A Survey on Hate Speech Detection using Natural Language Processing
Published 1 January 2017Open access
Anna Grau Schmidt, Michael Wiegand
Citations1,389
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
A survey on hate speech detection describes key areas that have been explored to automatically recognize these types of utterances using natural language processing and discusses limits of those approaches.
Abstract
This paper presents a survey on hate speech detection.Given the steadily growing body of social media content, the amount of online hate speech is also increasing.Due to the massive scale of the web, methods that automatically detect hate speech are required.Our survey describes key areas that have been explored to automatically recognize these types of utterances using natural language processing.We also discuss limits of those approaches.
Keywords
Computer Science
Journal of Machine Learning ResearchLatent dirichlet allocation
27,049 Citations2003David M. Blei, Andrew Y. Ng +1 more
arXiv (Cornell University)Efficient Estimation of Word Representations in Vector Space
18,050 Citations2013Tomáš Mikolov, Kai Chen +2 more
Two novel model architectures for computing continuous vector representations of words from very large data sets are proposed and it is shown that these vectors provide state-of-the-art performance on the authors' test set for measuring syntactic and semantic word similarities.
arXiv (Cornell University)Efficient Estimation of Word Representations in Vector Space
11,710 Citations2013Tomáš Mikolov, Kai Chen +2 more
arXiv (Cornell University)Distributed Representations of Sentences and Documents
5,128 Citations2014Quoc V. Le, Tomáš Mikolov
Paragraph Vector is an unsupervised algorithm that learns fixed-length feature representations from variable-length pieces of texts, such as sentences, paragraphs, and documents, and its construction gives the algorithm the potential to overcome the weaknesses of bag-of-words models.
Class-based n -gram models of natural language
2,893 Citations1992Peter F. Brown, P.V. deSouza +3 more
This work addresses the problem of predicting a word from previous words in a sample of text and discusses n-gram models based on classes of words, finding that these models are able to extract classes that have the flavor of either syntactically based groupings or semanticallybased groupings, depending on the nature of the underlying statistics.
Hateful Symbols or Hateful People? Predictive Features for Hate Speech Detection on Twitter
1,655 Citations2016Zeerak Waseem, Dirk Hovy
A list of criteria founded in critical race theory is provided, and these are used to annotate a publicly available corpus of more than 16k tweets and present a dictionary based the most indicative words in the data.
BT Technology JournalConceptNet — A Practical Commonsense Reasoning Tool-Kit
1,560 Citations2004H Liu, Pankaj Kumar Singh
Journal of the American Society for Information Science and TechnologySentiment strength detection in short informal text
1,450 Citations2010Mike Thelwall, Kevan Buckley +3 more
A huge number of informal messages are posted every day in social network sites, blogs, and discussion forums, and emotions seem to be frequently important in these texts for expressing friendship, love and affection.
Abusive Language Detection in Online User Content
1,107 Citations2016Chikashi Nobata, Joel Tetreault +3 more
A machine learning based method to detect hate speech on online user comments from two domains which outperforms a state-of-the-art deep learning approach and a corpus of user comments annotated for abusive language, the first of its kind.
Hate Speech Detection with Comment Embeddings
712 Citations2015Nemanja Djuric, Jing Zhou +4 more
This work proposes to learn distributed low-dimensional representations of comments using recently proposed neural language models, that can then be fed as inputs to a classification algorithm, resulting in highly efficient and effective hate speech detectors.
Detecting Offensive Language in Social Media to Protect Adolescent Online Safety
630 Citations2012Ying Chen, Yilu Zhou +2 more
This work proposes the Lexical Syntactic Feature (LSF) architecture to detect offensive content and identify potential offensive users in social media, and incorporates a user's writing style, structure and specific cyber bullying content as features to predict the user's potentiality to send out offensive content.
Policy & InternetCyber Hate Speech on Twitter: An Application of Machine Classification and Statistical Modeling for Policy and Decision Making
596 Citations2015Pete Burnap, Matthew Williams
It is demonstrated how the results of the classifier can be robustly utilized in a statistical model used to forecast the likely spread of cyber hate in a sample of Twitter data.
Sarcasm as Contrast between a Positive Sentiment and Negative Situation
591 Citations2013Ellen Riloff, Ashequl Qadir +4 more
This work develops a sarcasm recognizer that automatically learns lists of positive sentiment phrases and negative situation phrases from sarcastic tweets and shows that identifying contrasting contexts using the phrases learned through bootstrapping yields improved recall for sarcasm recognition.
Detecting Hate Speech on the World Wide Web
514 Citations2012William B. Warner, Julia Hirschberg
The definition of hate speech, the collection and annotation of the hate speech corpus, and a mechanism for detecting some commonly used methods of evading common "dirty word" filters are described.
International Journal of Multimedia and Ubiquitous EngineeringA Lexicon-based Approach for Hate Speech Detection
495 Citations2015Njagi Dennis Gitari, Zuping Zhang +2 more
The goal of the research is to create a model classifier that uses sentiment analysis techniques and in particular subjectivity detection to not only detect that a given sentence is subjective but also to identify and rate the polarity of sentiment expressions.
Proceedings of the AAAI Conference on Artificial IntelligenceLocate the Hate: Detecting Tweets against Blacks
457 Citations2013Irene Kwok, Yuzhou Wang
A supervised machine learning approach is applied, employing inexpensively acquired labeled data from diverse Twitter accounts to learn a binary classifier for the labels “racist” and “nonracist", which has a 76% average accuracy on individual tweets, suggesting that with further improvements, this work can contribute data on the sources of anti-black hate speech.
ACM Transactions on Interactive Intelligent SystemsCommon Sense Reasoning for Detection, Prevention, and Mitigation of Cyberbullying
417 Citations2012Karthik Dinakar, Birago Jones +3 more
An “air traffic control”-like dashboard is proposed, which alerts moderators to large-scale outbreaks that appear to be escalating or spreading and helps them prioritize the current deluge of user complaints.
EPJ Data ScienceUs and them: identifying cyber hate on Twitter across multiple protected characteristics
397 Citations2016Pete Burnap, Matthew Williams
This work uses text parsing to extract typed dependencies, which represent syntactic and grammatical relationships between words, and are shown to capture ‘othering’ language - consistently improving machine classification for different types of cyber hate beyond the use of a Bag of Words and known hateful terms.
Lecture notes in computer scienceImproving Cyberbullying Detection with User Context
382 Citations2013Maral Dadvar, Dolf Trieschnigg +2 more
It is shown that taking user context into account improves the detection of cyberbullying.
Lecture notes in computer scienceAutomatic Crime Prediction Using Events Extracted from Twitter Posts
339 Citations2012Xiaofeng Wang, Matthew S. Gerber +1 more
This approach is based on the automatic semantic analysis and understanding of natural language Twitter posts, combined with dimensionality reduction via latent Dirichlet allocation and prediction via linear modeling, and tested on the task of predicting future hit-and-run crimes.
International Journal of Human-Computer StudiesMining communities and their relationships in blogs: A study of online hate groups
322 Citations2006Michael Chau, Jennifer Xu
A semi-automated approach that consists of four modules, namely blog spider, information extraction, network analysis, and visualization is applied to identify and analyze a selected set of 28 anti-Blacks hate groups on Xanga, one of the most popular blog hosting sites.
Learning from Bullying Traces in Social Media
306 Citations2012Junming Xu, Kwang-Sung Jun +2 more
Evidence is presented that social media, with appropriate natural language processing techniques, can be a valuable and abundant data source for the study of bullying in both worlds.
Detecting offensive tweets via topical feature discovery over a large scale twitter corpus
270 Citations2012Guang Xiang, Bin Fan +3 more
This work proposes a novel semi-supervised approach for detecting profanity-related offensive content in Twitter that exploits linguistic regularities in profane language via statistical topic modeling on a huge Twitter corpus, and detects offensive tweets using automatically these generated features.
Lecture notes in computer scienceOffensive Language Detection Using Multi-level Classification
257 Citations2010Amir H. Razavi, Diana Inkpen +2 more
An automatic flame detection method is described which extracts features at different conceptual levels and applies multi-level classification for flame detection and there is an auxiliary weighted pattern repository which improves accuracy by matching the text to its graded entries.
Social Network Analysis and MiningTweeting the terror: modelling the social media reaction to the Woolwich terrorist attack
238 Citations2014Pete Burnap, Matthew Williams +7 more
Novel findings are reported that identify that the sentiment expressed in the tweet is statistically significantly predictive of both size and survival of information flows of this nature.
The British Journal of CriminologyCyberhate on Social Media in the aftermath of Woolwich: A Case Study in Computational Criminology and Big Data
212 Citations2015Matthew Williams, Pete Burnap
Do Characters Abuse More Than Words?
195 Citations2016Yashar Mehdad, Joel Tetreault
This study investigates the effectiveness of word and character n-grams for abusive language detection in user-generated online comments and shows the power of character-based features for detecting abusive language.
Improved cyberbullying detection using gender information
180 Citations2012Maral Dadvar, Franciska de Jong +2 more
IEEE Intelligent SystemsUS Domestic Extremist Groups on the Web: Link and Content Analysis
178 Citations2005Yilu Zhou, Edna Reid +3 more
A study of semiautomated methodologies to capture and organize domestic extremist Web site data revealed interorganizational structures and cluster affinities that coincided with both domain expert knowledge and earlier manual research.
Measuring the Reliability of Hate Speech Annotations: The Case of the European Refugee Crisis
176 Citations2016Björn Roß, Michael Rist +4 more
It is concluded that the presence of hate speech should perhaps not be considered a binary yes-or-no decision, and raters need more detailed instructions for the annotation, which was very low overall.
Technological Forecasting and Social ChangeDetecting tension in online communities with computational Twitter analysis
170 Citations2013Pete Burnap, Omer Rana +6 more
Results indicate that a combination of conversation analysis methods and text mining outperforms a number of machine learning approaches and a sentiment analysis tool at classifying tension levels in individual tweets.
Smokey: automatic recognition of hostile messages
170 Citations1997Ellen Spertus
Some approaches to flame recognition are described, mcluding a prototype system, Smokey, which builds a 47-element feature vector based on the syntax and semantics of each sentence, combining the vectors for the sentences within each message.
Journal of the American Society for Information Science and TechnologyAutomatic identification of personal insults on social news sites
154 Citations2011Sara Owsley Sood, Elizabeth F. Churchill +1 more
This paper addresses the issue of off-topic, negative comments with malicious intent through a machine learning approach to automatic detection of inappropriate negative user contributions, and shows great potential for semiautomated community management.
Ghent University Academic Bibliography (Ghent University)Detection and Fine-Grained Classification of Cyberbullying Events
154 Citations2015Cynthia Van Hee, Els Lefever +6 more
A new scheme for cyberbullying annotation is developed and applied, which describes the presence and severity of cyberbullies, a post author's role (harasser, victim or bystander) and a number of fine-grained categories related to cyber Bullying, such as insults and threats.
Proceedings of the International AAAI Conference on Web and Social MediaAnalyzing the Targets of Hate in Online Social Media
152 Citations2021Leandro Silva, Mainack Mondal +3 more
This paper provides the first of a kind systematic large scale measurement study of the main targets of hate speech in online social media, gathering traces from two social media systems: Whisper and Twitter and developing and validate a methodology to identify hate speech on both these systems.
Profanity use in online communities
145 Citations2012Sara Owsley Sood, Judd Antin +1 more
Analysis of comments from a social news site is provided to provide evidence that current profanity detection systems are performing poorly and evaluate the cases on which they fail, and to address community differences regarding creation/tolerance of profanity.
International Joint Conference on Artificial IntelligenceContent-driven detection of cyberbullying on the instagram social network
130 Citations2016Haoti Zhong, Hao Li +5 more
This work investigates use of posted images and captions for improved detection of bullying in response to shared content, and identifies the importance of these advanced features in assisting detection of cyberbullying in posted comments.
Repositorio InstitucionalHate speech, machine classification and statistical modelling of information flows on Twitter: interpretation and communication for policy decision making
110 Citations2014Pete Burnap, Matthew Williams
A supervised machine learning text classifier is trained and tested to distinguish between hateful and/or antagonistic responses with a focus on race, ethnicity or religion; and more general responses, and it is demonstrated how the results can be robustly utilized in a statistical model used to forecast the likely spread of hate speech in a sample of Twitter data.
arXiv (Cornell University)Detection of Cyberbullying Incidents on the Instagram Social Network
91 Citations2015Homa Hosseinmardi, Sabrina Arredondo Mattson +4 more
arXiv (Cornell University)Prediction of Cyberbullying Incidents on the Instagram Social Network
77 Citations2015Homa Hosseinmardi, Sabrina Arredondo Mattson +4 more