Understanding and Predicting Software Developer Expertise in Stack Overflow and GitHub

This thesis attempts to understand and predict software developer expertise based on their activity and experience on GitHub and Stack Overflow platforms. An exploratory survey was conducted with 73 software developers and a mixed methods approach was applied to analyze the survey results. Further, using Machine Learning techniques the thesis attempts to predict software developer expertise based on their participation on social coding platforms. The thesis found that both knowledge and experience are only necessary but not sufficient conditions for a developer to become an expert, and an expert would necessarily have to possess adequate soft skills. Lastly, an expert's contribution to GitHub seems to be driven by personal factors, while contribution to Stack Overflow is motivated more by professional drivers (i.e., skills and expertise). The last section determined the best predicting classifier-algorithm for contributors, understood the distribution of expertise and their characteristics and compared prediction capability of the model.