Characterizing and Predicting Good First Issues

Background. Where to start contributing to a project is a critical challenge for newcomers of open source projects. To support newcomers, GitHub utilizes the Good First Issue (GFI) label, with which project members can manually tag issues in an open source project that are suitable for the newcomers. However, manually labeling GFIs is time- and effort-consuming given the large number of candidate issues. In addition, project members need to have a close understanding of the project to label GFIs accurately. Aims. This paper aims at providing a thorough understanding of the characteristics of GFIs and an automatic approach in GFIs prediction, to reduce the burden of project members and help newcomers easily onboard. Method. We first define 79 features to characterize the GFIs and further analyze the correlation between each feature and GFIs. We then build machine learning models to predict GFIs with the proposed features. Results. Experiments are conducted with 74,780 issues from 10 open source projects from GitHub. Results show that features related to the semantics, readability, and text richness of issues can be used to effectively characterize GFIs. Our prediction model achieves a median AUC of 0.88. Results from our user study further prove its potential practical value. Conclusions. This paper provides new insights and practical guidelines to facilitate the understanding of GFIs and the automation of GFIs labeling.