Список литературы

2518-1092

Research result. Information technologies

2518-1092

10.18413/2518-1092-2022-8-2-0-5

3145

ARTIFICIAL INTELLIGENCE AND DECISION MAKING

<strong>THE METHOD OF IDENTIFYING INDIRECT SIGNS OF CORRUPTION ACTS BASED ON VIDEO RECORDINGS OF SPEECHES OF CIVIL SERVANTS</strong>

Krainovskikh

Veronika Igorevna

Krainovskikh

Veronika Igorevna

vikraynova@edu.hse.ru

Komarova

Alyona Alekseevna

Komarova

Alyona Alekseevna

Basov

Oleg Olegovich

Basov

Oleg Olegovich

oobasov@mail.ru

Basov

Oleg Olegovich

Basov

Oleg Olegovich

oobasov@mail.ru

2023

8200

At the moment, the problem of countering corruption in the field of public service still does not lose its relevance. It is assumed that when committing acts of corruption, people show certain verbal and non-verbal signals, with the help of which it is possible to identify signs of corruption. The article deals with the problem of violation of anti-corruption legislation in state and municipal institutions from the point of view of the psycho-emotional state of officials. It is proposed to use machine learning methods to analyze video and audio recordings of speeches with unprepared speech of officials of various levels of government, where they answer questions from journalists and the public, in order to determine emotions and identify aggression, uncertainty, and evasiveness in answers. The results of the study may be useful for government agencies involved in the fight against corruption, as well as for the public interested in transparency and honesty of the activities of civil servants.

anti–corruptionpublic administrationmachine learningverbal analysisanalysis of audio-video recordingsanalysis of psycho-emotional state

Список литературы

Ovsyannikova V.V. On the question of the classification of emotions: categorical and multidimensional approaches // Financial analytics: problems and solutions. – 2013. – No. 37. – P. 43-48.

Rogov E.I. The handbook of a practical psychologist: a textbook //Moscow: VL. – 1998. – P. 134-142.

Samigullin T.R., Smirnov I.Z., Laushkina A.A. Determination of markers of aggressive human behavior based on the analysis of audio and text channels //Scientific result. Information technology. – 2022. – Vol. 7. – No. 2. – P. 55-62.

Bazarevsky V. et al. Blazeface: Sub-millisecond neural face detection on mobile gpus //arXiv preprint arXiv:1907.05047. – 2019.

Burkhardt F. et al. A database of German emotional speech // Interspeech. – 2005. – Т. 5. – P. 1517-1520.

Chow A., Louie J. Detecting lies via speech patterns. – 2017.

Devyatkin D. A. et al. Intelligent analysis of manifestations of verbal aggressiveness in network community texts //Scientific and Technical Information Processing. – 2014. – Т. 41. – P. 377-389.

Goupil L. et al. Listeners’ perceptions of the certainty and honesty of a speaker are associated with a common prosodic signature // Nature communication. – 2021. – Т. 12. – №. 1. – P. 861.

Gournay P., Lahaie O., Lefebvre R. A canadian french emotional speech dataset // Proceedings of the 9th ACM multimedia systems conference. – 2018. – P. 399-402.

Korobov M. Morphological analyzer and generator for Russian and Ukrainian languages // Analysis of Images, Social Networks and Texts: 4th International Conference, AIST 2015, Yekaterinburg, Russia, April 9–11, 2015, Revised Selected Papers 4. – Springer International Publishing, 2015. – P. 320-332.

Kossaifi J. et al. Sewa db: A rich database for audio-visual emotion and sentiment research in the wild // IEEE transactions on pattern analysis and machine intelligence. – 2019. – Т. 43. – №. 3. – P. 1022-1040.

Laushkina, Anastasia & Smirnov, Ivan & Medvedev, Anatoly & Laptev, Andrey & Sinko, Mikhail. (2022). Detecting incongruity in the expression of emotions in short videos based on a multimodal approach. Cybernetics and Physics. P. 210-216.

Luna-Jiménez C. et al. A Proposal for Multimodal Emotion Recognition Using Aural Transformers and Action Units on RAVDESS Dataset // Applied Sciences. 2021. – Vol. 12. – № 1. – P. 327.

Marcolla F., de Santiago R., Dazzi R. Novel Lie Speech Classification by using Voice Stress // Proceedings of the 12th International Conference on Agents and Artificial Intelligence. SCITEPRESS – Science and Technology Publications. – 2020. – P. 742–749.

McFee B. et al. librosa: Audio and music signal analysis in python //Proceedings of the 14th python in science conference. – 2015. – Т. 8. – P. 18-25.

Oviatt S. et al. (ed.). The Handbook of Multimodal-Multisensor Interfaces: Signal Processing, Architectures, and Detection of Emotion and Cognition-Volume 2. – Association for Computing Machinery and Morgan & Claypool, 2018.

S. Haq P.J.B.J. Multimodal Emotion Recognition / ed. Wang W. IGI Global, 2010. P. 398–423.

Saeed H. H., Shahzad K., Kamiran F. Overlapping toxic sentiment classification using deep neural architectures //2018 IEEE international conference on data mining workshops (ICDMW). – IEEE, 2018. – P. 1361-1366.

Sinko M. et al. Method of constructing and identifying predictive models of human behavior based on information models of non-verbal signals //Procedia Computer Science. – 2022. – Т. 212. – P. 171-180.

Tenney I., Das D., Pavlick E. BERT rediscovers the classical NLP pipeline // arXiv preprint arXiv:1905.05950. – 2019.

Tsai Y. H. H. et al. Learning factorized multimodal representations // arXiv preprint arXiv:1806.06176. – 2018.

Tsai Y. H. H. et al. Multimodal transformer for unaligned multimodal language sequences //Proceedings of the conference. Association for Computational Linguistics. Meeting. – NIH Public Access, 2019. – Т. 2019. – P. 6558.

Tzirakis P. et al. End-to-end multimodal emotion recognition using deep neural networks // IEEE Journal of selected topics in signal processing. – 2017. – Т. 11. – №. 8. – P. 1301-1309.

The IMF estimated the losses to the world economy from corruption [Electronic resource]. – URL: https://www.rbc.ru/economics/18/09/2017/59bfead89a794704d063c4f0 (date of application: 03.04.2023).

Brief description of the state of crime in the Russian Federation for January-June 2022. URL: https://xn--b1aew.xn--p1ai/reports/item/31209853 / (accessed 03.04.2023).

HSE has proposed using artificial intelligence to prevent corruption in the Russian Federation [Electronic resource]. – URL: https://tass.ru/ekonomika/14304599 (date of application: 03.04.2023).

Bert for Sequence Classification (Question vs Statement) [Electronic resource]. – URL: https://sparknlp.org/2021/11/04/bert_sequence_classifier_question_statement_en.html (accessed: 04/15/2023).