https://github.com/jakehartnell/nlpfinalproject

https://github.com/jakehartnell/nlpfinalproject

Last synced: 4 days ago
JSON representation

• Host: GitHub
• URL: https://github.com/jakehartnell/nlpfinalproject
• Owner: JakeHartnell
• Created: 2013-11-05T22:52:25.000Z (about 11 years ago)
• Default Branch: master
• Last Pushed: 2015-02-01T16:56:24.000Z (almost 10 years ago)
• Last Synced: 2024-10-11T06:11:48.259Z (26 days ago)
• Language: Python
• Size: 813 KB
• Stars: 1
• Watchers: 4
• Forks: 1
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
NLPFinalProject

===============

Our goal is to create a bot that uses the hypothes.is API to evaluate whether an annotation is spam, detrimental, or uncivil, and then flag it for moderation. 

We plan to use the YouTube API to assemble a training set for what really uncivil comments look like, and hopefully refine our approach to see if the threaded discussion is related to the content on the page. We hope to design light weight features that can be used to make decisions in a computationally efficient way. 

Ultimately, the classifier should be able to identify the sentiment of any generic web discussion, offering a wider range of usability. We hope to possibly be able to contribute some code back to the open source hypothes.is project.