Toxic Comments Classification using Neural Network

Abstract

Humans have built broad models of expressing their thoughts via several appliances. The internet has not only become a credible method for expressing one's thoughts, but is also rapidly becoming the single largest means of doing so. In this context, one area of focus is the study of negative online behaviors of users like, toxic comments that are threat, obscenity, insults and abuse. The task of identifying and removing toxic communication from public forums is critical. The undertaking of analyzing a large corpus of comments is infeasible for human moderators. Our approach is to use Natural Language Processing (NLP) techniques to provide an efficient and accurate tool to detect online toxicity. We apply TF-IDF feature extraction technique, Neural Network models to tackle a toxic comment classification problem with a labeled dataset from Wikipedia Talk Page.