Features of texts written by a frustrated person.

Relevance. The designing of tools to identify a psychological distress in network is one of the most significant challenges of the era of information technology. There are evidences of certain peculiarities of the speech and textual activity of frustrated person. However, for texts in Russian, any tool for monitoring of the intensity of frustration in online content does not currently exist. 

Objective. The purpose of our work is the listing of text features to carry out automatic analysis of the network content for detecting texts of frustrated users.

Methods. The material of the study is a set of posts and comments of 2-10 sentences collected in social networks LiveJournal, Pikabu and Facebook were written by 100 Russian-speaking users aged 27-64 years. The texts were divided as written by unexcited persons (500 texts) and by frustrated persons (500 texts). For automatic text analysis, the "RSA Machine" created in Federal Research Center "Computer Science and Control" of Russian Academy of Sciences was used, which allows to determine 197 text features, to compare texts, and to identify the most important dividing features. Mathematically, the texts were classified using the machine learning.

Results. The Random Forest method with a preliminary binarization procedure revealed the most significant features of text written by frustrated person: the sentiment; the frequency of punctuation, negative word forms and first-person pronouns; the number of semantic roles causative, liquidative and destructive; number of particles, invectives and words from the vocabulary of resistance.

Conclusions. Using the identified features the network texts written by frustrated person can be confidently determined; it is applicable for monitoring in order to ensure information and psychological security.

References

Arutyunova,N.D. (1987). Anomalii i yazyk: K probleme «yazykovoy kartiny mira» [Anomalies and language: To the problem of "linguistic picture of the world"]. Voprosy yazykoznaniya [Questions of linguistics], 3, 3—19.

Beatty, M.J., & McCroskey, J.C. (1997). It’s our nature: Verbal aggressiveness as temperamental expression. Communication Quarterly, 45, 4, 446—460. DOI: doi.org/10.1080/01463379709370076

Beigi, G., Hu, X., Maciejewski, R., & Liu, H. (2016). An Overview of Sentiment Analysis in Social Media and its Applications in Disaster Relief. In: Sentiment Analysis and Ontology Engineering (pp. 313—340). Switzerland: Springer. DOI: doi.org/10.1007/978-3-319-30319-2_13

Biggs, J. (2014). Study: Feelings On Facebook Spread From Friend To Friend. URL: https://techcrunch.com/2014/03/13/study-feelings-on-facebook-spread-from-friend-to-friend/

Bond, R.M., Fariss, C.J., Jones, J., et al. (2012). A 61-million-person experiment in social influence and political mobilization. Nature, 489, 295—298. DOI: doi.org/10.1038/nature11421

Brew, C. (2016). Classifying ReachOut posts with a radial basis function SVM. In: Proceedings of the 3rd Workshop on Computational Linguistics and Clinical Psychology: From Linguistic Signal to Clinical Reality (San Diego, CA, June 16)(pp. 138—132). DOI: doi.org/10.18653/v1/W16-0315

Brown, P.F., deSouza, P.V., et al. (1992). Class-based n-gram models of natural language. Computational Linguistics, 18, 4, 467—479.

Cacioppo, J.T., Fowler, J.H., & Christakis, N.A. (2009). Alone in the crowd: the structure and spread of loneliness in a large social network. Journal of Personality and Social Psychology, 97,6, 977. DOI: doi.org/10.1037/a0016076

Coppersmith, G., Dredze, M., Harman, C., et al. (2015). ClPsych 2015 shared task: depression and PTSD on twitter. In: Proceedings of the 2nd Workshop on Computational Linguistics and Clinical Psychology: From Linguistic Signal to Clinical Reality (Denver, Colorado, May 31—June 5, 2015), 31—39. DOI: doi.org/10.3115/v1/W15-1204

Coviello, L., Sohn, Y., Kramer, A., et al. (2014). Detecting Emotional Contagion in Massive Social Networks. PLOS ONE, 9, 3, 1—6. URL:  https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0090315(date of retrieval: 25.07.2019) DOI: doi.org/10.1371/journal.pone.0090315

Enikolopov,S.N., Kuznetsova,Yu.M., Smirnov,I.V.,et al. (2019). Sozdanie instrumenta avtomaticheskogo analiza teksta v interesakh sotsio-gumanitarnykh issledovaniy.Chast1: Metodicheskie i metodologicheskie aspekty [Creating a tool for automatic text analysis in the interests of socio-humanitarian research.Part 1: Methodical and Methodological Aspects].Iskusstvennyy intellekt i prinyatie resheniy[Artificial Intelligence and Decision Making], 2, 28—38.

Fersini, E., Pozzi, F.A., & Messina, E. Approval network: a novel approach for sentiment analysis in social networks. World Wide Web, 2016. DOI: doi.org/10.1007/s11280-016-0419-8 

Kharchenko,V.K., Koreneva,E.Yu. (2007). Yazyk frustratsii: M. Lermontov, M. Gorʹkiy, O. Ualʹd, S. Esenin [Language of frustration: M. Lermontov, M. Gorky, O. Wilde, S. Esenin]. Moscow: Izd-vo Literaturnogo instituta im. A.M. Gorʹkogo.

Khacheresova, L.M. (2011). Nekotorye aspekty yazyka frustratsii angliyskogo gazetnogo teksta [Some Aspects of the Frustration of English Newspaper Text]. Vestnik Pyatigorskogo gosudarstvennogo lingvisticheskogo universiteta[Bulletin of the Pyatigorsk State Linguistic University], 4, 115—117.

Kolchyna, O., Souza, T.T.P., Treleaven, P.C., & Aste, T. Twitter Sentiment Analysis: Lexicon Method, Machine Learning Method and Their Combination, 2016. URL: https://arxiv.org/pdf/1507.00955.pdf

Kolyshkina,I.M.  (2011). Kontsept «Smertʹ» v kontseptosfere frustratsii (na primere proizvedeniy L. Andreeva) [The concept of “Death” in the concept-sphere of frustration (for example, the works of L. Andreev)].In E.A. Popova (Ed.), Funktsionalʹno-kommunikativnye i lingvokulʹturologicheskie aspekty izucheniya teksta i diskursa [Functional-communicative and linguocultural aspects of the study of text and discourse] (pp. 99—112). Lipetsk: LGPU. 

Komalova, L.R. (2013). Verbalʹnaya realizatsiya otvetnoy agressii v situatsii konflikta i frustratsii [Verbal realization of reciprocal aggression in a situation of conflict and frustration]. In E.M. Devyatkina (Es.), Problemy yazyka: vzglyad molodykh uchenykh. Sbornik nauchnykh statey po materialam Vtoroy konferentsii-shkoly[Problems of language: a view of young scientists.Collection of scientific articles based on the materials of the Second Conference-School] (pp. 187—198). Moscow: Institut yazykoznaniya RAN.

Kozhina, M.N. (2002). Rechevedenie i funktsionalʹnaya stilistika: voprosy teorii [Speech and Functional Stylistics: Theoretical Issues]. Permʹ: Izd-vo PGU; PSI; PSSGK. 

Kozlova, N.S. (2015). Vzaimosvyazʹ psikhicheskikh sostoyaniy i internet-aktivnosti lichnosti [The relationship of mental states and Internet activity of the individual]. Universum: psikhologiya i obrazovanie: ehlektronnyy nauchnyy zhurnal[Universum: psychology and education: electronic scientific journal], 8(18). URL: http://7universum.com/ru/psy/archive/item/2512 (date of retrieval: 25.07.2019)

Kuznetsova, Yu.M., Chudova, N.V. (2018a). Vyyavlenie tekstovykh pokazateley sostoyaniya frustratsii s pomoshchʹyu avtomaticheskogo relyatsionno-situatsionnogo analiza [Identification of textual indicators of the state of frustration using automatic relational-situational analysis]. In: B.S. Alishev, A.O. Prokhorov, A.V. Chernov (Eds.), Psikhologiya sostoyaniy cheloveka: aktualʹnye teoreticheskie i prikladnye problemy: Materialy Tretʹey Mezhdunarodnoy nauchnoy konferentsii (Kazanʹ, 8—10 noyabrya 2018 g.)[Psychology of human condition: current theoretical and applied problems:Materials of the Third International Scientific Conference (Kazan, November 8–10, 2018)](pp. 279—282). Kazanʹ: Izd-vo Kazan. un-ta.

Kuznetsova, Yu.M., Chudova, N.V. (2018b). Semanticheskiy podkhod k setevoy diagnostike vrazhdebnosti [Semantic approach to network diagnosis of hostility]. Vestnik Moskovskogo gosudarstvennogo oblastnogo universiteta: ehlektronnyy zhurnal [Bulletin of the Moscow State Regional University: electronic journal], 4, 162—172. URL: https://evestnik-mgou.ru/ru/Articles/View/933 (date of retrieval: 25.07.2019)

Le, Q., Mikolov, T. (2014). Distributed representations of sentences and documents. The 31th International Conference on Machine Learning  (pp. 1188—1196).

Losada, D.E., Crestani, F., & Parapar, J. (2017). eRISK 2017: CLEF Lab on Early Risk Prediction on the Internet: Experimental Foundations. In: Jones G. et al. (eds.) Experimental IR Meets Multilinguality, Multimodality, and Interaction. CLEF 2017. Lecture Notes in Computer Science, vol. 10456. Springer, Cham. DOI: doi.org/10.1007/978-3-319-65813-1_30

Lozhkina,L.I. (2015). Frustratsiya ehmotsionalʹnogo vzaimodeystviya podrostkov v seti  [Frustrationoftheemotionalinteractionofteenagersinthenetwork]. Nauka-Rastudent.ru: ehlektronnyy nauchno-prakticheskiy zhurnal [Science-Rastudent.ru: electronicscientificjournal],7(19),27. URL: https://elibrary.ru/item.asp?id=23825302  (dateof retrieval: 25.07.2019)

Malmasi, S., Zampieri, M., & Dras, M. (2016).Predicting post severity in mental health forums. In: Proceedings of the 3rd Workshop on Computational Linguistics and Clinical Psychology (San Diego, CA, June 16)(pp. 133—137). DOI: doi.org/10.18653/v1/W16-0314

McKim, S., Wang, Y., et al. (2016). Data61-csiro systems at the clpsych 2016 shared task. In: Proceedings of the 3rd Workshop on Computational Linguistics and Clinical Psychology(San Diego, CA, June 16)(pp. 128—132). DOI: doi.org/10.18653/v1/W16-0313

Mikolov T., Yih W., & Zweig G. (2013). Linguistic regularities in continuous space word representations. Proceedings of NAACL-HLT 2013, Atlanta, Georgia, 9–14 June 2013, 13, 746—751.

Milne, D.N., Pink, G., et al. (2016). CLPsych 2016 shared task: Triaging content in online peer-support forums. In: Proceedings of the Third 3rd Workshop on Computational Linguistics and Clinical Psychology (San Diego, CA, June 16)(pp. 118—127). DOI: doi.org/10.18653/v1/W16-0312

Osipov,G.S., Smirnov,I.V., Tikhomirov,I.A. (2008). Relyatsionno-situatsionnyy metod poiska i analiza tekstov i ego prilozheniya [Relational situational method for searching and analyzing texts and its applications]. Iskusstvennyy intellekt i prinyatie resheniy[Artificial Intelligence and Decision Making], 2,3—10.

Pedersen, T. (2015). Screening Twitter users for depression and PTSD with lexical decision lists. In: Proceedings of the Workshop on Computational Linguistics and Clinical Psychology: From Linguistic Signal to Clinical Reality(pp. 46—53). URL: https://www.scilit.net/article/2b79fd2e82d4576617530b394ace825eDOI: doi.org/10.3115/v1/W15-1206

Pennebaker, J.W. (2011). The Secret Life of Pronouns. What Our Words Say About Us. N.Y.: Bloomsbury Press. DOI: doi.org/10.1016/S0262-4079(11)62167-2

Pennington, J., Socher, R., & Manning, C.D. (2014). GloVe: Global Vectors for Word Representation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, EMNLP.URL: https://nlp.stanford.edu/pubs/glove.pdfDOI: doi.org/10.3115/v1/D14-1162

Preoţiuc-Pietro, D., Sap, M., et al. Mental illness detection at the world well-being project for the clpsych 2015 shared task. In:Proceedings of the 2nd Workshop on Computational Linguistics and Clinical Psychology: From Linguistic Signal to Clinical Reality (Denver, Colorado, May 31—June 5, 2015)(pp. 40—45). DOI: doi.org/10.3115/v1/W15-1205

Resnik, P., Armstrong, W., et al. (2015). Beyond LDA: exploring supervised topic modeling for depression related language in twitter. In: Proceedings of the 2nd Workshop on Computational Linguistics and Clinical Psychology: From Linguistic Signal to Clinical Reality(Denver, Colorado, May 31—June 5, 2015) (pp. 99–107) DOI: doi.org/10.3115/v1/W15-1212

Rosenquist, J.N., Fowler, J.H., & Christakis, N.A. (2011). Social network determinants of depression. Molecular Psychiatry, 16, 273—281. DOI: doi.org/10.1038/mp.2010.13

Shmelyov,A.D. (2002). Russkaya yazykovaya modelʹ mira. Materialy k slovaryu [Russian language model of the world. Dictionary materials]. Moscow: Yazyki slavyanskoy kulʹtury. (Yazyk. Semiotika. Kulʹtura. Series Minor).

Vasilyuk, F.E. (1984). Psikhologiya perezhivaniya: Analiz preodoleniya kriticheskikh situatsiy [Psychology of experience: Analysis of coping with critical situations]. Moscow: MSU Press. 

Vaynshteyn, S.V., Smirnova, A.S. (2012). Frustratsiya igrovogo zhelaniya i motivatsiya uchastnikov mnogopolʹzovatelʹskikh kompʹyuternykh rolevykh igr: ehmpiricheskie osnovaniya dlya strategiy psikhologicheskogo konsulʹtirovaniya [Frustration of the game desire and motivation of participants in multiplayer computer role-playing games:]. Vestnik Permskogo universiteta. Filosofiya. Psikhologiya. Sotsiologiya [Bulletin of Perm University. Philosophy. Psychology. Sociology], 2, 121—133.

Vorontsova, O.Yu., Enikolopov, S.N., Kuznetsova, Yu.M. et al. (2018). Lingvisticheskie kharakteristiki tekstov psikhicheski bolʹnykh i zdorovykh lyudey [Linguistic characteristics of texts of mentally ill and healthy people]. Psikhologicheskie issledovaniya: ehlektronnyy nauchnyy zhurnal  [Psychological research: electronic scientific journal], 11, № 61. URL: http://psystudy.ru/index.php/num/2018v11n61/1622-enikolopov61.html (date of retrieval: 25.07.2019)

Yang, H., Willis, A., de Roeck A., & Nuseibeh B. (2012). A Hybrid Model for Automatic Emotion Recognition in Suicide Notes. Biomedical Informatics Insights, 5, 1, 17—30. DOI: doi.org/10.4137/BII.S8948

Yu, C. (2011). The display of frustration in arguments: A multimodal analysis. Journal of Pragmatics, 43, 2964—2981. DOI: doi.org/10.1016/j.pragma.2011.03.007

Zharkikh,N.G. (2009). Kommunikativnaya kompetentnostʹ studentov v situatsiyakh frustratsii [Communicative competence of students in situations of frustration]. Izvestiya RGPU im. A.I. Gertsena[Proceedings of the Russian State Pedagogical University named after A.I. Herzen],109,170—175.

Zolotova, G.A., Onipenko, N.K., Sidorova, M.Yu. (2004). Kommunikativnaya grammatika russkogo yazyka [Communicative grammar of the Russian language] / Ed. by G.A. Zolotova. Moscow: Nauka.