About
The tool has tree main parts; Issue classification model, the plugin APIs, and the Jira plugin.
More Details: Issue Labeler is a plugin for Jira , which utilizes a deep neural language model to predict an issue's type based on its title and description. Specifically, the plugin would classify an issue into three types: bug, improvement, or new feature. The issue-labeler plugin was implemented by fine-tuning Google's pre-trained ALBERT language model, using 42,514 labeled issue reports extracted from 77 projects. The plugin showed an average of 67% across the 3 issue categories in terms of F1-score. The plugin will provide developers with a tool that recommends issue labels to, in turn, optimize the process of tagging and resolving these issues. The tool has tree main parts; Issue classification model, the model, plugin APIs, and the Jira plugin.
Issue Labeler Model
Google ALBERT model
Issue Labeler Jira Plugin
Jira plugin
Open Source
GitHub repository
Set up
The following are the steps to set up the plugin.
-
Step 1
Copy the plugin installation link
https://issue-labeler-plugin.herokuapp.com/install -
Step 2
Sign in to your Jira account and navigate to the "Manage Apps" setting found under "Apps" at the top of your dashboard
Note: Be sure to enable development mode for your Jira instance by toggling the option under Manage Apps > Settings > Enable Development Mode -
Step 3
- Click on "Upload App" and paste the URL into it.
- Click on "Upload App" and paste the URL into it and click "Upload"
