Skip to content

Offensive Tweets Identification using Convolutional Neural Networks

Notifications You must be signed in to change notification settings

johnnytorres/toxicitydetector

Repository files navigation

Offensive Tweets Identification using Convolutional Neural Networks

This is the implementation of the model for the task of identifying offensive tweets in the Task 6 of SemEval-2019 (International Workshop on Semantic Evaluation), as detailed in the paper:

JTML at SemEval-2019 Task 6: Offensive Tweets Identification using Convolutional Neural Networks

Please cite the paper if you use the code. Thanks!

Preparing the environment

Please install the requirements in your python environment (virtual is recommended)

pip install -r requirements.txt

Reproducing the results

First, run the script to download the dataset and prepare the embeddings

./script-data.sh

Then, run the scripts to train the models with k-Fold (k=10)

./script-experiments.sh

About

Offensive Tweets Identification using Convolutional Neural Networks

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published