The Problem of Identifying Text Markers of Depression and Depressiveness in Automatic Text Analysis
- 作者: Nikitina E.N.1, Stankevich M.A.1, Chudova N.V.1
-
隶属关系:
- Federal Research Center “Computer Science and Control” of the Russian Academy of Sciences
- 期: 卷 22, 编号 1 (2025)
- 页面: 123-143
- 栏目: PERSONALITY AND DIGITAL TECHNOLOGIES: OPPORTUNITIES AND CHALLENGES
- URL: https://journal-vniispk.ru/2313-1683/article/view/326280
- DOI: https://doi.org/10.22363/2313-1683-2025-22-1-123-143
- EDN: https://elibrary.ru/UCTISS
- ID: 326280
如何引用文章
全文:
详细
The paper examines the interdisciplinary topic of the possibility of determining the psychological characteristics of authors from their texts, which may be useful for artificial intelligence methods. The aim of the study was to identify textual markers of depression and depressiveness. For this purpose, a study of two corpora of texts was carried out using a linguistic analyzer developed at the Federal Research Center “Computer Science and Control” of the Russian Academy of Sciences (FRC CSC RAS). One corpus consisted of 557 essays written by patients with clinical depression ( N = 110) and healthy subjects ( N = 447), and the other was formed by 224 social media posts written by people with high (89) and low (135) scores of depressiveness on the Beck Depression Inventory (BDI). In total, data on 108 text parameters were obtained for both corpora. The authors identified textual features common and specific to the texts of the depressed patients and the texts of those with a high level of depressiveness according to the questionnaire data, and provided their psychological and linguistic interpretations. At the same time, not only lexical features were taken into account, but also grammatical ones (in the broad sense), such as parts of speech, morphemes, grammemes, locative, temporal and causal noun phrases, indicators of text segmentation and text coherence, etc. Based on the results of the analyses, three complex indicators of depression were proposed, including a number of specific psycholinguistic, linguistic and psychological markers. For the texts of the subjects with signs of depression according to the BDI, markers were selected from social media messages, which were combined into two complex indicators. They are proposed to be considered in mass surveys as indicators of dissatisfaction (hostility) rather than depression. The authors also discuss the theoretically and experimentally identified problem of identifying text markers of depression and formulate proposals on the methodology of using AI tools in network psychodiagnostics.
作者简介
Elena Nikitina
Federal Research Center “Computer Science and Control” of the Russian Academy of Sciences
Email: yelenon@mail.ru
ORCID iD: 0000-0002-6207-8693
SPIN 代码: 6989-9498
PhD in Philology, Senior Researcher
9 Ave. of the 60th Anniversary of October, 117321, Moscow, Russian FederationMaksim Stankevich
Federal Research Center “Computer Science and Control” of the Russian Academy of Sciences
Email: stankevich@isa.ru
ORCID iD: 0000-0003-0705-5832
SPIN 代码: 1916-7298
Junior Researcher
9 Ave. of the 60th Anniversary of October, 117321, Moscow, Russian FederationNatalia Chudova
Federal Research Center “Computer Science and Control” of the Russian Academy of Sciences
编辑信件的主要联系方式.
Email: nchudova@gmail.com
ORCID iD: 0000-0001-9306-1280
SPIN 代码: 3421-2959
PhD in Psychology, Senior Researcher
9 Ave. of the 60th Anniversary of October, 117321, Moscow, Russian Federation参考
- Devyatkin, D. (2019). Extraction of cognitive operations from scientific texts. Communications in Computer and Information Science, 1093, 189–200. https://doi.org/10.1007/978-3-030-30763-9_16
- Devyatkin, D., Chudova, N., Chuganskaya, A., & Sharypina, D. (2021). Methods for recognition of frustration-derived reactions on social media. Lecture Notes in Computer Science, 12948 LNAI, 17–30. https://doi.org/10.1007/978-3-030-86855-0_2
- Devyatkin, D., Enikolopov, S., Salimovsky, V., & Chudova, N. (2021). Speech reactions to frustration: automatic categorization. Psychological Studies, 14(78). (In Russ.). https://doi.org/10.54359/ps.v14i78.160
- Enikolopov, S., & Chudova, N. (2017). The problem of a hostile attitude. Psychological Studies, 10(54). (In Russ.). https://doi.org/10.54359/ps.v10i54.360
- Enikolopov, S.N., Kovalev, A.K., Kiznetsova, J.M., Chudova, N.V., & Starostina, E.V. (2019). Features of texts written by a frustrated person. Moscow University Psychology Bulletin, (3), 66–85. (In Russ.). http://doi.org/10.11621/vsp.2019.03.66
- Enikolopov, S.N., Kuznetsova, Y.M., Osipov, G.S., Smirnov, I.V., & Chudova, N.V. (2021). The method of relational-situational analysis of text in psychological research. Psychology. Journal of the Higher School of Economics, 18(4), 748–769. (In Russ.). http://doi.org/10.17323/1813-8918-2021-4-748-769
- Gong, Y., & Poellabauer, C. (2017). Topic modeling based multi-modal depression detection. In Proceedings of the 7th Annual Workshop on Audio/Visual emotion challenge (AVEC ‘17) (pp. 69–76). NY: Association for Computing Machinery. https://doi.org/10.1145/3133944.3133945
- Grigoriev, O., Kuznetsova, Y., Nikitina, E., Smirnov, I., & Chudova, N. (2022). Causative-Emotive Analysis. Part I. Emotional reactions of social networks users research. Psikhologicheskii Zhurnal, 43(3), 114–121. (In Russ.). https://doi.org/10.31857/S020595920020501-7
- Ignatiev, N., Smirnov, I. V., & Stankevich, M. (2022). Predicting depression with text, image, and profile data from social media. In Proceedings of the 11th International Conference on Pattern Recognition Applications and Methods - ICPRAM (pp. 753–760). SciTePress. https://doi.org/10.5220/0010986100003122
- Islam, M. R., Kabir, M. A., Ahmed, A., Kamal, A. R. M., Wang, H., & Ulhaq, A. (2018). Depression detection from social network data using machine learning techniques. Health Information Science and Systems, 6, 8. https://doi.org/10.1007/s13755-018-0046-0
- Kovalev, A.K., Kuznetsova, Y.M., Minin, A.N., Penkina, M.Y., Smirnov, I.V., Stankevich, M.A., & Chudova, N.V. (2019). Text analysis approach for identifying psychological characteristics (with aggressiveness as an example). Voprosy kiberbezopasnosti–Cybersecurity Issues, 4(32), 72–79 (in Russ.). https://doi.org/10.21681/2311-3456-2019-4-72-79
- Kuznetsova, Y.M. (2020). A trial of the thematic groups of words for text mining. In Security: Information, Technology, Behavior (pp. 28–36). St. Petersburg: “NATSRZAVITIE” Publ. (In Russ.). https://doi.org/10.37539/SITB294.2020.37.95.003
- Levin, K. (2001). Dynamic psychology: Selected works. Moscow: Smysl Publ. (In Russ.).
- Litvinova, T. A., & Litvinova, O. A. (2015). Identification and diagnosis of the personality of the author of a written text. Voronezh: Voronezh State Pedagogical University Publ. (In Russ.).
- Litvinova, T.A., Biryukova, E.D., & Zagorovskaya, O.V. (2021). Predicting gender, age and psychological characteristics of the author of a written text using corpus and computer linguistics methods: possibilities and limitations. Issues of Criminology, Criminalistics and Forensic Examination, (1), 105–111. (In Russ.).
- Moreno, J. D., Martinez-Huertas, J. A., Olmos, R., Jorge-Botana, G., & Botella, J. (2021). Can personality traits be measured analyzing written language? A meta-analytic study on computational methods. Personality and Individual Differences, 177, 110818. https://doi.org/10.1016/j.paid.2021.110818
- Nikitina, E.N., & Onipenko, N.K. (2019). A cognitive linguistic interpretation of statistical analysis results based on texts by persons with mental disorder. Artificial Intelligence and Decision Making, 1(3), 60–69. (In Russ.). https://doi.org/10.14357/20718594190307
- Nikitina, E.N., & Onipenko, N.K. (2022). On linguistic component in a psycholinguistic research (based on the material of psych verbs in texts by persons with mental disorders). Tomsk State University Journal of Philology (79), 109–130. (In Russ.) http://dx.doi.org/10.17223/19986645/79/6
- Orabi, A.H., Buddhitha, P., Orabi, M.H., & Inkpen, D. (2018, June). Deep learning for depression detection of twitter users. In Proceedings of the Fifth Workshop on Computational Linguistics and Clinical Psychology: From Keyboard to Clinic (pp. 88–97). New Orleans, LA.: Association for Computational Linguistics. https://doi.org/10.18653/v1/W18-0609
- Osipov, G.S., Smirnov, I.V., & Tikhomirov, I.A. (2008). Relational-situational method of search and analysis of texts and its applications. Artificial Intelligence and Decision Making, (2), 3–10 (In Russ.).
- Petraevskiy, V.A., & Kravets, A.G. (2024). The textual information intellectual analysis method for psychiatric diagnosis. Vestnik of Astrakhan State Technical University. Series: Management, Computer Science and Informatics, (2), 95–104. (In Russ.). https://doi.org/10.24143/2072-9502-2024-2-95-104
- Shalileh, S.A., Koptseva, A.O., Shishkovskaya, T.I., Khudyakova, M.V., & Dragoy, O.V. (2023). An explained artificial intelligence-based solution to identify depression severity symptoms using acoustic features. Doklady Rossiiskoj Akademii Nauk. Matematika, Informatika, Processy Upravleniya, 514(2), 242–249. (In Russ.) https://doi.org/10.31857/S26869543236009
- Smirnov, I. V. (2023). Intelligent text analysis based on multi-level natural language processing methods. Moscow: FRC CSC RAS. (In Russ.).
- Smirnov, I., Stankevich, M., Kuznetsova, Y., Suvorova, M., Larionov, D., Nikitina, E., & Grigoriev, O. (2021). TITANIS: A tool for intelligent text analysis in social media. Lecture Notes in Computer Science, 12948 LNAI, 232–247. https://doi.org/10.1007/978-3-030-86855-0_16
- Smirnov, I.V., Ushakova, A.V., & Chudova, N.V. (2020). Method for detecting text markers of depression and depressiveness. Lecture Notes in Computer Science, 12412 LNAI, 325–337. https://doi.org/10.1007/978-3-030-59535-7_24
- Solokhov, T.D., & Kochkarov A.A. (2024). Forecasting the depression with user data from Russian language social network. Modeling, Optimization and Information Technology, 12(2). (In Russ.). https://doi.org/10.26102/2310-6018/2024.45.2.016
- Stankevich, M.A., Kuznetsova, Y.M., Smirnov, I.V., Kiselnikova, N.V., & Enikolopov, S.N. (2019). Predicting depression from essays in Russian. Computational Linguistics and Intellectual Technologies, 18(25), 637–647.
- Tausczik, Y.R., & Pennebaker, J.W. (2010). The psychological meaning of words: LIWC and computerized text analysis methods. Journal of language and social psychology, 29(1), 24–54. https://doi.org/10.1177/0261927X09351676
- Zolotova, G.A. (1988). Syntactic dictionary: Repertoire of elementary units of Russian syntax. Moscow: Nauka Publ. (In Russ.)
补充文件

