Mobile collaboration is an emerging kind of collaboration that adopts mobile devices (i.e., laptops, PDAs, and smart phones) and social media software to improve the efficiency and productivity of collaboration. However, many collaborative teams suffer from an anti-social behavior called social loafing. Social loafing will hinder knowledge exchange within the team and further influence team performance and project outcomes. Moreover, the state of an individual’s social loafing is unobservable and changes overtime, making it difficult to be identified in real time. Therefore, our research aims to investigate the evolution of social loafing and its impact on knowledge contribution in the mobile collaboration context. We propose a machine learning model to infer individuals’ unobserved and evolving social loafing state from the series of task behaviors (quantity and quality of the contributed knowledge). Also, we explore how one’s centrality in a social network affects his/her knowledge contribution behavior when he/she is in different social loafing states. We conduct an empirical study and the results show that individuals with high or low social loafing state are very ‘sticky’ to maintain the previous state and the centrality in the network only positively influences individuals in medium social loafing state. In conclusion, our research adopts a machine leaning method to infer the evolution of individuals’ social loafing and provides a comprehensive understanding of knowledge contribution in team work.
Jiang, Shan; Zhang, Xi; Cheng, Yihang; and Xu, Dongming, "How To Reorganize Social Network For Better Knowledge Contribution During Mobile Collaboration? A Study Based On Anti-Social Behavioral Perspective" (2018). CONF-IRM 2018 Proceedings. 5.