GitHub - Shreyas9699/Convolutions-text-classification: 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 Public

Notifications You must be signed in to change notification settings
Fork 1
Star 0

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%.

0 stars 1 fork Branches Tags Activity

Star

Notifications

Branches Tags

Name		Name	Last commit message	Last commit date
Latest commit History 4 Commits
.ipynb_checkpoints		.ipynb_checkpoints
.gitattributes		.gitattributes
README.txt		README.txt
test.csv.zip		test.csv.zip
toxic_classification.ipynb		toxic_classification.ipynb
train.csv.zip		train.csv.zip

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