Deep Learning Based Fusion Approach for Hate Speech Detection

Yanling Zhou,Xiufeng Liu,Nick Savage,Yanyan Yang,Han Liu

doi:10.1109/access.2020.3009244

Abstract

In recent years, the increasing prevalence of hate speech in social media has been considered as a serious problem worldwide. Many governments and organizations have made significant investment in hate speech detection techniques, which have also attracted the attention of the scientific community. Although plenty of literature focusing on this issue is available, it remains difficult to assess the performances of each proposed method, as each has its own advantages and disadvantages. A general way to improve the overall results of classification by fusing the various classifiers results is a meaningful attempt. We first focus on several famous machine learning methods for text classification such as Embeddings from Language Models (ELMo), Bidirectional Encoder Representation from Transformers (BERT) and Convolutional Neural Network (CNN), and apply these methods to the data sets of the SemEval 2019 Task 5. We then adopt some fusion strategies to combine the classifiers to improve the overall classification performance. The results show that the accuracy and F1-score of the classification are significantly improved.

Highlights

The popularity of social media platforms such as Facebook, Twitter and YouTube, etc. provide channels for internet users to express their opinions and share comments that are visible to all
RELATED WORK we introduce the terminology of hate speech and the principles of state-of-the-art deep learning methods
The format of an annotated tweet in the training set has the following pattern: ID Tweet-text HS: Where ID is a progressive number denoting the tweet within the dataset, Tweet-text is the given text of the tweet, HS which is given in the training data and to be predicted in the test set, if the Tweet-text is hate speech the value is 1, otherwise the value is 0

Summary

Introduction

The popularity of social media platforms such as Facebook, Twitter and YouTube, etc. provide channels for internet users to express their opinions and share comments that are visible to all. The popularity of social media platforms such as Facebook, Twitter and YouTube, etc. Provide channels for internet users to express their opinions and share comments that are visible to all. Social networks encourage the interactions between people to be more indirect and anonymous providing anonymity for some people making them feel safer even though they express hate speech. It can lead to disruptive anti-social outcomes if it continues to be unregulated and uncontrolled. The polarity detection of speech on platforms is the first step and is critical to government departments, social security services, law enforcement and social media companies which

Methods

Results

Conclusion