Categorizing Code Review Comments using Machine Learning

Abstract

Code review turns into a progressively mainstream method to find out early defects in source code. These days experts are going for peer-investigating their codes by their co-developers to make the source code clean. Chipping away at a circulated or scattered team, a code review is required to check the patches to consolidate. Code looking into can likewise be a structure of approving practical and non-useful necessities. In some cases, analysts don't put organized remarks, which turns into a bottleneck to developers for tackling the discoveries or recommendations remarked by the reviewers. For making the review support progressively successful, organized also, productive survey remarks are compulsory. Mining the repositories of five commercialized projects, we extricate 2185 review comments. We have utilized 6 machine learning classifiers to prepare our model. Among those Stochastic Gradient Descent (SGD) vector machines, the procedure accomplishes a higher exactness of 63.89%. This examination will assist the specialists with building up organized and viable code review by categorizing and culture among worldwide programming engineers.