Artificial Intelligence Chatbots Mimic Human Collective Behaviour
Open accessAbstract
Artificial Intelligence (AI) chatbots, such as ChatGPT, have been shown to mimic individual human behaviour in a wide range of psychological and economic tasks. Do groups of AI chatbots also mimic collective behaviour? If so, artificial societies of AI chatbots may aid social-scientific research by simulating human collectives. To investigate this theoretical possibility, we focus on whether AI chatbots natively mimic one commonly observed collective behaviour: homophily, or people’s tendency to form community with similar others. In a large simulated online society of AI chatbots powered by large-language models (N = 24,443), we find that communities form over time around bots using a common language. In addition, among chatbots that predominantly use English (N = 16,003), communities emerge around bots that post similar content. The findings suggest that AI chatbots mimic homophily, a key aspect of human collective behaviour. Thus, in addition to simulating individual human behaviour, AI-powered artificial societies may advance social science research by allowing researchers to simulate nuanced aspects of collective behaviour.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Researchers have noted GPT's ability to help with computational social science tasks, detect misinformation, infer politicians' ideologies, write persuasive political arguments, respond to patient questions, simulate human research participants, and model collective behavior.
“Researchers have also recently noted GPT’s ability to help with computational social science tasks (49–54), detect misinformation (55), infer politicians’ ideologies (56), write persuasive political arguments (57), respond to patient questions (58), simulate human research participants (59–61), and model collective behavior (56).”
From GPT is an effective tool for multilingual psychological text analysis (2024) · cites this paper as [56]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Birds of a Feather: Homophily in Social Networks
McPherson, M., Smith-Lovin, L., & Cook, J. M. (2001) · Annual Review of Sociology · doi:10.1146/annurev.soc.27.1.415 · Cited by 18,567 · see citing works
The Proceedings of the National Academy of Sciences
Richards, J. W. (1915) · Science · doi:10.1126/science.42.1074.161 · Cited by 13,941 · see citing works
The weirdest people in the world?
Henrich, J., Heine, S. J., & Norenzayan, A. (2010) · Behavioral and Brain Sciences · doi:10.1017/s0140525x0999152x · Cited by 12,641 · see citing works
Finding community structure in very large networks
Clauset, A., Newman, M. E. J., & Moore, C. (2004) · Physical Review E · doi:10.1103/physreve.70.066111 · Cited by 7,390 · see citing works
Graph drawing by force‐directed placement
Fruchterman, T. M. J., & Reingold, E. M. (1991) · Software: Practice and Experience · doi:10.1002/spe.4380211102 · Cited by 6,352 · see citing works
Mathematical Methods of Statistics.
Geary, R. C., & Cramer, H. L. (1947) · The Economic Journal · doi:10.2307/2226151 · Cited by 6,095 · see citing works
Near linear time algorithm to detect community structures in large-scale networks
Raghavan, U. N., Albert, R., & Kumara, S. R. T. (2007) · Physical Review E · doi:10.1103/physreve.76.036106 · Cited by 3,535 · see citing works
Art and the science of generative AI
Epstein, Z., Hertzmann, A., the Investigators of Human Creativity, Akten, M., Farid, H., Fjeld, J., Frank, M. R., Groh, M., Herman, L., Leach, N., et al. (2023) · Science · doi:10.1126/science.adh4451 · Cited by 788 · see citing works
Himelboim, I., McCreery, S., & Smith, M. A. (2013) · J. Comput. Mediat. Commun. · doi:10.1111/jcc4.12001 · Cited by 547 · see citing works
Friendship prediction and homophily in social media
Aiello, L., Barrat, A., Schifanella, R., Cattuto, C., Markines, B., & Menczer, F. (2012) · TWEB · doi:10.1145/2180861.2180866 · Cited by 447 · see citing works
AI and the transformation of social science research
Grossmann, I., Feinberg, M., Parker, D. C., Christakis, N. A., Tetlock, P. E., & Cunningham, W. A. (2023) · Science · doi:10.1126/science.adi1778 · Cited by 377 · see citing works
Classifying Twitter Topic-Networks Using Social Network Analysis
Himelboim, I., Smith, M. A., Rainie, L., Shneiderman, B., & Espina, C. (2017) · Social Media + Society · doi:10.1177/2056305117691545 · Cited by 338 · see citing works
Beyond WEIRD: A review of the last decade and a look ahead to the global laboratory of the future
Apicella, C. L., Ara Norenzayan, A., & Henrich, J. (2020) · Evolution and Human Behavior · doi:10.1016/j.evolhumbehav.2020.07.015 · Cited by 282 · see citing works
Valente, T. W., & Pitts, S. (2016) · Annual Review of Public Health · doi:10.1146/annurev-publhealth-031816-044528 · Cited by 207 · see citing works
Changing times: Migrants’ social network analysis and the challenges of longitudinal research
Ryan, L., & D’Angelo, A. (2017) · Social Networks · doi:10.1016/j.socnet.2017.03.003 · Cited by 154 · see citing works
Playing repeated games with large language models
Akata, E., Schulz, L., Coda-Forno, J., Oh, S. J., Bethge, M., & Schulz, E. (2025) · Nature Human Behaviour · doi:10.1038/s41562-025-02172-y · Cited by 147 · see citing works
Semantic similarity from natural language and ontology analysis
Harispe, S., Ranwez, S., & Janaqi, S. (2015) · Cited by 136 · see citing works
GPT is an effective tool for multilingual psychological text analysisPreprint
Rathje, S., Mirea, D.-M., Sucholutsky, I., Marjieh, R., Robertson, C., & Bavel, J. J. V. (2023) · doi:10.31234/osf.io/sekf5 · Cited by 129 · see citing works
Self-citationSemantic Similarity from Natural Language and Ontology Analysis
Harispe, S., Ranwez, S., Janaqi, S., et al. (2015) · Synthesis lectures on human language technologies · doi:10.1007/978-3-031-02156-5 · Cited by 109 · see citing works
Social media behavior is associated with vaccine hesitancy
Rathje, S., He, J. K., Roozenbeek, J., Van Bavel, J. J., & van der Linden, S. (2022) · PNAS Nexus · doi:10.1093/pnasnexus/pgac207 · Cited by 100 · see citing works
Self-citationTitzmann, P. F., & Silbereisen, R. Κ. (2009) · Journal of Family Psychology · doi:10.1037/a0015493 · Cited by 98 · see citing works
Inducing anxiety in large language models increases exploration and biasPreprint
Coda-Forno, J., Witte, K., Jagadish, A. K., Binz, M., Akata, Z., & Schulz, E. (2023) · arXiv.org · doi:10.48550/arxiv.2304.11111 · Cited by 79 · see citing works
Veselovsky, V., Ribeiro, M. H., & West, R. (2023) · arXiv · doi:10.48550/arxiv.2306.07899 · Cited by 73 · see citing works
Immigrant Adolescents' Adaptation to a New Context: Ethnic Friendship Homophily and Its Predictors
Titzmann, P. F. (2014) · Child Development Perspectives · doi:10.1111/cdep.12072 · Cited by 65 · see citing works
Should large language models replace human participants?Preprint
Crockett, M. J., & Messeri, L. (2023) · doi:10.31234/osf.io/4zdx9 · Cited by 43 · see citing works
Bichler, G., & Malm, A. E. (2018) · Routledge eBooks · doi:10.4324/9780203431405-16 · Cited by 35 · see citing works
Flagged first, then by citations
Research works printed but not linked: 31
- Abar, S., Theodoropoulos, G. K., Lemarinier, P., & O'Hare, G. M. P. (2017). Agent Based Modelling and Simulation tools: A review of the state-of-art software. Computer Science Review , 24 , 13-33. https://doi.org/10.1016/j.cosrev.2017.03.001 · DOI
- Aher, G., Arriaga, R. I., & Kalai, A. T. (2022). Using large language models to simulate multiple humans. arXiv Preprint arXiv:2208.10264 . · arXiv
- Argyle, L. P., Busby, E. C., Fulda, N., Gubler, J. R., Rytting, C., & Wingate, D. (2023). Out of One, Many: Using language models to simulate human samples. Political Analysis , 31 (3), 337-351. https://doi.org/10.1017/pan.2023.2 · DOI · Paper page
- Atari, M., Xue, M. J., Park, P. S., Blasi, D., & Henrich, J. (2024). Which Humans? https://doi.org/10.31234/osf.io/5b26t · DOI · Paper page
- Baldassarri, D., & Abascal, M. (2017). Field experiments across the social sciences. Annual Review of Sociology , 43 (1), 41-73. https://doi.org/10.1146/annurev-soc-073014112445 · DOI
- Baumann, F., Lorenz-Spreen, P., Sokolov, I. M., & Starnini, M. (2020). Modeling Echo Chambers and Polarization Dynamics in Social Networks. Physical Review Letters , 124 (4), 048301. https://doi.org/10.1103/PhysRevLett.124.048301 · DOI · Paper page
- Bender, E. M., Gebru, T., McMillan-Major, A., & Shmitchell, S. (2021). On the Dangers of Stochastic Parrots: Can language models be too big? 🦜 . Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency , 610-623.
- Binz, M., & Schulz, E. (2023). Using cognitive psychology to understand GPT-3. Proceedings of the National Academy of Sciences , 120 (6), e2218523120.
- Cinelli, M., De Francisci Morales, G., Galeazzi, A., Quattrociocchi, W., & Starnini, M. (2021). The echo chamber effect on social media. Proceedings of the National Academy of Sciences , 118 (9), e2023301118. https://doi.org/10.1073/pnas.2023301118 · DOI · Paper page
- Cinelli, M., Quattrociocchi, W., Galeazzi, A., Valensise, C. M., Brugnoli, E., Schmidt, A. L., Zola, P., Zollo, F., & Scala, A. (2020). The COVID-19 social media infodemic. Scientific Reports , 10 (1), Article 1. https://doi.org/10.1038/s41598-020-73510-5 · DOI · Paper page
- Conover, M., Ratkiewicz, J., Francisco, M., Gonçalves, B., Menczer, F., & Flammini, A. (2011). Political polarization on twitter. Proceedings of the International Aaai Conference on Web and Social Media , 5 (1), 89-96.
- Dasgupta, I., Lampinen, A. K., Chan, S. C. Y., Sheahan, H. R., Creswell, A., Kumaran, D., McClelland, J. L., & Hill, F. (2023). Language models show human-like content effects on reasoning tasks (arXiv:2207.07051). arXiv. https://doi.org/10.48550/arXiv.2207.07051 · DOI · Paper page
- De Choudhury, M. (2011). Tie formation on twitter: Homophily and structure of egocentric networks. 2011 IEEE Third International Conference on Privacy, Security, Risk and Trust and 2011 IEEE Third International Conference on Social Computing , 465-470.
- Faralli, S., Stilo, G., & Velardi, P. (2015). Large scale homophily analysis in twitter using a twixonomy. Twenty-Fourth International Joint Conference on Artificial Intelligence .
- Gao, C., Lan, X., Lu, Z., Mao, J., Piao, J., Wang, H., Jin, D., & Li, Y. (2023). S3: Socialnetwork Simulation System with Large Language Model-Empowered Agents (arXiv:2307.14984). arXiv. https://doi.org/10.48550/arXiv.2307.14984 · DOI · Paper page
- Geschke, D., Lorenz, J., & Holtz, P. (2019). The triple-filter bubble: Using agent-based modelling to test a meta-theoretical framework for the emergence of filter bubbles and echo chambers. British Journal of Social Psychology , 58 (1), 129-149. https://doi.org/10.1111/bjso.12286 · DOI
- Gumel, A. B., Iboi, E. A., Ngonghala, C. N., & Elbasha, E. H. (2021). A primer on using mathematics to understand COVID-19 dynamics: Modeling, analysis and simulations. Infectious Disease Modelling , 6 , 148-168. https://doi.org/10.1016/j.idm.2020.11.005 · DOI
- Kang, J. H., & Lerman, K. (2012). Using lists to measure homophily on twitter. AAAI Workshop on Intelligent Techniques for Web Personalization and Recommendation , 18 .
- Knoke, D., & Yang, S. (2019). Social network analysis . SAGE publications.
- Lazer, D. M. J., Pentland, A., Watts, D. J., Aral, S., Athey, S., Contractor, N., Freelon, D., Gonzalez-Bailon, S., King, G., Margetts, H., Nelson, A., Salganik, M. J., Strohmaier, M., Vespignani, A., & Wagner, C. (2020). Computational social science: Obstacles and opportunities. Science , 369 (6507), 1060-1062. https://doi.org/10.1126/science.aaz8170 · DOI · Paper page
- Li, N., Gao, C., Li, Y., & Liao, Q. (2023). Large Language Model-Empowered Agents for Simulating Macroeconomic Activities (arXiv:2310.10436). arXiv. https://doi.org/10.48550/arXiv.2310.10436 · DOI
- Li, Y., Zhang, Y., & Sun, L. (2023). MetaAgents: Simulating Interactions of Human Behaviors for LLM-based Task-oriented Coordination via Collaborative Generative Agents (arXiv:2310.06500). arXiv. https://doi.org/10.48550/arXiv.2310.06500 · DOI · Paper page
- Lotito, Q. F., Zanella, D., & Casari, P. (2021). Realistic aspects of simulation models for fake news epidemics over social networks. Future Internet , 13 (3), Article 3. https://doi.org/10.3390/fi13030076 · DOI
- McInnes, L., Healy, J., & Melville, J. (2018). Umap: Uniform manifold approximation and projection for dimension reduction. arXiv Preprint arXiv:1802.03426 . · arXiv
- Park, J. S., O'Brien, J., Cai, C. J., Morris, M. R., Liang, P., & Bernstein, M. S. (2023). Generative Agents: Interactive Simulacra of Human Behavior. Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology , 1-22. https://doi.org/10.1145/3586183.3606763 · DOI · Paper page
- Pastor-Galindo, J., Nespoli, P., & Ruipérez-Valiente, J. A. (2023). Generative Agent-Based Social Networks for Disinformation: Research Opportunities and Open Challenges (arXiv:2310.07545). arXiv. https://doi.org/10.48550/arXiv.2310.07545 · DOI
- Rathje, S., Van Bavel, J. J., & van der Linden, S. (2021). Out-group animosity drives engagement on social media. Proceedings of the National Academy of Sciences , 118 (26), e2024292118. https://doi.org/10.1073/pnas.2024292118 · DOI · Paper page
- Silva, P. C. L., Batista, P. V. C., Lima, H. S., Alves, M. A., Guimarães, F. G., & Silva, R. C. P. (2020). COVID-ABS: An agent-based model of COVID-19 epidemic to simulate health and economic effects of social distancing interventions. Chaos, Solitons & Fractals , 139 , 110088. https://doi.org/10.1016/j.chaos.2020.110088 · DOI
- Sunstein, C. R. (2019). Conformity . New York University Press. https://doi.org/10.18574/nyu/9781479896585.001.0001 · DOI · Paper page
- Wahlström, M., & Törnberg, A. (2021). Social Media Mechanisms for Right-Wing Political Violence in the 21st Century: Discursive Opportunities, Group Dynamics, and CoOrdination. Terrorism and Political Violence , 33 (4), 766-787. https://doi.org/10.1080/09546553.2019.1586676 · DOI
- Zhang, T., Tao, D., Qu, X., Zhang, X., Zeng, J., Zhu, H., & Zhu, H. (2020). Automated vehicle acceptance in China: Social influence and initial trust are key determinants. Transportation Research Part C: Emerging Technologies , 112 , 220-233. https://doi.org/10.1016/j.trc.2020.01.027 · DOI
Cited by
Sorted by citations
GPT is an effective tool for multilingual psychological text analysis
Rathje, S., Mirea, D.-M., Sucholutsky, I., Marjieh, R., Robertson, C. E., & Van Bavel, J. J. (2024) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2308950121 · Cited by 297 · see citing works
Self-citation
- Authors
- He, J., Wallis, F., Gvirtz, A., & Rathje, S.
- Affiliations
- University of Cambridge (GB)
- University College London (GB)
- King's College London (GB)
- New York University (US)
- Venue
- Research Square
- Published
- 2024-01-15
- OpenAlex
- W4390875237
- Cited by
- 4
- References
- 26
- Citations by year
- 2026: 1 · 2025: 1 · 2024: 2
- Type
- posted content
- Language
- en
- Open access
- green
- doi.org
- Locations
- Research Square (acceptedVersion, cc-by)
- Funders
- Sage Foundation
- Topics
- Physical Sciences › Physics and Astronomy › Statistical and Nonlinear Physics › Opinion Dynamics and Social Influence
- Social Sciences › Safety Research › Ethics and Social Impacts of AI
- Physical Sciences › Computer Science › Artificial Intelligence › Multi-Agent Systems and Negotiation
- Keywords
- AI chatbots, collective behavior, homophily, artificial societies, large language models, community formation, social simulation, ChatGPT, language similarity, content similarity
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
