-16).

Methods. The results of two or more tests were analyzed simultaneously. The study implemented "Parental Attitude Research Instrument" (PARI) by Schafer & Bell, "Analysis of family relationships" by Eidemiller, the Tapping test by Ilyin, the Cattell Culture Fair Intelligence Test, the 12-factor personality questionnaire by Cattell (CPQ), the "Unfinished sentences" test by Michal, the personality test by Rogers & Diamond, and the 14-factor personality questionnaire by Cattell (14 PF). Data processing algorithms were implemented on the DEDUCTOR analytical platform.

Results. Using the «decision tree» method, a large number of psychological traits were classified according to their relationship to different target attributes (psychological characteristics). The study demonstrated the possibilities of the proposed data processing algorithm for evaluating the latent connections between psychological characteristics and for building the hierarchical structures corresponding to vertical system data analysis. In particular, the proposed tool allowed for identifying the relationships between individual psychological and psychosocial characteristics of pre-adolescent schoolchildren (aged 11-12); between personality traits and adaptation characteristics of 14-15-year-old teenagers; between parental attitudes and family relationships among preschoolers' mothers.

Conclusions. The "decision tree" method allows for the analysis of latent relationships between heterogeneous psychodiagnostics data by the level of significance of input features, even without analyzing the structure of the "tree" itself. The method makes it possible to identify the range of values of psychological features in which the intrasystemic relationships are more stable. The data analysis demonstrates the influence of IQ indicators as individual psychological characteristics on the results of schoolchildren testing. Verbal and non-verbal intelligence (14-PF questionnaire and Cattell Culture Fair Intelligence Test) appear to be significant indicators in the interrelations of psychological features.

References

Barabanshchikov, V.A. (2007). Systematic approach within the framework of psychological cognition. Metodologiya i istoriya psikhologii = Methodology and History of Psychology, 2(1), 86−99. (In Russ.)

Cattell, R.B. (1990). Advanced in Cattelian Personality Theory. Handbook of Personality. Theory and Research. New York: Guilford Publ.

Christensen, A.P., Golino, H, Silvia, P.J. (2020). A Psychometric Network Perspective on the Validity and Validation of Personality Trait Questionnaires. European Journal of Personality, 34(6), 1095–1108. https://doi.org/10.1002/per.2265

Chuprikova, N.I. (2009). Development theory: Differentiation-integration paradigm. Moscow: Languages of Slavic Cultures Publ.

Colledani, D., Robusto, E. Anselmi, P. (2024) Shortening and Personalizing Psychodiagnostic Assessments with Decision Tree-Machine Learning Classifiers: An Application Example Based on the Patient Health Questionnaire-9. International Journal of Mental Health and Addiction, 1–21. https://doi.org/10.1007/s11469-024-01332-x

De Young, C.G., Carey, B.E., Krueger, R.F., Ross, S.R. (2016). Ten aspects of the Big Five in the Personality Inventory for DSM-5. Personality Disorders: Theory, Research, and Treatment, 7(2), 113–123. https://doi.org/10.1037/per0000170

Duke, V., Samoilenko, A. (2001). Data Mining: training course. St. Petersburg: Piter Publ. (In Russ.)

Eidemiller, E.G., Yustitsky, V.V. (1989). Family psychotherapy: The basic principles and practical experience. International Journal of Family Psychiatry, 10(3–4), 325–337.

Eisenberg, N., Miller, P. A., Shell, R., McNalley, S., Shea, C. (1991). Prosocial development in adolescence: A longitudinal study. Developmental Psychology, 27(5), 849–857. https://doi.org/10.1037/0012-1649.27.5.849

Ganzen, V.A. (1984). System descriptions in psychology. Leningrad: Leningrad Univ. Publ. (In Russ.)

Israel, A., Brandt, N.D., Spengler, M., Göllner, R., Lüdtke, O., Trautwein, U., Wagner, J. (2022). The longitudinal interplay of personality and school experiences in adolescence. European Journal of Personality, 37(4), 131–153. https://doi.org/10.1177/08902070211062326

Kudryashov, A.V. (1992). The best psychological tests. Petrozavodsk: Petrokom Publ. (In Russ.)

Kuznetsova, V.B. (2017). Personality traits as a mediator of the relationship between parenting practices and behavior problems in children. Psikhologicheskiy zhurnal = Psychological Journal, 38(1), 31−40.

Levitin, A.V. (2006). Introduction to development and analysis (Chapter 10). In the Limitations of the power of algorithms: Decision trees. Algorithms. (pp. 409−417). Moscow: Williams Publ. (In Russ.)

Lomov, B.F. (1996). Consistency in psychology: selected psychological works. Voronezh: MODEK; Moscow: Moscow Psychological and Social Institute Publ. (In Russ.)

Lubovsky, D.V. (1994). Application of the diagnostic complex of a projective interview in the work of a child psychologist-practitioner. Moscow: Center for Psychological Service Publ. (In Russ.)

McCrae, R.R., Costa, P.T. (2021). Understanding persons: From Stern's personalistics to Five-Factor Theory. Personality and Individual Differences, 169, 109816. https://doi.org/10.1016/j.paid.2020.109816

Mõttus, R., Wood, D., Condon, D.M., Zimmermann, J. (2020). Descriptive, Predictive and Explanatory Personality Research: Different Goals, Different Approaches, but a Shared Need to Move Beyond the Big Few Traits. European Journal of Personality, 34(6), 1175–1201. https://doi.org/10.1002/per.2311

Poddyakov, A.N. (2007). H. Werner's comparative developmental psychology in a modern context. Kul'turno istoricheskaya psikhologiya = Cultural Historical Psychology, 3(1), 63−72. (In Russ.)

Price, L., Rauf, I., Gooch, D., Katz, D., Pearce, O., Price, B. (2024). Children's perspectives on pain-logging: Insights from a Co-Design Approach. Proceedings of the 2024 ACM Designing Interactive Systems Conference. (pp. 1306–1318). https://doi.org/10.1145/3643834.3661597

Rogers, C.R., Dymond, R.F. (1999). Psychotherapy and Personality Change: Coordinated Research Studies in the Client-Centered Approach. Chicago: University of Chicago Publ.

Schaefer, E.S., Bell, R.Q. (1958). Development of a parental attitude research instrument. Child Development, 29, 339–361.

Shchebetenko, S., Kalugin, A.Y., Mishkevich, A.M., Soto, C.J., John, O.P. (2020) Measurement invariance and sex and age differences of the big five inventory-2. Evidence From the Russian Version. Assessment, 27(3), 472−486. https://doi.org/10.1177/1073191119860901

Shitikov, V.K., Mastitsky, S.E. (2017). Classification, Regression and Other Data Mining Algorithms Using R. (In Russ.). URL: https://ranalytics.github.io/data-mining (accessed: 12.02.2023).

Slavutskaya, E.V. (2011). The study of intellectual indicators of younger adolescents with a developmental impact on their emotional and volitional sphere. News of Saratov University. New series. Series: Philosophy. Psychology. Pedagogy = News of Saratov University. New series. Series: Philosophy. Psychology. Pedagogy, 11(2), 76−81. (In Russ.)

Slavutskaya, E.V., Abrukov, V.S., Slavutsky, L.A., Bichurina, S.U., Sadovaya, V.V. (2020). Vertical system analysis of student psychodiagnostic data using the "decision tree" method. Science for Education Today, 10(3), 87–107. (In Russ.). https://doi.org/10.15293/2658-6762.2003.05

Slavutskaya, E.V., Slavutskii, L.A, Nikolaev, E.L., Zakharova, A.N. (2021). Neural Network Models for the Analysis and Visualization of Latent Dependencies: Examples of Psycho Diagnostic Data Processing. Knowledge in the Information Society: Joint Conferences XII Communicative Strategies of the Information Society (CSIS2020) and XX Professional Culture of the Specialist of the Future (PCSF2020). (pp. 61−70). St. Petersburg, Cham: Springer Verlag Publ. https://doi.org/10.1007/978-3-030-65857-1_7

Slavutskaya, E.V., Slavutskii, L.A. (2024). Intra System Links Dynamics as a Cause of Development Cyclicity: The Simplest Equations. Digital and Information Technologies in Economics and Management (DITEM2023): Lecture Notes in Networks and Systems, Dushanbe. (pp. 25–36). Cham: Springer Nature Switzerland AG Publ. https://doi.org/10.1007/978-3-031-55349-3_3

Slavutskaya, E.V., Slavutsky, L.A. (2022). Data mining of psychodiagnostics: traditional methods and modern approaches. Cheboksary: Chuvash State Pedagogical University Publ. (In Russ.)

Slavutskaya, E.V., Vladimirova, O.N. (2022). A systematic analysis of psychodiagnostic data and the manifestation of the integro-differentiation principle in personality development. Kazanskiy pedagogicheskiy zhurnal = Kazan Pedagogical Journal, (2), 195–206. (In Russ.). https://doi.org/10.51379/KPJ.2022.152.2.028

Sosnowska, J., Kuppens, P., De Fruyt, F., Hofmans, J. (2020). New directions in the conceptualization and assessment of personality — a dynamic systems approach. European Journal of Personality, 34(6), 988−998. https://doi.org/10.1002/per.2233

Soto, C.J., John, O.P. (2017). Short and extra-short forms of the Big Five Inventory 2: The BFI-2-S and BFI-2-XS. Journal of Research in Personality, 68, 69−81.