In this demo paper, we present Parallel OPM. Informed by research on player needs of AI in educational games [1], it is a new visualization system that uses play community data from other players to help players compare and reflect on their gameplay with their peers in the game Parallel [2]. In this demo paper/session: participants will (i) have the opportunity to play a level in the game Parallel [2] (ii) Use the guided reflection system to analyze and reflect on their gameplay compared to their peers.

Algorithmic fairness is an essential requirement as AI becomes integrated in society. In the case of social applications where AI distributes resources, algorithms often must make decisions that will benefit a subset of users, sometimes repeatedly or exclusively, while attempting to maximize specific outcomes. How should we design such systems to serve users more fairly? This paper explores this question in the case where a group of users works toward a shared goal in a social exergame called Step Heroes. We identify adverse outcomes in traditional multi-armed bandits (MABs) and formalize the Greedy Bandit Problem. We then propose a solution based on a new type of fairness-aware multi-armed bandit, Shapley Bandits. It uses the Shapley Value for increasing overall player participation and intervention adherence rather than the maximization of total group output, which is traditionally achieved by favoring only high-performing participants. We evaluate our approach via a user study (n=46). Our results indicate that our Shapley Bandits effectively mediates the Greedy Bandit Problem and achieves better user retention and motivation across the participants.

This paper recognizes idle games as a promising direction for exergames and other games designed for behavioral change. Based on a survey of 11 popular idle games, we extend existing literature by identifying the common core gameplay loop (active participation, inactive progress, and return reward) as well as the design patters used to support the loop. Furthermore, we propose an initial approach to extending idle game patterns to social exergames, focusing on improving player adherence.