Analyzing Cascade Sizes of Stopped Projects in SourceForge: Is SOC Theory Applicable to OSSOCs?

Abstract

Based on three rounds of data extraction, we first construct complex network models to identify the cascade sizes of stopped projects and their distributions in SourceForge (March 2000 to February 2013). We then analyze and discover characteristics of these cascade sizes and their distributions: most cascade sizes are 1; two extreme sizes coexist; and the cascade sizes in each Period of SourceForge's peak phase exhibit a power-law distribution while lacking scale-free properties. Finally, we discuss the limitations of this study and their implications for Self-Organized Criticality theory.