arunarn2/ToxicCommentChallenge
Text classification using GloVe embeddings, CNN and stacked bi-directional LSTM with Max K Pooling.
This project helps online community managers and content moderators automatically identify and classify harmful online comments across six categories like 'toxic', 'obscene', and 'threat'. It takes raw user comments as input and outputs classifications indicating the type of toxicity present. It's designed for anyone managing online forums, social media, or other platforms where user-generated content needs to be monitored for abusive language.
No commits in the last 6 months.
Use this if you need to automatically detect and categorize various forms of toxicity in online user comments to maintain a safe and positive community.
Not ideal if you require nuanced human-like interpretation of sarcasm or highly complex, subtle forms of online abuse, as automated systems have limitations.
Stars
8
Forks
2
Language
Python
License
—
Category
Last pushed
May 08, 2018
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/arunarn2/ToxicCommentChallenge"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
codelion/adaptive-classifier
A flexible, adaptive classification system for dynamic text classification
jiegzhan/multi-class-text-classification-cnn-rnn
Classify Kaggle San Francisco Crime Description into 39 classes. Build the model with CNN, RNN...
jiegzhan/multi-class-text-classification-cnn
Classify Kaggle Consumer Finance Complaints into 11 classes. Build the model with CNN...
cbaziotis/datastories-semeval2017-task4
Deep-learning model presented in "DataStories at SemEval-2017 Task 4: Deep LSTM with Attention...
iamaziz/ar-embeddings
Sentiment Analysis for Arabic Text (tweets, reviews, and standard Arabic) using word2vec