-
Notifications
You must be signed in to change notification settings - Fork 1
Implemented word embedding and transfer learning to classify comments into toxic or non-toxic comments using Convolution. The model was able to classify comments into toxic or non-toxic with accuracy >= 95%.
Shreyas9699/Convolutions-text-classification
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Folders and files
Name | Name | Last commit message | Last commit date | |
---|---|---|---|---|
Repository files navigation
The idea of this project is To apply word embeddings for text classification, use 1D convolutions as feature extractors in natural language processing (NLP), and perform binary text classification using deep learning. The dataset I worked on classifying a large number of Wikipedia comments as being either toxic or not (i.e. comments that are rude, disrespectful, or otherwise likely to make someone leave a discussion). This issue is especially imtortant, given the conversations the global community and tech companies are having on content moderation, online harassment, and inclusivity. The data set we will use comes from the Toxic Comment Classification Challenge on Kaggle. Pre-requisite: Tensorflow https://www.tensorflow.org/install Keras Dataset: https://www.kaggle.com/c/jigsaw-toxic-comment-classification-challenge Embeddings: http://nlp.stanford.edu/data/glove.6B.zip
About
Implemented word embedding and transfer learning to classify comments into toxic or non-toxic comments using Convolution. The model was able to classify comments into toxic or non-toxic with accuracy >= 95%.
Topics
Resources
Stars
Watchers
Forks
Releases
No releases published