GitHub / andiosika / NLP-to-identify-toxic-or-abusive-language-for-online-conversation-using-Keras-Deep-Learning-Models
Natural Language Processing: A multi-headed model capable of detecting different types of online discussion toxicity like threats, obscenity, insults, and identity-based hate using Keras RNN LSTM and focal loss to address a hyper-imbalanced dataset.
JSON API: http://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/andiosika%2FNLP-to-identify-toxic-or-abusive-language-for-online-conversation-using-Keras-Deep-Learning-Models
PURL: pkg:github/andiosika/NLP-to-identify-toxic-or-abusive-language-for-online-conversation-using-Keras-Deep-Learning-Models
Stars: 5
Forks: 2
Open issues: 1
License: None
Language: Jupyter Notebook
Size: 166 MB
Dependencies parsed at: Pending
Created at: almost 5 years ago
Updated at: 6 months ago
Pushed at: over 4 years ago
Last synced at: 5 months ago
Topics: focal-loss, keras-neural-networks, nlp, nlp-machine-learning, toxic-comment-classification