The diffusion of user roles via social networks in online health communities

As a major source of social support for people with health problems, Online Health Communities (OHCs) have attracted a great number of members. Using text mining and unsupervised machine learning techniques, we revealed that users of a popular breast cancer OHC play different roles in social support activities. A role transition network was constructed to illustrate how users' roles change over time. We also found evidence for role diffusion via social ties-users tend to adopt roles of their network neighbors. The comparison of how users' roles spread among users suggests that some roles are more viral that others. Our findings provide a better understanding of dynamics in users' roles, which could greatly help managing an active and successful OHC.