Jigsaw Unintended Bias in Toxicity Classification
Do, Quan (2019)
All rights reserved. This publication is copyrighted. You may download, display and print it for Your own personal use. Commercial use is prohibited.
Julkaisun pysyvä osoite on
The purpose of this thesis was to implement a Deep Learning Model to classify the toxicity of online comments. The main focus was on analysing the sentiment of sentences and on classifying this into categories. The data was collected from Jigsaw Unintended Bias in Toxicity Classification competition on Kaggle.