The growing number of bike sharing systems (BSS) in many cities largely facilitates biking for transportation and recreation. Most recent bike sharing systems produce time and location specific data, which enables the study of travel behavior and mobility of each individual. However, despite a rapid growth of interest, studies on massive bike sharing data and the underneath travel pattern are still limited. Few studies have explored and visualized spatiotemporal patterns of bike sharing behavior using flow clustering, nor examined the station functional profiles based on over-demand patterns. This study investigated the spatiotemporal biking pattern in Chicago by analyzing massive BSS data from July to December in 2013 and 2014. The BSS in Chicago gained more popularity. About 15.9% more people subscribed to this service. Specifically, we constructed bike flow similarity graph and used fastgreedy algorithm to detect spatial communities of biking flows. By using the proposed methods, we discovered unique travel patterns on weekdays and weekends as well as different travel trends for customers and subscribers from the noisy massive amount data. In addition, we also examined the temporal demands for bikes and docks using hierarchical clustering method. Results demonstrated the modeled over-demand patterns in Chicago. This study contributes to offer better knowledge of biking flow patterns, which was difficult to obtain using traditional methods. Given the trend of increasing popularity of the BSS and data openness in different cities, methods used in this study can extend to examine the biking patterns and BSS functionality in different cities.