Collaborative Software Development (CSD) as an effective software development paradigm has achieved rapid development. In CSD, one critical and challenging problem is to find a group of compatible and diverse developers who can complete the assigned task as quickly as possible. To solve this problem, most previous approaches focus on measuring the relevance of tasks and developers based on their historical interactions. However, such approaches usually suffer from data sparsity and cold start problem which may reduce the recommendation accuracy. Moreover, previous approaches often ignored the diversity of team members which may reduce the overall collaboration efficiency. In this paper, we propose an attentive text-enhanced graph embedding learning framework, termed as CsdRec. We first incorporate text embedding into one-hop interaction learning and two-hop graph learning to learn the relevance between tasks and team members. Then, we explicitly model the team members’ diversity and incorporate it with relevance. Finally, to evaluate the performance of CsdRec, we conduct extensive experiments on two real-world datasets. The experimental results show that CsdRec outperforms other state-of-the-art approaches significantly.

Code review as an effective software quality assurance practice has been widely applied in many open-source software communities. However, finding a suitable reviewer for certain codes can be very challenging in open-source communities due to the difficulty of learning the characteristics of reviewers and the code-reviewer interaction sparsity in open-source software communities. To tackle this problem, most previous approaches focus on learning developers’ capabilities and experiences and recommending suitable developers based on their historical interactions. However, such approaches usually suffer from data-sparsity and noise problems, which may reduce the recommendation accuracy. In this paper, we propose an attentive neighbor embedding propagation enhanced code reviewer recommendation framework (termed ANEP). In ANEP, we first construct the reviewer–code interaction graph and learn the semantic representations of the reviewer and code based on the transformer model. Then, we explicitly explore the attentive high-order embedding propagation of reviewers and code and refine the representations along their neighbors. Finally, to evaluate the effectiveness of ANEP, we conduct extensive experiments on four real-world datasets. The experimental results show that ANEP outperforms other state-of-the-art approaches significantly.

Software developer recommendation is a critical task for online collaboration platforms. Identifying suitable developers remains challenging due to difficulties in capturing interaction behavioral preferences and semantic relevance, as well as handling data sparsity and cold-start issues. Traditional approaches typically model developers’ competencies (e.g., skills, expertise, and experience) or infer their preferences from historical task interactions. However, they often underperform because they fail to address several key challenges: (1) effectively capturing deep interaction behavioral preferences; (2) modeling latent textual semantics between developers and tasks; and (3) integrating behavioral preferences with semantic relevance in a unified manner. To address these challenges, we propose HiSDevRec, a novel dual-modality hybrid framework for developer recommendation that jointly models interaction-based behavioral preferences and textual semantic relevance. Specifically, we introduce a hybrid representation learning approach that integrates ID-based behavioral patterns with semantic representations derived from textual information. We further employ graph attention networks to capture higher-order propagation over the interaction graph, generating enriched representations for developers and tasks. In addition, we design a self-supervised disentanglement mechanism to explicitly separate behavioral and semantic representations, improving recommendation performance while enabling factor-level interpretability. Finally, we conduct extensive experiments on two real-world datasets, along with a case study and a user survey in an industrial setting. The results demonstrate that HiSDevRec consistently outperforms state-of-the-art baselines.