What Makes a Good Team? A Large-scale Study on the Effect of Team Composition in Honor of Kings

Abstract

Team composition is a central factor in determining the effectiveness of a team. In this paper, we present a large-scale study on the effect of team composition on multiple measures of team effectiveness. We use a dataset from the largest multiplayer online battle arena (MOBA) game, Honor of Kings, with 96 million matches involving 100 million players. We measure team effectiveness based on team performance (whether a team is going to win), team tenacity (whether a team is going to surrender), and team rapport (whether a team uses abusive language). Our results confirm the importance of team diversity and show that diversity has varying effects on team effectiveness: although diverse teams perform well and show tenacity in adversity, they are more likely to abuse when losing than less diverse teams. Our study also contributes to the situation vs. personality debate and show that abusive players tend to choose the leading role and players do not become more abusive when taking such roles. We further demonstrate the predictive power of features based on team composition in prediction experiments. 1 CCS CONCEPTS• Applied computing → Law, social and behavioral sciences.

Quantifying the Causal Effects of Conversational Tendencies

“…At a high level, Kendall's tau compares the rankings of counselors according to B and according to Y by capturing 11 In support forum settings, Choudhury and Kıcıman [14] and Saha and Sharma [55] similarly examine the causal effects of linguistic behaviors on outcomes such as the risk of suicidal ideation; the techniques they employ can be seen as controling for circumstance using observable attributes, which we contrast with our use of observed selection variables in Section 3.1. 12 We measure a counselor's speed in a conversation as the number of words they write, per minute taken to reply to a texter. Following Althoff et al [1], we measure sentiment as the VADER compound score of each message [25] and similarity as the cosine similarity between a counselor's message and the texter's preceding message; we obtain conversation-level measures of response length, sentiment and similarity by averaging over the counselor's messages in a conversation.…”

Predicting Individual Treatment Effects of Large-scale Team Competitions in a Ride-sharing Economy

“…Team competition. Team competitions have been increasingly applied in online communities, such as crowdsourcing [27], education [28], online games [11], and charitable giving [10]. It has been shown that team competitions are effective in improving key metrics, such as participation [28].…”

“…The former usually estimate the treatment effect at the experiment Figure 1: Workflow and Treatment Effect of a Team Contest level, averaged over all treated teams and participants (e.g., [10,27,28]). Studies of the latter have examined team-level properties and their influences on team performance in online games, such as the positive factor of diverse team composition [11]. To the best of our knowledge, few have aimed to analyze and predict the heterogeneous effect of team competitions on individual team members, especially in the context of the sharing economy.…”

“…Team structures and interrelations between members are also predictive. In social network and organization literature, there are theoretical and empirical discussions about how structural properties affect the functionality of a team or community (e.g., [7,11]). Our analysis provides empirical evidence (in the context of the sharing economy) to these theories while also reveals novel findings.…”

Learning from Team and Group Diversity: Nurturing and Benefiting from our Heterogeneity

“…Among multiple complicating factors, the research literature has examined the positive and negative contributions of team diversity to documents [49] and to many other forms of collective production, including WikiProject Film community articles [37], team performance in a large-scale online game [7] or decision-making [42], laboratory tasks of mapnavigation [12], laboratory studies of brainstorming [51], team performance [41,50], individual performance in a team setting [15], self-reports via surveys [10], and senior-executive ratings [10]. Some of these tasks were consequential for participantse.g., [20,21,22,41,49,50], while other tasks were laboratory exercises for people who had no stake in the outcomes [12,51].…”