The knowledge exchange platform is an innovative way that empowers online learning for the Internet users to utilize their spare time slots for knowledge sharing and seeking. Many researchers have conducted research on the user interaction and content of the knowledge payment platform. This paper analyzes the user interaction and user comments by analyzing the data of Zhihu live, a major online knowledge exchange platform in China. We employ social network analysis and deep learning method to explore the users’ interaction structure in Zhihu live platform and their emotional tendency for knowledge exchange. Particularly, we use social network analysis theory supplemented by social analysis tools Gephi and neural network algorithm, LSTM to achieve our goals. We propose a set of hypotheses from the perspective of a small world phenomenon and users’ social engagement in the platform. Our results show that there is a small world phenomenon on core topics and the more frequent users interaction is, the more positive the users’ comments are. Theoretically, this study explores the users’ knowledge seeking and sharing behavior from the perspective of user interaction and user emotion. Also, our research offers implications to practice that enhancing sociality can be an effective strategy to motivate the desirable users’ paid knowledge sharing behaviors in the platform.
Tu, Yan and Xin, Xiaping, "Social Network Analysis for Online Knowledge Exchange Platform: Evidence from Zhihu" (2020). WHICEB 2020 Proceedings. 3.