Trained models & code to predict toxic comments on all 3 Jigsaw Toxic Comment Challenges. Built using ⚡ Pytorch Lightning and 🤗 Transformers. For access to our API, please email us at [email protected].

A web-app to identify toxic comments in a youtube channel and delete them.

A WordPress plugin that uses AI to encourage authors of toxic comments to re-phrase them in a more kind way.

Natural Language Processing: Toxic Comments Detection and Classification

Toxic Comment Classification Challenge | Kaggle

CNN and LSTM multi-label text classification

Telegram bot that detects toxic comments based on Perspective API

Identify toxicity in online comments

Fast text toxicity classification model

A DL project that helps in classifying Toxic Comment weather it is positive or not.

Analyzing Jigsaw's toxic comments Kaggle challenge using fastai + pytorch

A Machine Learning model to detect Toxic comment on Kaggel dataset.

Convolutional Neural Networks for Toxicity Detection in Online Comments

Repository of the paper "Supporting Online Toxicity Detection with Knowledge Graphs" (ICWSM 22).

A project to implement toxic comment classification based on the Jigsaw/Conversational AI challenge.

TOXIC-BOY-OP/MUSIC-BOTOP

Profanity detection using fastText.

Build a multi-headed model that’s capable of detecting different types of of toxicity like threats, obscenity, insults, and identity-based hate.

Binary classification of toxic comments for Wikishop's wiki system. Achieved F1=0.947 on test set using BERT embeddings + SMOTE + logistic regression, exceeding target 0.75. Includes preprocessing, TF‑IDF baselines (LogReg, RandomForest, CatBoost), and model evaluation. Aims to automate moderation and reduce manual workload.

Портфельный NLP-кейс по классификации токсичных комментариев