Anti-social behaviors with the label "toxicity" are commonly understood as inescapable when playing online games with strangers, particularly in multiplayer online battle arenas (MOBA). Prior work in understanding in-game toxicity has primarily focused on verbal communication methods such as voice and text chat, which we extend into non-verbal communication, such as pings, emotes, and map annotations. In a semi-structured interview study among ten players of popular MOBAs (League of Legends and DotA2), we explored players’ perspectives on perceived toxicity through nonverbal communication features and the consequences of that toxicity. Our results echo prior work that "toxicity" refers to an exceptionally broad domain of behaviors and discuss player perceptions that may contribute to its normalization. In regard to nonverbal communications, pings stand out as players’ primary nonverbal communication method, primarily as strategic communication but often also toxic pings, which players consider unique in their form and intensity of toxicity compared to verbal communications. We discuss design implications for MOBAs, particularly in the context of player perspectives on limiting communication exclusively to nonverbal communication.

In this paper we describe the intervention framework of ATLAS, an artificial socially intelligent agent that advises teams. The framework treats interventions as atomic components, and manages the lifecycle of each intervention through presentation, as well as followups to interventions. The key benefit of this framework is that it allows for rapid development of scenario-specific Interventions that leverage scenario-agnostic team models. The implementation of this framework is reported for three player teams in a Search and Rescue task simulated in Minecraft. Low competence teams advised by ATLAS improved more between first and second trials than those with a human advisor while the reverse was found for high competence. Four times as many interventions were proposed as were presented. 15 % of advice was withheld to avoid repetitive advice, excessive rate of advice, and needlessly advising high performing teams, while a Theory of Mind model and delay for confirmation mechanism filtered out other unnecessary advice.

In this paper, we propose a novel personalized decision support system that combines Theory of Mind (ToM) modeling and explainable Reinforcement Learning (XRL) to provide effective and interpretable interventions. Our method leverages DRL to provide expert action recommendations while incorporating ToM modeling to understand users' mental states and predict their future actions, enabling appropriate timing for intervention. To explain interventions, we use counterfactual explanations based on RL's feature importance and users' ToM model structure. Our proposed system generates accurate and personalized interventions that are easily interpretable by end-users. We demonstrate the effectiveness of our approach through a series of crowd-sourcing experiments in a simulated team decision-making task, where our system outperforms control baselines in terms of task performance. Our proposed approach is agnostic to task environment and RL model structure, therefore has the potential to be generalized to a wide range of applications.

Prior research has shown that gesture-based communication plays an integral role in online multiplayer games, especially for teams consisting of strangers with no prior common experiences. What motivates a particular form of in-game communication and its impact, especially promptly after a communication attempt, on team performance is less explored. In this paper, we present a framework for studying individual communication attempts using a gestured-based tool, "Ping", in a popular MOBA game, Heroes of the Storm. We design a framework to capture the game's situational context prior to the communication, the communication attempt, and its immediate impact. Using this framework, we analyze and identify game factors that influence players' decisions to communicate and their choice of communication. We also present how communication has an immediate positive effect on the team's performance. Our findings further the discussion of studying communication behaviors for virtual teams engaging in synchronous, collaborative work with shared visual spaces.