Theoretical and Empirical Modeling of Identity and Sentiments in Collaborative Groups

• Applicant: Professor Dr. Tobias Schröder
• Subject Area: Social Psychology, Industrial and Organisational Psychology ; Empirical Social Research
• Term: from 2017 to 2020
• Project identifier: Deutsche Forschungsgemeinschaft (DFG) - Project number 329048354

• Final Report Year: 2021

Final Report Abstract

THEMIS.COG was an interdisciplinary research collaboration of computer scientists and social scientists from the University of Waterloo (Canada), Potsdam University of Applied Sciences (Germany), and Dartmouth College (U.S.A.). Funded by the Transatlantic Partnership’s Digging Into Data initiative, the project aimed at theoretical and empirical modeling of identity and sentiments in collaborative groups. Understanding the social forces behind self-organized collaboration is important because technological and social innovations are increasingly generated through informal, distributed processes of collaboration, rather than in formal organizational hierarchies or through market forces. Our work used a data-driven approach to explore the social psychological mechanisms that motivate such collaborations and determine their success or failure. We focused on the example of GitHub, the world’s current largest digital platform for open, collaborative software development. In contrast to most, purely inductive contemporary approaches leveraging computational techniques for social science, THEMIS.COG followed a deductive, theory-driven approach. We capitalized on affect control theory, a mathematically formalized theory of symbolic interaction originated by sociologist David R. Heise and further advanced in previous work by some of the THEMIS.COG collaborators, among others. Affect control theory states that people control their social behaviours by intuitively attempting to verify culturally shared feelings about identities, social roles, and behaviour settings. From this principle, implemented in computational simulation models, precise predictions about group dynamics can be derived. It was the goal of THEMIS.COG to adapt and apply this approach to study the GitHub collaboration ecosystem through a symbolic interactionist lens. In many ways, the project was more challenging than we had anticipated. Specifically, current computational techniques for natural language processing and sentiment analysis did not allow us to match GitHub data to affect control theory models in the precise or even automatic ways we had aspired. Nevertheless, we were able to develop various novel theoretical and empirical computational approaches to the study of group collaboration. Among them were a classification of socio-emotional versus task-oriented group behaviours and other ways of extracting emotional information from group discussions, a demonstration of correlations between developer personality/identity and the likelihood to get code changes accepted, development of a typology of interaction patterns on GitHub, and various approaches to simulating group dynamics among software developers with affect control theory. THEMIS.COG thus contributed substantially to the novel endeavour of theory development in social science based on large amounts of naturally occurring digital data. Keywords: Computational Social Science, Group Dynamics, Software Development, Virtual Teams, GitHub, Identity, Affect Control Theory, Sentiment Analysis, Social Simulation

Publications

• (2018). Affective dynamics and control in group processes. Group Interaction Frontiers in Technology (GIFT’18), Boulder, CO, USA. ACM, New York, NY, USA
  Hoey, J., Schröder, T., Morgan, J. H., Rogers, K. B., & Nagappan, M.
  
• (2018). Artificial intelligence and social simulation: Studying group dynamics on a massive scale. Small Group Research, 49(6), 647-683
  Hoey, J., Schröder, T., Morgan, J. H., Rogers, K. B., Rishi, D., & Nagappan, M.
  
• (2019). Effects of personality traits on pull request acceptance. IEEE Transactions on Software Engineering
  Iyer, R. N., Yun, S. A., Nagappan, M., & Hoey, J.
  
• (2019). Relating values and social network structure. International Conference on Computational Social Science, Amsterdam
  Paryab, N., Sachs, A., Li, A., Nagappan, M., & Hoey, J.
  
• (2020), A topology of groups: What GitHub can tell us about online collaboration. Technological Forecasting and Social Change, 161, 12029
  Zöller, N., Morgan, J. H. & Schröder, T.
  
• (2020). When do word embeddings accurately reflect surveys on our beliefs about people? The 58th Annual Meeting of the Association for Computational Linguistics
  Kenneth, J., & Morgan, J. H.
  
• (2021). Denotative and connotative control of uncertainty: A Bayesian dual-process model. Judgment and Decision Making, 16(2), 505-550
  Hoey, J., MacKinnon, N. J., & Schröder. T.
  
• (2021). Modeling interaction in collaborative groups: Affect control within social structure. Journal of Artificial Societies and Social Simulation
  Zöller, N., Morgan, J. H. & Schröder, T.
  
• (2021). Modeling the culture of online collaborative groups with affect control theory. In P. Ahrweiler & M. Neumann (Eds.), Advances in Social Simulation (pp. 147-169). Springer Proceedings in Complexity
  Morgan, J. H., Zhao, J., Zöller, N., Sedlacek, A., Chen, L., Piper, H., Beck, Y., Rogers, K. B., Hoey, J., & Schröder, T.
  
• (2022). Modeling impression formation processes among Chinese and Americans. American Behavioral Scientist
  Zhao, J.