Artificial Intelligence and Social Simulation: Studying Group Dynamics on a Massive Scale

Abstract

Recent advances in artificial intelligence and computer science can be used by social scientists in their study of groups and teams. Here, we explain how developments in machine learning and simulations with artificially intelligent agents can help group and team scholars to overcome two major problems they face when studying group dynamics. First, because empirical research on groups relies on manual coding, it is hard to study groups in large numbers (the scaling problem). Second, conventional statistical methods in behavioral science often fail to capture the nonlinear interaction dynamics occurring in small groups (the dynamics problem). Machine learning helps to address the scaling problem, as massive computing power can be harnessed to multiply manual codings of group interactions. Computer simulations with artificially intelligent agents help to address the dynamics problem by implementing social psychological theory in data-generating algorithms that allow for sophisticated statements and tests of theory. We describe an ongoing research project aimed at computational analysis of virtual software development teams.

AI and social theory

“…Collins has discussed the nature of prediction in his model and assessed various alternative predictions and explanations, but he argues that his 'model' fares better. Instead of going into whether Collins outpredicts these rival explanations, our main point here is that Collins' model has been tested by others using computational methods, including sometime collaborators (Hanemann 1987) but also others who build on and extend or improve upon his work (see e.g., Turchin 2019: 16-28) and use his ideas as part of more comprehensive-not just state-breakdown related-testing of theories using computational models. Collins' state breakdown model, as outlined in Fig.…”

“…Still, and this returns us to current limits, a major shortcoming of current AI-based models is that there is inadequate semanticisation. Both natural human language and formal mathematical language are used by social scientists to theorise, and both come with their own sets of strengths and weaknesses (Hanemann 1987). Formal language is more precise and facilitates automated symbol manipulation.…”

“…This observation is not new: already in 1994, Bainbridge et al argued that a strategic use of AI-systems can not only render existing social theories more rigorous, but also inspire new theories. Since then, much progress has been made, and, in more recent years, AI-based models have been used by social scientists to study individuals and groups (Hoey et al 2018), to develop theories of human behaviour (Edelmann et al 2020) as well as to evaluate results previously obtained by means of traditional statistical techniques (Di Franco and Santurro 2020). However, as Radford and Joseph (2020) point out, work in this area too often privileges AI-based models that perform well on narrowly defined technical parameters over models that are founded in a deeper understanding of the society under study.…”

Theoretical and Empirical Modeling of Identity and Sentiments in Collaborative Groups

“…Our initial investigations centered around attempts to characterize discussions on GitHub in terms of their social purposes (the description in this section is based on Hoey et al, 2018 and, where more details on methods and results can be found). We used the Interaction Process Analysis (IPA) categories of Bales (1950) as a standard classification scheme for human actions in a group.…”

The Effectiveness of Group Counseling Based on Islamic Value to Reduce The Late Behaviour of Students

“…Group dynamics is a study that describes the various forces that determine the behaviour of members and group behaviour that cause changes in the group to achieve common goals that have been set. Group dynamics are psychological relationships that take place together from group members, paying attention to human behaviour in small groups and the forces that exist in the group, the causes for the growth of these powers and their influence on individuals, groups and their environment (Hoey et al, 2018).…”