Catalogue Search | MBRL
Are you sure you want to remove the book from the shelf?
{{itemTitle}}
80,826
result(s) for
"Hate speech."
Sort by:
A Literature Review of Textual Hate Speech Detection Methods and Datasets
Online toxic discourses could result in conflicts between groups or harm to online communities. Hate speech is complex and multifaceted harmful or offensive content targeting individuals or groups. Existing literature reviews have generally focused on a particular category of hate speech, and to the best of our knowledge, no review has been dedicated to hate speech datasets. This paper systematically reviews textual hate speech detection systems and highlights their primary datasets, textual features, and machine learning models. The results of this literature review are integrated with content analysis, resulting in several themes for 138 relevant papers. This study shows several approaches that do not provide consistent results in various hate speech categories. The most dominant sets of methods combine more than one deep learning model. Moreover, the analysis of several hate speech datasets shows that many datasets are small in size and are not reliable for various tasks of hate speech detection. Therefore, this study provides the research community with insights and empirical evidence on the intrinsic properties of hate speech and helps communities identify topics for future work.
Journal Article
Resources and benchmark corpora for hate speech detection
Hate Speech in social media is a complex phenomenon, whose detection has recently gained significant traction in the Natural Language Processing community, as attested by several recent review works. Annotated corpora and benchmarks are key resources, considering the vast number of supervised approaches that have been proposed. Lexica play an important role as well for the development of hate speech detection systems. In this review, we systematically analyze the resources made available by the community at large, including their development methodology, topical focus, language coverage, and other factors. The results of our analysis highlight a heterogeneous, growing landscape, marked by several issues and venues for improvement.
Journal Article
Just words : on speech and hidden harm
We all know that speech can be harmful. But what are the harms and how exactly does the speech in question brings those harms about? Mary Kate McGowan identifies a previously overlooked mechanism by which speech constitutes, rather than merely causes, harm. She argues that speech constitutes harm when it enacts a norm that prescribes that harm. McGowan illustrates this theory by considering many categories of speech including sexist remarks, racist hate speech, pornography, verbal triggers for stereotype threat, micro-aggressions, political dog whistles, slam poetry, and even the hanging of posters. Just Words explores a variety of harms - such as oppression, subordination, discrimination, domination, harassment, and marginalization - and ways in which these harms can be remedied.
Book
Emotionally Informed Hate Speech Detection: A Multi-target Perspective
Hate Speech and harassment are widespread in online communication, due to users' freedom and anonymity and the lack of regulation provided by social media platforms. Hate speech is topically focused (misogyny, sexism, racism, xenophobia, homophobia, etc.), and each specific manifestation of hate speech targets different vulnerable groups based on characteristics such as gender (misogyny, sexism), ethnicity, race, religion (xenophobia, racism, Islamophobia), sexual orientation (homophobia), and so on. Most automatic hate speech detection approaches cast the problem into a binary classification task without addressing either the
topical focus
or the
target-oriented
nature of hate speech. In this paper, we propose to tackle, for the first time, hate speech detection from a multi-target perspective. We leverage manually annotated datasets, to investigate the problem of transferring knowledge from different datasets with different topical focuses and targets. Our contribution is threefold: (1) we explore the ability of hate speech detection models to capture common properties from topic-generic datasets and transfer this knowledge to recognize specific manifestations of hate speech; (2) we experiment with the development of models to detect both topics (racism, xenophobia, sexism, misogyny) and hate speech targets, going beyond standard binary classification, to investigate
how to detect hate speech at a finer level of granularity
and
how to transfer knowledge across different topics and targets
; and (3) we study the impact of affective knowledge encoded in sentic computing resources (SenticNet, EmoSenticNet) and in semantically structured hate lexicons (HurtLex) in determining specific manifestations of hate speech. We experimented with different neural models including multitask approaches. Our study shows that: (1) training a model on a combination of several (training sets from several) topic-specific datasets is more effective than training a model on a topic-generic dataset; (2) the multi-task approach outperforms a single-task model when detecting both the hatefulness of a tweet and its topical focus in the context of a multi-label classification approach; and (3) the models incorporating EmoSenticNet emotions, the first level emotions of SenticNet, a blend of SenticNet and EmoSenticNet emotions or affective features based on Hurtlex, obtained the best results. Our results demonstrate that multi-target hate speech detection from existing datasets is feasible, which is a first step towards hate speech detection for a specific topic/target when dedicated annotated data are missing. Moreover, we prove that domain-independent affective knowledge, injected into our models, helps finer-grained hate speech detection.
Journal Article
Free Speech and Hate Speech in the United States
Free Speech and Hate Speech in the United States explores the concept and treatment of hate speech in light of escalating social tensions in the global twenty-first century, proposing a shift in emphasis from the negative protection of individual rights toward a more positive support of social equality.
Drawing on Axel Honneth’s theory of recognition, the author develops a two-tiered framework for free speech analysis that will promote a strategy for combating hate speech. To illustrate how this framework might impact speech rights in the United States, she looks specifically at hate speech in the context of symbolic speech, disparaging speech, Internet speech, and speech on college campuses.
Entering into an ongoing debate about the role of speech in society, this book will be of key importance to First Amendment scholars, and to scholars and students of communication studies, media studies, media law, political science, feminist studies, American studies, and history.
eBook
Hate : why we should resist it with free speech, not censorship
\"Dispelling rampant confusion about \"hate speech,\" this book explains how U.S. law appropriately distinguishes between punishable and protected discriminatory speech. It shows that more speech-restrictive laws consistently have suppressed vital expression about public issues, targeting minority viewpoints and speakers; and that \"counterspeech\" has more effectively promoted equality and societal harmony\"--Provided by publisher.
Book
A Deep Learning Approach for Automatic Hate Speech Detection in the Saudi Twittersphere
With the rise of hate speech phenomena in the Twittersphere, significant research efforts have been undertaken in order to provide automatic solutions for detecting hate speech, varying from simple machine learning models to more complex deep neural network models. Despite this, research works investigating hate speech problem in Arabic are still limited. This paper, therefore, aimed to investigate several neural network models based on convolutional neural network (CNN) and recurrent neural network (RNN) to detect hate speech in Arabic tweets. It also evaluated the recent language representation model bidirectional encoder representations from transformers (BERT) on the task of Arabic hate speech detection. To conduct our experiments, we firstly built a new hate speech dataset that contained 9316 annotated tweets. Then, we conducted a set of experiments on two datasets to evaluate four models: CNN, gated recurrent units (GRU), CNN + GRU, and BERT. Our experimental results in our dataset and an out-domain dataset showed that the CNN model gave the best performance, with an F1-score of 0.79 and area under the receiver operating characteristic curve (AUROC) of 0.89.
Journal Article