Expert Recommendation System for StackOverflo

Identifying Subject Matter Experts (SMEs) is crucial to Community Question Answering (CQA) systems. The success of CQA systems heavily relies on the contribution of these experts who provide a significant number of high-quality, useful answers. SO is a community-based question answering platform for developers to ask technical questions. We propose a novel approach to find SMEs for StackOverflow (SO) in an unsupervised manner. Our technique uses the Latent Dirichlet Allocation (LDA) model and Latent Semantic Analysis (LSA) to automatically predict the skill-set needed to answer questions based on their content and find experts with the same skill-set. The effectiveness of this approach is demonstrated through comprehensive experiments on the SO dataset for Python, C++, Java and C# programming languages by considering SO threads of a configurable elapsed time window and predicting who will answer questions in the following month.