One size does not fit all: Rethinking recognition system design for behaviorally heterogeneous online communities

Online knowledge-sharing communities typically acknowledge their top contributors by implementing recognition systems. Extant recognition systems suffer from several limitations such as treatment of the entire community as homogeneous and inflexibility of customization. We propose a framework based on socio-technical design principles for designing a multi-criterion- and multi-segment-based recognition system that exploits multiple user characteristics for differential recognition according to community goals. We apply this framework on data gathered from Yelp.com and show how it can be used to recognize top members of different identified behavioral segments (amateurs, adepts, and enthusiasts) based on their performance on various relevant factors.