Advances in Machine Learning Algorithms for Hate Speech Detection in Social Media: A Review

Abstract

The aim of this paper is to review machine learning (ML) algorith ms and techniques for hate speech detection in social media (SM). Hate speech problem is normally model as a text classification task. In this study, we examined the basic baseline components of hate speech classification using ML algorithms. There are five basic baseline componentsdata collection and exploration, feature extraction, dimensionality reduction, classifier selection and training, and model evaluation, were reviewed. There have been improvements in ML algorithms that were employed for hate speech detection over time. New datasets and different performance metrics have been proposed in the literature. To keep the researchers informed regarding these trends in the automatic detection of hate speech, it calls for a comprehensive and an updated state-of-the-art. The contributions of this study are two-fold. First to equip the readers with the necessary information on the critical steps involved in hate speech detection using ML algorithms. Secondly, the weaknesses and strengths of each method is critically evaluated to guide researchers in the algorithm choice dilemma. The different variants of ML techniques were reviewed which include classical ML, ensemble approach and deep learning methods. Researchers and professionals alike will benefit immensely from this study.

Tackling racial bias in automated online hate detection: Towards fair and accurate detection of hateful users with geometric deep learning

“…Notably, incorporating sentence-level context has been shown to improve hateful content detection, with several papers deploying transformer-based models such as Bidirectional Encoder Representation from Transformers (BERT) to better distinguish between hateful and non-hateful content, even when they have lexical similarities [37,57]. Indeed, as Mullah and Zainon [46] write in their comprehensive review of ML methods for automated hate speech detection, deep learning techniques leveraging such language models can considerably improve how context-dependent hate speech is detected. Liu et al [36], for example, leverage transfer learning by fine-tuning a pre-trained BERT model to produce the most accurate classifier for offensive language in the SemEval 2019 Task 6 competition.…”

Down the Rabbit Hole: Detecting Online Extremism, Radicalisation, and Politicised Hate Speech

“…Studies seldom cross-examine models and evaluate the performance between non-textual network analysis (a 'who-knows-who' approach), textual, and/or multimedia approaches for ERH detection. While we identified ten prior literature reviews for hateful content detection, none consider the similarities and definitional nuance between ERH concepts and what Extremism, Hate Speech, or Radicalisation means in practice by researchers [2,5,20,42,43,51,82,97,110,114]. Evaluating the consensus for ERH definitions, dataset collection and extraction techniques, model choice and performance are all essential to create ethical models without injurious censorship or blowback.…”

Multi-Model Learning to Detect Twitter Hate Speech

“…The TF_IDF statistic is intended to assess the relevance of a word in a set of texts (or corpus). It is represented by an equation (1). The frequency of the term, TF (t, d), is the frequency of occurrence of the term t internal document d. , , ( , )…”

“…Nowadays online social networks (OSN) are the most important and fastest means of communication. In fact, it is the popular way to communicate with each other [1]. Offers users freedom of expression.…”