What it does
Text Classification assigns one or more classes to a document according to their content. Classes are selected from a previously established taxonomy (a hierarchy of categories or classes). This app takes care of all preprocessing tasks (extracting text, tokenization, stopword removal, and lemmatization) required for automatic classification.
This app supports a variety of text classification scenarios like:
- Binary classification like spam filtering (HAM, SPAM) or simple sentiment analysis (POSITIVE, NEGATIVE).
- Multiple class classification like selecting one category among several alternatives - movie genre classification (thriller, terror, romantic, etc.)
- Multilabel categorization - assigning all categories that apply to a single document
- Complex taxonomy categorization - assigning categories arranged in a multilevel taxonomy
The app combines statistical document classification with rule-based filtering, which allows us to obtain a high degree of precision in a wide range of environments.
Try it out with some sample text!
How I built it
Using Forge UI and API
Challenges I ran into
Getting started with Forge
Accomplishments that I'm proud of
A working app
What I learned
Forge Atlassian developer products
What's next for Text classification for JIRA
Better visualization of app response output. Same feature for Confluence.