Generative ai and sociology: analyzing virtual respondent technology
Research Article
Acknowledgments
The article was prepared within the framework of the RUDN University Research Institute 100939-0-000 “Application of artificial intelligence technologies in sociological research: practice and prospects”.
How to Cite
Puzanova Z.V., Koshoridze G.G., Koshoridze D.G. Generative ai and sociology: analyzing virtual respondent technology. Sociology: methodology, methods, mathematical modeling (Sociology: 4M). 2025. No. 60. P. 216-246. DOI: https://doi.org/10.19181/4m.2025.34.1.6 (in Russ.).
Abstract
The article analyzes the use of virtual respondents and large language models (LLM) in sociological research, including a review of domestic and foreign examples. The technical aspects of survey simulation with the help of LLM, including the choice of models, as well as practical recommendations for their application are considered. The advantages of this technology, such as the possibility of rapid data collection and adaptability, as well as disadvantages, including ethical risks and limitations in representativeness, are analyzed. Based on two pilot studies, it is found that to improve the effectiveness of the virtual respondent, it is recommended to first conduct a pilot survey with real participants, upload the results to the LLM and create a generalized virtual respondent trained on real responses to generate more reliable responses to the questions of interest.
Keywords:
virtual respondents, large language models, survey simulation, empirical research, representativeness, artificial intelligence, neural network
References
1. Using AI for Political Polling, ASH Centrer [site]. 07.06.2024. URL: https://ash.harvard.edu/articles/using-ai-for-political-polling/ (date of access: 29.07.2025).
2. Puzanova Zh.V., Tertyshnikova A.G., Pavlova U.O. Technological Discourse in the Russian Media: Main Strategies for Representing Artificial Intelligence (in Russian), RUDN Journal of Sociology. 2024, vol. 24, no. 3, p. 747-763. DOI: 10.22363/2313-2272-2024-24-3-747-763.
3. Artificial intelligence in sociology (in Russian), SocioLogos [site]. 23.09.2024. URL: https://sociologos.ru/blog/iskusstvennyy-intellekt-v-sotsiologii/ (date of access: 29.07.2025).
4. AI pollsters are here and here’s how they performed in the US election, IndiaAI [site]. URL: https://indiaai.gov.in/article/ai-pollsters-are-here-and-here-s-how-they-performed-in-the-us-election (date of access: 29.07.2025).
5. AI-generated survey responses could make research less accurate – and a lot less interesting, Stanford Report [site]. 21.11.2024. URL: https://news.stanford.edu/stories/2024/11/ai-generated-survey-responses-could-make-research-less-accurate-lot-less-interesting (date of access: 29.07.2025).
6. Bisbee J., Clinton J. D., Dorff C., Kenkel B., Larson J.M. Synthetic Replacements for Human Survey Data? The Perils of Large Language Models, Political Analysis, 2024, vol. 32, no. 4, p. 401-416. DOI: 10.1017/pan.2024.5.
7. Horton J.J. Large Language Models As Simulated Economic Agents: What Can We Learn from homo Silicus? National Bureau of Economic Research, 2023, no. w31122.
8. Artificial Intelligence in Social Research (in Russian), HSE [site]. URL: https://www.hse.ru/edu/dpo/905478596 (date of access: 29.07.2025).
9. Kniazhevich N., Dey E., Popina E. AI-Fueled Stock Rally Dealt $1 Trillion Blow by Chinese Upstart DeepSeek, Bloomberg [site]. 27.01.2025. URL: https://www.bloomberg.com/news/articles/2025-01-27/nasdaq-futures-slump-as-china-s-deepseek-sparks-us-tech-concern (date of access: 29.07.2025).
10. World Bank Open Data. World Development Indicators: Internet Users (% of Population), World Bank Group [site]. URL: https://data.worldbank.org (date of access: 29.07.2025).
11. Santurkar S., Durmus E., Ladhak F., Lee C., Liang P., Hashimoto T. Whose Opinions Do Language Models Reflect? Proceedings of the 40th International Conference on Machine Learning, PMLR, 2023, p. 29971-30004.
2. Puzanova Zh.V., Tertyshnikova A.G., Pavlova U.O. Technological Discourse in the Russian Media: Main Strategies for Representing Artificial Intelligence (in Russian), RUDN Journal of Sociology. 2024, vol. 24, no. 3, p. 747-763. DOI: 10.22363/2313-2272-2024-24-3-747-763.
3. Artificial intelligence in sociology (in Russian), SocioLogos [site]. 23.09.2024. URL: https://sociologos.ru/blog/iskusstvennyy-intellekt-v-sotsiologii/ (date of access: 29.07.2025).
4. AI pollsters are here and here’s how they performed in the US election, IndiaAI [site]. URL: https://indiaai.gov.in/article/ai-pollsters-are-here-and-here-s-how-they-performed-in-the-us-election (date of access: 29.07.2025).
5. AI-generated survey responses could make research less accurate – and a lot less interesting, Stanford Report [site]. 21.11.2024. URL: https://news.stanford.edu/stories/2024/11/ai-generated-survey-responses-could-make-research-less-accurate-lot-less-interesting (date of access: 29.07.2025).
6. Bisbee J., Clinton J. D., Dorff C., Kenkel B., Larson J.M. Synthetic Replacements for Human Survey Data? The Perils of Large Language Models, Political Analysis, 2024, vol. 32, no. 4, p. 401-416. DOI: 10.1017/pan.2024.5.
7. Horton J.J. Large Language Models As Simulated Economic Agents: What Can We Learn from homo Silicus? National Bureau of Economic Research, 2023, no. w31122.
8. Artificial Intelligence in Social Research (in Russian), HSE [site]. URL: https://www.hse.ru/edu/dpo/905478596 (date of access: 29.07.2025).
9. Kniazhevich N., Dey E., Popina E. AI-Fueled Stock Rally Dealt $1 Trillion Blow by Chinese Upstart DeepSeek, Bloomberg [site]. 27.01.2025. URL: https://www.bloomberg.com/news/articles/2025-01-27/nasdaq-futures-slump-as-china-s-deepseek-sparks-us-tech-concern (date of access: 29.07.2025).
10. World Bank Open Data. World Development Indicators: Internet Users (% of Population), World Bank Group [site]. URL: https://data.worldbank.org (date of access: 29.07.2025).
11. Santurkar S., Durmus E., Ladhak F., Lee C., Liang P., Hashimoto T. Whose Opinions Do Language Models Reflect? Proceedings of the 40th International Conference on Machine Learning, PMLR, 2023, p. 29971-30004.
Article
Received: 28.01.2025
Accepted: 20.08.2025
Citation Formats
Other cite formats:
APA
Puzanova, Z. V., Koshoridze, G. G., & Koshoridze, D. G. (2025). Generative ai and sociology: analyzing virtual respondent technology. Sociology: Methodology, Methods, Mathematical Modeling (Sociology: 4M), (60), 216-246. https://doi.org/10.19181/4m.2025.34.1.6
Section
MEASUREMENT IN SOCIOLOGY
JATS XML
