Awesome Open Source
Awesome Open Source

Ticket Tagger

Machine learning driven issue classification bot. Add to your repository now!

AGPL Build

use ticket tagger


Visit our GitHub App and install.

install ticket tagger


Ticket Tagger is licensed under the GNU Affero General Public License. Every file should include a license header, if not, the following applies:

Ticket Tagger automatically predicts and labels issue types.
Copyright (C) 2018-2021  Rafael Kallis

This program is free software: you can redistribute it and/or modify
it under the terms of the GNU Affero General Public License as published by
the Free Software Foundation, either version 3 of the License, or
(at your option) any later version.

This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
GNU Affero General Public License for more details.

You should have received a copy of the GNU Affero General Public License
along with this program.  If not, see <>. 

Carefully read the full license agreement.

"... [The AGPL-3.0 license] requires the operator of a network server to provide the source code of the modified version running there to the users of that server."

Derivative Work




  • nodejs ^12.x is required to compile/install dependencies
  • wget is required for fetching datasets
  • we recommend at least 8 GB of RAM if you want to train or benchmark the model

get started:

git clone ticket-tagger
cd ticket-tagger

# install appropriate nodejs version
npx nave use 12

# compile/install dependencies
npm install

# fetch dataset
npm run dataset

# run benchmark
npm run benchmark

# run linter
npm run lint

# run tests
npm test

# run server
NODE_ENV="development" npm start

confounding factors:

Impact of Label Distribution

# balanced distribution
npm run dataset:balanced
npm run benchmark

# unbalanced distribution
npm run dataset:unbalanced
npm run benchmark

Impact of function words

npm run dataset:balanced
npm run benchmark

Impact of Language Consistency in Issue Tickets

# baseline
npm run dataset:english:baseline
npm run benchmark

# english
npm run dataset:english
npm run benchmark

Presence of Code Snippets in Issue Tickets

# baseline
npm run dataset:nosnip:baseline
npm run benchmark

# no snippets
npm run dataset:nosnip
npm run benchmark

generate dataset:

Datasets can be downloaded either using npm run dataset:balanced or npm run dataset:unbalanced. The datasets were generated using github archive's which can be accessed through google BigQuery.

Add the query below to your BigQuery console and adjust if needed (e.g., resample issues to create a balanced dataset, etc.).

-- unbalanced dataset

  CONCAT('__label__', label, ' ', title, ' ', REGEXP_REPLACE(body, '(\r|\n|\r\n)',' '))
    LOWER(JSON_EXTRACT_SCALAR(payload, '$.issue.labels[0].name')) AS label,
    JSON_EXTRACT_SCALAR(payload, '$.issue.title') AS title,
    JSON_EXTRACT_SCALAR(payload, '$.issue.body') AS body
    AND type = 'IssuesEvent'
    AND JSON_EXTRACT_SCALAR(payload, '$.action') = 'closed' )
  (label = 'bug' OR label = 'enhancement' OR label = 'question')
  AND body != 'null';

run serverless app:

You need a .env file in order to run the github app. The file should look like this:

GITHUB_CERT="<private key>"

Note: When running app in production, environment variables should be provided by host.

Get A Weekly Email With Trending Projects For These Topics
No Spam. Unsubscribe easily at any time.
Javascript (1,551,389
Machine Learning (30,586
Github App (285
Issue Tracker (220
Fasttext (210
Related Projects