Modeling Content and Membership Growth Dynamics of User-Generated Content Sharing Networks With Two Case Studies

• Main Authors: Rong-Huei Chen, Shi-Chung Chang
• Format: Article
• Language: English
• Published: IEEE 2018-01-01
• Series: IEEE Access
• Subjects: User-generated content; sharing network; growth dynamics; Bass diffusion model; network state-dependent generalization; positive feedback to individual
• Online Access: https://ieeexplore.ieee.org/document/8245798/

User-generated content sharing networks (UGCSNets), in which members are content contributors as well as users, have had a significant impact on the sharing economy and on society via the sharing and reuse of contents. In a UGCSNet, managing for growth requires a quantitative grasp of how individual members' participation and sharing affect and are affected by the membership and content volume; these interactions form a dynamic loop. In this paper, a quantitative modeling approach for the loop dynamics of UGCSNet growth is developed by exploiting limited empirical data. A teaching material sharing network serves as a baseline case study, and Wikipedia serves as a validation case for the modeling approach design. The novel modeling approach consists of 1) set of generalized bass diffusion model-embedded stochastic difference equations (GBDSDEs) of the loop dynamics and 2) a quasi-bootstrap-based nonlinear least square method to extract from the limited empirical data and periodically update the model parameters as the UGCSNet evolves. In GBDSDEs, two difference equations describe the number of members and content volume evolution. The stochastic drives consist of measures of individual participation and content uploading. The drive models are an innovative generalization of the bass diffusion model as probabilistic models of known qualitative descriptions regarding how the individual willingness to participate and share is affected by the total membership and content volume. Analyses of the coefficients of determination show good fits between model predictions and actual outcomes for both Smart Creative Teachers Net and Wikipedia growths. Applications of the modeling approach to what-if analyses demonstrate its value to predict and assess the effects of specific managerial strategies-such as the initial content volume and the number of founding altruistic members-on the growth of a UGCSNet.