Predicting conflict-prone disputes using the structure of turn-taking: the case of Wikipedia

ABSTRACT

Detection of conflict-prone discussions on online social platforms can help moderate debates and prevent negative social processes such as the formation of echo chambers or polarization of opinions. Here, we examined how controversy of a discussion topic can be estimated from formal characteristics of discussion threads on the English Wikipedia. We discovered that dyadic turn-taking patterns tended to convey highly emotional, personal content, disagreement, and words relating to the conflict. Using the fraction of such two-person patterns in the multi-person discussion as a predictor, we were able to classify effective and conflict-prone discussions with 80% accuracy. These results show that monitoring of turn-taking patterns may become one of the easy heuristics that help detect conflicts in task-oriented online groups.

KEYWORDS:

• turn-taking
• discussion threads
• conflict
• content analysis
• Wikipedia

Disclosure statement

No potential conflict of interest was reported by the author(s).

Notes

1 The data collection took place in October–November–December 2013; however, the rules and customs related to talk page discussions (specifically, related to conflict management and discussion layout) have not changed since then and thus we can expect similar effects of controversy on current talk pages (compare Wikipedia: Talk Page Guidelines (2021) and Wikipedia: Talk Page Guidelines (2013)).

2 The distribution of thread length variable was not normal.

Additional information

Funding

This work was supported by the Polish National Science Center [grant number 2018/31/D/HS6/00573] received by KZ.

Notes on contributors

Karolina Ziembowicz

Karolina Ziembowicz is an assistant professor at the Institute of Psychology, The Maria Grzegorzewska University, her scientific interests include the dynamics of social interaction, quantification of social emergence processes, as well as the influence of technology on human behavior.

Magdalena Roszczyńska-Kurasińska

Magda Roszczyńska-Kurasińska is a Ph.D., an economist, and psychologist at the Robert Zajonc Institute for Social Studies, University of Warsaw, her main research interests focus on the psychology of decision making, phenomena of trust, policy modeling, and behavioral economics. She studies the influence of social context on economic decisions.

Agnieszka Rychwalska

Agnieszka Rychwalska is an assistant professor at the Robert Zajonc Institute for Social Studies, University of Warsaw. She specializes in applications of complex systems theory to social sciences and neuroscience. In her approach, she uses complexity tools – networks, computer simulations and modeling of dynamical systems – to understand the specifics of social and psychological phenomena.

Andrzej Nowak

Andrzej Nowak is a professor at Psychology Departments at University of Warsaw, Poland and Florida Atlantic University, USA. His primary focus is the dynamical approach to social psychology, social influence, computer simulations of psychological and social processes, psychology and new technology, conflict, behavioral economy.