https://github.com/jakehartnell/nlpfinalproject
https://github.com/jakehartnell/nlpfinalproject
Last synced: 8 months ago
JSON representation
- Host: GitHub
- URL: https://github.com/jakehartnell/nlpfinalproject
- Owner: JakeHartnell
- Created: 2013-11-05T22:52:25.000Z (over 12 years ago)
- Default Branch: master
- Last Pushed: 2015-02-01T16:56:24.000Z (over 11 years ago)
- Last Synced: 2025-02-13T14:46:57.183Z (over 1 year 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.