https://github.com/akayeshmantha/toxic-comment-neural-network-classifier

The Abusive Content Detection identifies the comments in your content and classifies according to it's severity.
https://github.com/akayeshmantha/toxic-comment-neural-network-classifier

api-client flux keras-tensorflow neural-network python3 tensorflow text-classification

Last synced: 2 months ago
JSON representation

The Abusive Content Detection identifies the comments in your content and classifies according to it's severity.

• Host: GitHub
• URL: https://github.com/akayeshmantha/toxic-comment-neural-network-classifier
• Owner: Akayeshmantha
• License: apache-2.0
• Created: 2018-11-29T06:36:29.000Z (over 6 years ago)
• Default Branch: master
• Last Pushed: 2018-11-29T06:53:45.000Z (over 6 years ago)
• Last Synced: 2025-02-01T18:44:52.496Z (4 months ago)
• Topics: api-client, flux, keras-tensorflow, neural-network, python3, tensorflow, text-classification
• Language: Jupyter Notebook
• Homepage:
• Size: 18.6 KB
• Stars: 0
• Watchers: 3
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        

The model can be invoked via the /invocations

endpoint.

It has 6 classes which toxic comment falls under

1. Toxic - level normal

2. Toxic - level high

3. Obscene

4. Threat

5. Insult

6. Identity Hate