SYSTEMS PSYCHOLOGY
AND SOCIOLOGY

    Views: 899

A SYSTEMATIC ORGANIZATION OF PSYCHOLOGICAL WORK WITH STUDENTS ON THE BASIS OF PSYCHOLINGUISTIC ANALYSIS OF WRITTEN SPEECH

B.М. Abushkin, 

А.V. Meshchankin

     MCU, Moscow,

N. S. Mertsalova,

NMRC for cardiology of the Ministry of Health of Russia, Moscow

The article deals with a new approach for the system organization of adaptive personal diagnosis and active dialogue with a teenager, aimed at the awareness and development of their personal qualities, as well as social interests and opportunities.

Modern diagnostic practice in the educational sphere uses almost all methodological developments of psychology. The variety of techniques is determined by their measuring characteristics. Many of them date back to the middle of the last century and earlier.

The problem of the system organization of psychologists ' work in solving modern problems of diagnostic work at the school is caused by the disparity in the use of scientific and conceptual apparatus, and in the interpretation of the results, limited to certain aspects of personal portrait. The system approach, typical for the modern stage of building practical work in psychology, involves working with students from the system-formed qualities of the emerging personality.

The proposed approach for the organization of adaptive work with students, taking into account the modern computing capabilities of computers and information technology allows us to enter into a system analysis and forecast on individual aspects of the development of students

To solve this problem, a tool for psycholinguistic analysis of written speech of adolescents was chosen to study the characteristics of the emotional sphere of adolescents.  The paper proposes a method for finding the correlation of cognitive characteristics of a person and his writing based on modern methods of distributive semantics. When developing the methodology, work was done to substantiate a set of basic emotions and on their basis, the subjects were marked with pre-selected adjectives of the Russian language, and the statistics on the proposed adjectives were collected. Further, on the basis of methods of distributive semantics, the generalization of the basic emotions of adjectives into other adjectives of the Russian language obtained in the experiment was carried out. A selection of text and images was developed, the validation of which took place on the control group of 200 people. The collection consisted of 18 text cards and 18 pictures describing the situation of a person's life, which should excite a particular basic emotion. with instructions to the subject-to give a free written response to the proposed text.

On the basis of the control sample of adolescents with known professional prospects, a neural network was trained, which puts professional perspectives in accordance with the emotional portrait and adaptively adapts to all new changes in the future. The first results allowing to judge the validity of the whole software complex are obtained.

Key words: psycholinguistics; basic emotions; distributive semantics; cognitive abilities of the brain; written speech; text analysis.

For citation: Abushkin B. M., Meshchankin A. V., Mertsalova N. S.The systematic organization of psychological work with the students on the basis of psycholinguistic analysis of written speech // Systems Psychology and sociology. 2019. № 1 (29). P. 68-74

References

1. Osin E. N. Measurement of positive and negative emotions: development of a Russian-language analogue of PANAS methodology, Psychology // Journal of Higher school of Economics. 2012. V. 9. № 4. P. 91–110.

2. Romanova E. S. Professional formation and development from the standpoint of the dual approach // Systems psychology and sociology. 2010. V. № 1. P. 43–56.

3. Ryzhov B. N. System psychology: methodology and methods of psychological research. M.: Moscow state pedagogical University, 1999. 277 p.

4. Consoli D. Emotions that influence purchase decisions and their electronic processing // Annales Universitatis Apulensis Series Oeconomica. 2009. № 2 (11). P. 1–45.

5. Ekman P. and et. al. Universals and cultural differences in the judgments of facial expressions of emotion //Journal of personality and social psychology. 1987. V. 53. № 4. С. 712–717.

6. Felbo B. and et al. Using millions of emoji occurrences to learn any-domain representations for detecting sentiment, emotion and sarcasm. URL: https://arxiv.org/pdf/1708.00524.pdf

7. Curran J. R. From distributional to semantic similarity: Ph.D. thesis. Edinburgh: University of Edinburg, 2003. 177 p.

8. Lee L. Similarity-based approaches to natural language processing: Ph.D. thesis. USA: Harvard University, 1997. 63 p.

9. Lindquist K. A., Wager T., Kober H., Bliss-Moreau E., Barrett L. The brain basis of emotion: A meta-analytic review // Behevioral and brain sciences. 2012. V. 35. P. 121–202.

10. Mohammad S. M. Sentiment analysis: Detecting valence, emotions, and other affectual states from text // Emotion measurement. 2016. P. 201–237.

11. Mohammad S., Turney P. Emotions Evoked by Common Words and Phrases: Using Mechanical Turk to Create an Emotion Lexicon // Proceedings of the NAACL HLT 2010. Workshop on Computational Approaches to Analysis and Generation of Emotion in Text. 2010. Los Angeles, California. June 2010. P. 26– 34.

12. Ortony A., Turner T. What’s Basic About Basic Emotions? // Psychological Review. 1990. V. 97. № 3. P. 315–331.

13. Pelevina M., Arefyev N., Biemann C., Panchenko A. Making Sense of Word Embeddings // In Proceedings of the 1st Workshop on Representation Learning for NLP co-located with the ACL conference. Berlin, Germany. Association for Computational Linguistics. 2016. P 174–183.

14. Pennington J., Socher R., Manning C. Glove: Global vectors for word representation // Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP). 2014. P. 1532–1543.

15. Strapparava C., Valitutti A., Stock O. The Affective Weight of Lexicon // Proceedings of LREC, 2006. P. 423–426.

16. Turney P., Pantel. P. From Frequency to Meaning: Vector Space Models of Semantics // Journal of Artificial Intelligence Research. 2010. V. 37. P. 141–188.

17. Wood I., Ruder S. Emoji as emotion tags for tweets // Proceedings of the Emotion and Sentiment Analysis Workshop LREC2016. Portorož, Slovenia. 2016. P. 76–79.