Developer Recommendation for Stack Exchange Software Engineering Q&A Website based on K-Means clustering and Developer Social Network Metric

Verma, Ayushi; Sardana, Neetu; Lal, Sangeeta

Abstract

Nowadays Online question answering website platforms are getting popular as it allows the users to get responses from varied experts beyond their reach. Businesses use these sites for their growth and exposure. Enormous volumes of question are posted on these sites. Finding an expert for answering large voluminous questions requires specialized techniques. This paper proposes hybrid approach for finding prominent expert for the posted questions. The proposed approach uses clustering and social network metrics. The approach clusters the database questions based on tag similarity using K Means. The new posted question is matched with the clusters and best suitable cluster is extracted. Developer Social Network is constructed for chosen cluster and Page Rank with time decay has been applied to find the prominent developer. The proposed approach attains 60% accuracy.

Citation

Verma, A., Sardana, N., & Lal, S. (2020). Developer Recommendation for Stack Exchange Software Engineering Q&A Website based on K-Means clustering and Developer Social Network Metric. Procedia Computer Science, 167, 1665-1674. https://doi.org/10.1016/j.procs.2020.03.377

• Journal Article Type: Article
• Online Publication Date: Apr 16, 2020
• Publication Date: 2020
• Deposit Date: Jul 25, 2024
• Journal: Procedia Computer Science
• Print ISSN: 1877-0509
• Publisher: Elsevier
• Peer Reviewed: Peer Reviewed
• Volume: 167
• Pages: 1665-1674
• DOI: https://doi.org/10.1016/j.procs.2020.03.377
• Public URL: https://keele-repository.worktribe.com/output/879849
• Additional Information: This article is maintained by: Elsevier; Article Title: Developer Recommendation for Stack Exchange Software Engineering Q&A Website based on K-Means clustering and Developer Social Network Metric; Journal Title: Procedia Computer Science; CrossRef DOI link to publisher maintained version: https://doi.org/10.1016/j.procs.2020.03.377; Content Type: article; Copyright: © 2020 The Author(s). Published by Elsevier B.V.