AT-AI12 · NLP
Toxic Comment Detection
Detects abusive or hateful comments before they are posted.
- Suits
- Sem 5–6
- Branches
- CSE, ISE, AIML
- Type
- Software
How it works
The model is trained on comments that have been labelled for categories such as insult, threat and hate. A comment can belong to more than one category, so the model gives a separate score for each. On the test page you type a comment and see the score for every category along with an overall severity.
What it does
- Multi-label output
- Severity score
- Test page
Built with
Python, NLP libraries
What you get
- Working software with full source code
- Steps to install and run it on your laptop
- Rough report and explanation of the working
- Live demo on video call before the final payment
Good to know
- Features are as listed here. Anything extra is quoted separately.
- Runs on a normal laptop unless we tell you otherwise.
- Full reports and PPTs are not included.
Similar projects
- AT-AI07Fake News DetectionClassifies a news article as real or fake from its text.
- AT-AI08Product Review Sentiment AnalysisReads reviews and tells whether each is positive, negative or neutral.
- AT-AI09Spam Email and SMS ClassifierSeparates spam from genuine messages.
- AT-AI10Resume Screening and Job MatchingRanks resumes against a job description by skill match.