Survey of synthetic respondents: new opportunities or threats to data reliability?

Authors

  • Elena E. Kuchko Belarusian State University, 4 Niezaliezhnasci Avenue, Minsk 220030, Belarus
  • Margarita V. Vishnyakova Belarusian State University, 4 Niezaliezhnasci Avenue, Minsk 220030, Belarus , Giprosvyaz, 24 Surganava Street, Minsk 220012, Belarus
  • Yana I. Marchuk Giprosvyaz, 24 Surganava Street, Minsk 220012, Belarus

Keywords:

large language model, artificial intelligence, synthetic respondent, sociological research, machine learning

Abstract

The article explores the main applications of artificial intelligence models in the professional work of sociologists. Particular attention is paid to the use of large language models and their role in generating responses from synthetic respondents. It is noted that the use of synthetic respondents allows for faster research, access to hard-to-reach groups, and the elimination of the interviewer effect. At the same time, methodological limitations are emphasised, including the inability to account for emotional reactions, the reduction of social context, and the low quality of training of large language models caused by the unavailability of training datasets.

Author Biographies

  • Elena E. Kuchko, Belarusian State University, 4 Niezaliezhnasci Avenue, Minsk 220030, Belarus

    doctor of science (sociology), full professor; professor at the department of sociology, faculty of philosophy and social sciences

  • Margarita V. Vishnyakova, Belarusian State University, 4 Niezaliezhnasci Avenue, Minsk 220030, Belarus, Giprosvyaz, 24 Surganava Street, Minsk 220012, Belarus

    PhD (sociology); associate professor at the department of sociology, faculty of philosophy and social sciences, Belarusian State University, and head of the department of analysis and development forecast, Centre for Advanced Research in Digital Development, Giprosvyaz

  • Yana I. Marchuk, Giprosvyaz, 24 Surganava Street, Minsk 220012, Belarus

    specialist at the department of digital technologies, Centre for Advanced Research in Digital Development

References

  1. Фомина ЕЕ. Применение аппарата нейронных сетей для анализа результатов анкетирования. Вестник Пермского национального исследовательского политехнического университета. Социально-экономические науки. 2020;2:99–110. DOI: 10.15593/2224-9354/2020.2.8.
  2. Круглов ВВ, Дли МИ. Применение аппарата нейронных сетей для анализа социологических данных. Социологические исследования. 2001;9:112–114.
  3. Котов Д. Алгоритмы искусственного интеллекта в прикладных социологических исследованиях. Социодиггер [Интернет]. 2023 [процитировано 24 июня 2025 г.];4(7–8). Доступно по: https://sociodigger.ru/articles/articles-page/algoritmy-iskusstvennogo-intellekta-v-prikladnykh-sociologicheskikh-issledovanijakh#_ftn1.
  4. Ашихмин ЕГ, Левченко ВВ, Селеткова ГИ. Опыт применения больших языковых моделей для анализа количественных социологических данных. Вестник университета. 2024;11:205–215. DOI: 10.26425/1816-4277-2024-11-205-215.
  5. Ашихмин ЕГ, Левченко ВВ, Селеткова ГИ. Опыт применения больших языковых моделей для анализа социологических данных, полученных в результате интервью о восприятии студентами предпринимательской деятельности. Цифровая социология. 2024;3:4–14. DOI: 10.26425/2658-347X-2024-7-3-4-14.
  6. Драч ВЕ, Торкунова ЮВ. Использование генеративного искусственного интеллекта для социологических исследований. Дискурс. 2025;11(1):52–70. DOI: 10.32603/2412-8562-2025-11-1-52-70.
  7. Shrestha P, Dario K, Koaik F, Schnider R, Sayess D, Binbaz MS. Can synthetic survey participants substitute for humans in global policy research? Behavioral Science & Policy. 2025;2:26–45. DOI: 10.1177/23794607241311793.
  8. Филипова АГ, Абросимова ЕЕ, Зубова ОГ. Метод синтетических фокус-групп в контексте цифровой трансформации социологических исследований. Социодинамика. 2025;5:1–17. DOI: 10.25136/2409-7144.2025.5.74430.

Downloads

Published

2026-04-22

Issue

No. 3 (2025): Journal of the Belarusian State University. Sociology

Section

To Know so that to Foresee...

License

Copyright (c) 2026 Journal of the Belarusian State University. Sociology

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

The authors who are published in this journal agree to the following:

  1. The authors retain copyright on the work and provide the journal with the right of first publication of the work on condition of license Creative Commons Attribution-NonCommercial. 4.0 International (CC BY-NC 4.0).
  2. The authors retain the right to enter into certain contractual agreements relating to the non-exclusive distribution of the published version of the work (e.g. post it on the institutional repository, publication in the book), with the reference to its original publication in this journal.
  3. The authors have the right to post their work on the Internet (e.g. on the institutional store or personal website) prior to and during the review process, conducted by the journal, as this may lead to a productive discussion and a large number of references to this work. (See The Effect of Open Access.)

How to Cite

[1]
Kuchko, E.E. et al. 2026. Survey of synthetic respondents: new opportunities or threats to data reliability?. Journal of the Belarusian State University. Sociology. 3 (Apr. 2026), 31–35. DOI:https://doi.org/10.33581/2521-6821-2025-3-%p.