student from 01.01.2022 until now
Russian Federation
employee from 01.01.2016 until now
St. Petersburg, Russian Federation
employee from 01.01.2019 until now
Russian Federation
The study presents the development of a tool for intelligent analysis of passenger feedback on transport. Purpose: is to create an automated monitoring and semantic analysis system aimed at transforming unstructured user statements into structured data for managerial decision-making. Methods: modern information technologies were used, including natural language processing methods, machine learning, and integration of data from heterogeneous sources. Results: emphasize the effectiveness of the proposed text processing pipeline, which includes classification by transport mode and topic, sentiment analysis, and named entity recognition, for identifying key issues and public opinion trends. Practical significance: lies in increasing the responsiveness of transport regulators to passenger problems, optimizing service, and transitioning to data-driven management. The research is important for the development of digital technologies in the transport industry and improving the efficiency of passenger transportation management in the context of digital transformation.
data mining, natural language processing, Python, transport, passengers, sentiment, machine learning, media space
1. Cifrovye passazhirskie servisy: buduschee transporta obsudili na CIPRe // Associaciya «Cifrovoy transport i logistika». URL: http://www.dtla.ru/news/tsifrovye-passazhirskie-servisy-budushchee-transporta-obsudilinatsipre/ (data obrascheniya: 15.01.2026).
2. 80 % kompaniy transportnoy otrasli ispol'zuyut cifrovye tehnologii, no potencial rosta est' // Cifrovaya industriya promyshlennoy Rossii. URL: http://cipr.ru/news/80-kompanij-transportnoj-otrasli-ispolzuyut-czifrovyetehnologii- no-potenczial-rosta-est (data obrascheniya: 15.01.2026).
3. Analiz kommentariev v social'nyh setyah i messendzherah kak metod ocenki social'noy rezul'tativnosti cifrovyh gorodskih servisov / O. G. Filatova [i dr.] // International Journal of Open Information Technologies. 2024. T. 12, № 11. S. 103–110.
4. What do Riders Say and Where? The Detection and Analysis of Eyewitness Transit Tweets / O. Kabbani [et al.] // Journal of Intelligent Transportation Systems. 2023. Vol. 27, iss. 3. Pp. 347–363. DOI:https://doi.org/10.1080/15472450.2022.2026773
5. Lui Y., Li Y., Li W. A Natural Language Processing Approach for Appraisal of Passenger Satisfaction and Service Quality of Public Transportation // IET Intelligent Transport Systems. 2019. Vol. 13, iss. 11. Pp. 1701–1707. DOI: 10.1049/ iet-its.2019.0054
6. Maksyutin P. A., Shul'zhenko S. N. Obzor metodov klassifikacii tekstov s pomosch'yu mashinnogo obucheniya // Inzhenernyy vestnik Dona. 2022. № 12.
7. Zannat K. E., Choudhury C. F. Emerging Big Data Sources for Public Transport Planning: A Systematic Review on Current State of Art and Future Research Directions // Journal of the Indian Institute of Science. 2019. Vol. 99, iss. 4. Pp. 601–619. DOI:https://doi.org/10.1007/s41745-019-00125-9
8. Chowdhury S., Alzarrad A. Applications of Text Mining in the Transportation Infrastructure Sector: A Review // Information. 2023. Vol. 14, iss. 4. Art. 201. DOI:https://doi.org/10.3390/info14040201
9. Konovalova M. V. Kognitivnye aspekty verifikacii v internet-mediadiskurse // Lingvokul'turologiya. 2019. № 13. S. 125–131.
