Open source software repositories use issue boards to track current issues with the project. One of the neat features of issue boards on github is the ability to label issues from a preset list of labels. This organizes github issues on repositories, allowing developers to more easily read the issue board and understand which issues could be more important to them. One challenge with open source repositories is that people often do not label issues that they create, leaving the issue board uninformative and unorganized.
This project seeks an ML solution to automatically tag new issues, taking a slightly new direction than the previous work that has been done in this field. This project can be applied to any github repository or user that has a sufficient amount of tagged label data.
This project is maintained as part of the AIOps team in Red Hat’s AI CoE as part of the Office of the CTO. More information can be found at https://www.operate-first.cloud/.