Julian Frommel

Julian Frommel, Regan L Mandryk

Methods that detect user states such as emotions are useful for interactive systems. In this position paper, we argue for model-based approaches that are trained on user behaviour and self-reported user state as ground truths. In an application context, they record behaviour, extract relevant features, and use the models to predict user states. We describe how this approach can be implemented and discuss its benefits in comparison to solely self-reports in an application and to models of behaviour without the selfreport ground truths. Finally, we discuss shortcomings of this approach by considering its drawbacks and limitations.

Julian Frommel, Valentin Sagl, Ansgar E. Depping et al.

Online social interactions in multiplayer games can be supportive and positive or toxic and harmful; however, few methods can easily assess interpersonal interaction quality in games. We use behavioural traces to predict affiliation between dyadic strangers, facilitated through their social interactions in an online gaming setting. We collected audio, video, in-game, and self-report data from 23 dyads, extracted 75 features, trained Random Forest and Support Vector Machine models, and evaluated their performance predicting binary (high/low) as well as continuous affiliation toward a partner. The models can predict both binary and continuous affiliation with up to 79.1% accuracy (F1) and 20.1% explained variance (R2) on unseen data, with features based on verbal communication demonstrating the highest potential. Our findings can inform the design of multiplayer games and game communities, and guide the development of systems for matchmaking and mitigating toxic behaviour in online games.