Optimizing a gamified design through reinforcement learning : a case study in stack overflow
Martin, Jonathan
Optimizing a gamified design through reinforcement learning : a case study in stack overflow - 1 archivo (358,4 kB)
Formato de archivo PDF. -- Este documento es producción intelectual de la Facultad de Informática - UNLP (Colección BIPA/Biblioteca)
Gamification can be used to foster participation in knowledge sharing communities. While designing and assessing the potential impact of a gamification design in such a context, it is important to avoid work disruption and negative side effects. A gamification optimization approach implemented with deep reinforcement learning based on play-testing approaches helps prevent possible disruptive configuration and has the capability to adapt to different communities or gamification targets. In this research, a case of study for this approach is presented running over the Stack Overflow Q&A community. The approach detects the best configuration for a Contribution, Reinforcement, and Dissemination (CRD) gamification strategy using Stack Overflow historical data in a year. The results show that the approach funds proper gamification strategy configurations. Moreover, those configurations are robust enough to be applied along the time unseen periods.
DIF-M8322
OPTIMIZACIÓN
gamificación
Optimizing a gamified design through reinforcement learning : a case study in stack overflow - 1 archivo (358,4 kB)
Formato de archivo PDF. -- Este documento es producción intelectual de la Facultad de Informática - UNLP (Colección BIPA/Biblioteca)
Gamification can be used to foster participation in knowledge sharing communities. While designing and assessing the potential impact of a gamification design in such a context, it is important to avoid work disruption and negative side effects. A gamification optimization approach implemented with deep reinforcement learning based on play-testing approaches helps prevent possible disruptive configuration and has the capability to adapt to different communities or gamification targets. In this research, a case of study for this approach is presented running over the Stack Overflow Q&A community. The approach detects the best configuration for a Contribution, Reinforcement, and Dissemination (CRD) gamification strategy using Stack Overflow historical data in a year. The results show that the approach funds proper gamification strategy configurations. Moreover, those configurations are robust enough to be applied along the time unseen periods.
DIF-M8322
OPTIMIZACIÓN
gamificación