DevRec: enhancing developer recommendation using machine learning

Abstract In Open-Source Software (OSS) projects, effectively managing tasks such as committing code, merging pull requests, and closing issues require accurate role-based recommendations for developers. As the number of issues and contributors increases, assigning the right developers to specific roles becomes more complex. This paper introduces DevRec , a novel framework designed to enhance multi-role Dev elope r Rec ommendation for OSS projects. DevRec employs Semantic Analysis (SA) to interpret issue descriptions and historical developer contributions in OSS projects, thus improving the mapping between issues and suitable developers. Two complementary approaches are explored: Statistical-based Semantic Analysis (Statistical-SA) for ranking developer recommendations, and Machine Learning–Semantic Analysis (ML-SA) for predictive developer assignment. ML models are trained on previous developer behaviour and contributions across multiple projects to enhance recommendation accuracy. The framework is evaluated on a benchmark dataset comprising three OSS projects of varying sizes— Framework (small, 325 issues), Travis (medium, 5,457 issues), and Elasticsearch (large, 10,423 issues). Results show that Statistical-SA improves accuracy by 13.85% , 48.67% , and 1.66% respectively, over baseline methods. At the same time, ML-SA consistently outperforms Statistical-SA across all roles, achieving an average 2–5% improvement in Commit, Merge, and Close tasks. These findings highlight the effectiveness of integrating semantic and machine learning-based models for multi-role developer recommendations.