Published on Thu Sep 27 2018

Predictive Embeddings for Hate Speech Detection on Twitter

Rohan Kshirsagar, Tyus Cukuvac, Kathleen McKeown, Susan McGregor

We present a neural-network based approach to classifying online hate speech in general, as well as racist and sexist speech in particular. Using pre-trained word embeddings and max/mean pooling from simple, fully-connected networks we are able to predict the occurrence of hate speech.

0
0
0
Abstract

We present a neural-network based approach to classifying online hate speech in general, as well as racist and sexist speech in particular. Using pre-trained word embeddings and max/mean pooling from simple, fully-connected transformations of these embeddings, we are able to predict the occurrence of hate speech on three commonly used publicly available datasets. Our models match or outperform state of the art F1 performance on all three datasets using significantly fewer parameters and minimal feature preprocessing compared to previous methods.

Thu Jun 01 2017
NLP
Deep Learning for Hate Speech Detection in Tweets
Hate speech detection on Twitter is critical for applications like controversial event extraction, building AI chatterbots, content recommendation, and sentiment analysis. We define this task as being able to classify a tweet as racist, sexist or neither.
0
0
0
Tue Feb 27 2018
NLP
Hate Speech Detection: A Solved Problem? The Challenging Case of Long Tail on Twitter
The increasing propagation of hate speech on social media has drawn significant investment from governments, companies, and researchers. A large number of methods have been developed for automated hate speech detection online. This aims to classify textual content into non-hate or hate speech.
0
0
0
Mon Feb 08 2021
NLP
A study of text representations in Hate Speech Detection
Simple hate-keyword frequency features (BoW) work best, followed by pre-trained word embeddings (GLoVe) and N-gram graphs. A combination of these representations paired with Logistic Regression or 3-layer neurological network classifiers achieved the best detection performance.
0
0
0
Mon Sep 16 2019
Machine Learning
Prediction Uncertainty Estimation for Hate Speech Classification
Hate speech has a harmful effect on minority groups and communities. There is a pressing need for hate speech detection and filtering. We propose the adaptation of deep neural networks that can estimate prediction uncertainty. We evaluate our approach using different text embedding methods.
0
0
0
Mon Nov 23 2020
Machine Learning
Effect of Word Embedding Models on Hate and Offensive Speech Detection
Deep neural networks have been adopted successfully in hate speech detection. The effect of the word embedding models on the neural network's performance has not been appropriately examined in the literature.
0
0
0
Tue Mar 16 2021
Artificial Intelligence
dictNN: A Dictionary-Enhanced CNN Approach for Classifying Hate Speech on Twitter
0
0
0