Designing a predictive model of self-destructive behavior based on automated analysis of search queries

A. B. Uglova, B. A. Nizomutdinov

Abstract


The article considers the possibility of creating a predictive model of self-destructive behavior based on the results of automated analysis of users' search queries about destructive behaviors and the search for psychological help. An automated analysis of statistical information about user requests was carried out on the basis of an empirically identified implicit dictionary of markers about autodestructive behavior. The All-Russian and regional query statistics were processed and analyzed using the Yandex Wordstat tool. The study showed the annual variability of users' interest in self-destructive topics, as well as the regional specifics of requests. There was an increase in interest in the fourth quarter in the autumn-winter period and a decline in interest in the third quarter in the summer. The results obtained repeat the seasonal dynamics of clinical diseases identified in previous studies. To build a preventive model using regression analysis, predictors of an increase in requests for professional psychological assistance were identified. The regions with the greatest interest in self-destructive behavior (Barnaul, Belgorod, Irkutsk, Khabarovsk) were also identified, which can be useful for building a flexible monitoring system. The study showed that the analysis of information about self-destructive practices and the need for psychological help is one of the most objective analysis tools, since it allows you to evaluate large amounts of information without the influence of social desirability and socio-cultural stereotypes about psychological help.

Full Text:

PDF (Russian)

References


Tarasova E.N., Bezrukov E.V., Ursu A.V. Analysis of the population's needs for various types of psychological assistance // Biomedical, clinical and social issues of human health and pathology. 2020. pp. 244-246.

Uglova A. B., Bogdanovskaya I. M., Nizmutdinov B. A. A method of self-regulation using extended functionality based on a synthesizer biopsychosocial and cyberpsychological parade // Research of Science and education. 2023. No. 1 (61). P. 432-450. DOI: 10.32744/pse.2023.1.26.

Suler J. Dimensions of Cyberpsychology: The Boundaries of Self and Reality online // Consequences of digital realities. 2017. P. 1-23. DOI: 10.1016/B978-0-12-804157-4.00001-3.

Machimbarrena H.M., Gonzalez-Cabrera H., Ortega-Baron H., Beranui-Farges M., Alvarez-Bardon A., Tejero B. Profiles of problematic Internet use and its impact on the quality of life of adolescents related to health // International Journal of Environmental Research and Public Health. 2019. No. 16 (20). P. 3877.

Kaess M., Klar J., Wasserman D. Excessive and pathological use of the Internet – risky behavior or psychopathology? // Addictive behavior. 2021. Vol. 123. P. 107045.

Kalear A. L., McCallum S., Kazan D., Werner-Seidler A., Christensen H., Batterham P. J. Application of interpersonal psychological theory of suicide in the non-clinical community of adolescents // Journal of Affective Disorders. 2021. Vol. 294. P. 235-240. DOI: 10.1016/j.jad.2021.07.011.

Katazhina O., Envu K., Gulbas L. E. Sense of belonging and suicidal behavior of youth: what do communities and schools have to do with this? // Social work in public health. 2017. Vol. 32(7). P. 432-442. DOI: 10.1080/19371918.2017.1344602.

Gallier A. J., Khaychak G., Joyner T. What is the ability to commit suicide? // Overview of available evidence. 2020. DOI: 10.31234/osf.io/xgwa5.

Hyun M.C., Eun J.., Eun J.C. Conceptual analysis of uncertainty in people with mental disabilities // Archive of Psychiatric Nursing. 2023. Vol. 45. P. 44-53.

Burke T.A., Ammerman B.A., Iacobucci R. The use of machine learning in the study of suicidal and non-suicidal self-harming thoughts and behavior: a systematic review // J Affects the imbalance. February 15, 2019. P. 869-884.

Kusuma K., Larsen M., Kiroz J.S., Gillis M., Burnett A., Kian J., Torok M. Effectiveness of machine learning models in predicting suicidal thoughts, attempts and deaths: meta-analysis and systematic review // J Psychiatr Res. 2022. Vol. 155. P. 579-588.

Hare S. K., March S., Acharya U. R. Application of data fusion for automated identification of children with developmental and mental disorders: a systematic review of the last decade // Merging information. 2023. Vol. 99. P.101898.

Rosenfeld A., Benrimo D., Yaniv-Rosenfeld A. Big data analytics and artificial intelligence in psychiatric care // Application of big data in healthcare. 2021. P. 137-171.

Bernert R.A., Hilberg A.M., Melia R., Kim J.P., Shah N.H., Abnusi F. Artificial intelligence and suicide prevention: A systematic review of machine learning research // Environment and public health. 2020. No. 17(16). P. 5929.

Akimkin V.G., Tutelyan A.V., Shulakova N.I. Shulakova, Voronin E.M. COVID-19 pandemic: a new round of antibiotic resistance growth // Infectious diseases. 2021. Vol. 19. No. 3. P. 133-138. DOI: 10.20953/1729-9225-2021-3-133-138.

Perov E.V. Analysis of socio-economic conflictogenicity of society according to Yandex data.Wordstat search engine // Social and economic systems. 2018. No. 5. P. 5-16.

Simutkin G. G. Special patterns of the course of affective disorders. Tomsk: Publishing House Vol. un-ta, 2010. 416 p.

Gulliver A., Griffiths K.M., Christensen H. Perceived barriers and factors contributing to youth seeking help in the field of mental health: a systematic review // BMC Psychiatry. 2010. No. 10(1). P. 1-9.

Shi W., Shen Z., Wang S., Hall B.J. Barriers to professional psychological help among Chinese adults: a systematic review // Before. Psychiatrist. 2020. No. 11. P. 442.

Petrelli, M. Enter, A. Young, K. Zulauf, T. Willens College Students: Mental Health problems and treatment recommendations // Acad. Psychiatry. 2015. No. 39(5). P. 503-511.


Refbacks

  • There are currently no refbacks.


Abava  Кибербезопасность MoNeTec 2024

ISSN: 2307-8162