Graph Neural Network Models for Socio-Technical Code Review Optimisation

Timothy Adepitan

doi:10.36948/ijfmr.2024.v06i02.74379

Graph Neural Network Models for Socio-Technical Code Review Optimisation

Author(s)	Timothy Adepitan
Country	Nigeria
Abstract	The code review plays a huge role with modern software development to guarantee quality, security and maintainability. In large-scale and distributed development environments, especially those that support critical infrastructures (e.g. financial technologies, cloud platforms, critical safety infrastructure), code review is less a technical activity. Instead, it is a socio-technical process that is influenced by developer's collaboration networks, distribution of expertise, communication patterns, and organization's norms. Traditional code review assignment and prioritization mechanisms, which are often based on static rules for ownership, or manual selection of reviewers, have trouble scaling, and often lead to reviewer overload, delayed feedback and suboptimal defects themselves. Recent developments in graph neural networks (GNNs) provide a powerful modeling paradigm for modeling complex types of relational structures that are inherent in a socio-technical system. By representing code artifacts, developers, review interactions and dependencies as nodes and edges in heterogeneous graphs, models based on GNN can discover latent representations that integrate both technical aspects (such as the code) and social aspects (such as the advertisement collaboration dynamics). This article suggests a broad set of rules to apply GNN models to the growth of code review processes by optimizing the code reviewer assignment, prioritizing risk changes, and increasing the effectiveness of code reviews. Using the design-science research approach, the study synthesizes knowledge from the literature on software engineering, network science and machine learning, and evaluates the conceptual GNN driven review optimization pipeline. The results of analysis show that graph-based learning can significantly improve traditional heuristic and rule-based learning in reviewer recommendation accuracy, review latency reduction and defect discovery rate. The results indicate that GNN-based socio-technical modeling is a transformation towards intelligent, scalable and fair code review systems.
Keywords	Graph Neural Networks; Code Review Optimization; Socio-Technical Systems; Software Engineering Analytics; Reviewer Recommendation; Machine Learning for Software Engineering.
Field	Engineering
Published In	Volume 6, Issue 2, March-April 2024
Published On	2024-03-10
DOI	https://doi.org/10.36948/ijfmr.2024.v06i02.74379

View / Download PDF File

E-ISSN 2582-2160

doi

CrossRef DOI is assigned to each research paper published in our journal.

IJFMR DOI prefix is
10.36948/ijfmr

Downloads

Research Paper Format Copyright Permission Form and Undertaking Form Cover Page Vol 8 Isu 3 Cover Page Vol 8 Isu 2 Cover Page Vol 8 Isu 2

All research papers published on this website are licensed under Creative Commons Attribution-ShareAlike 4.0 International License, and all rights belong to their respective authors/researchers.

CC-BY-SA

About IJFMR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9687-828-838	editor@ijfmr.com

International Journal For Multidisciplinary Research

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

Graph Neural Network Models for Socio-Technical Code Review Optimisation

Share this