Deep Learning in Social Computing

The goal of social computing is to devise computational systems to learn mechanisms and principles to explain and understand the behaviors of each individual and collective teams, communities, and organizations. The unprecedented online data in social media provides a fruitful resource for this purpose. However, traditional techniques have a hard time in handling the complex and heterogeneous nature of social media for social computing. Fortunately, the recent revival and success of deep learning brings new opportunities and solutions to address these challenges. This chapter introduces the recent progress of deep learning on social computing in three aspects, namely user-generated content, social connections, and recommendation, which have covered most of the core elements and applications in social computing. Our focus lies in the discussions on how to adapt deep learning techniques to mainstream social computing tasks.