Locate the Hate: Detecting Tweets against Blacks

By Irene Kwok, Yuzhou Wang. 2013

473 citations recorded by the source corpus.

Although the social medium Twitter grants users freedom of speech, its instantaneous nature and retweeting features also amplify hate speech. Because Twitter has a sizeable black constituency, racist tweets against blacks are especially detrimental in the Twitter community, though this effect may not be obvious against a backdrop of half a billion tweets a day.1 We apply a supervised machine learning approach, employing inexpensively acquired labeled data from diverse Twitter accounts to learn a binary classifier for the labels “racist” and “nonracist.” The classifier has a 76% average accuracy on individual tweets, suggesting that with further improvements, our work can contribute data on the sources of anti-black hate speech.

Subfields: Artificial Intelligence, Information Systems, Natural Language Processing, AI Ethics, Fairness & Society

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Information Systems

In Natural Language Processing

In AI Ethics, Fairness & Society

Citations in the corpus

Challenges in Detoxifying Language Models (2021, background): “While detecting hate speech and offensive language (Warner and Hirschberg, 2012; Kwok and Wang, 2013; Davidson et al., 2017; Zampieri et al., 2019), mostly in the context of online community moderation, has long been a subject of research; the”
The Risk of Racial Bias in Hate Speech Detection (2019, background): “Many datasets have been created, but most are either small-scale pilots (∼100 instances; Kwok and Wang, 2013; Burnap and Williams, 2015; Zhang et al., 2018), or focus on other domains (e.”
Ex Machina: Personal Attacks Seen at Scale (2016, background): “In order to get reliable estimates of whether a comment is a personal attack, each comment was labeled by at least 10 different Crowdflower annotators.”
Automated Hate Speech Detection and the Problem of Offensive Language (2017, background): “…tend to have high recall but lead to high rates of false positives since the presence of offensive words can lead to the misclassiﬁcation of tweets as hate speech (Kwok and Wang 2013; Burnap and Williams 1 Facebook’s policy can be found here: www.facebook. com/communitystandards#hate-speech .”
Racial Bias in Hate Speech and Abusive Language Detection Datasets (2019, background): “However the variant with the “-a” sufﬁx is typically used innocuously by African-Americans (Kwok and Wang, 2013), indeed our results indicate that it is used far more frequently in black-aligned tweets (although it is still used by many white people).”
A Survey on Hate Speech Detection using Natural Language Processing (2017, methodology): “The actual term hate speech is used by Warner and Hirschberg (2012), Burnap and Williams (2015), Silva et al. (2016), Djuric et al. (2015), Gitari et al. (2015), Williams and Bur-nap (2015) and Kwok and Wang (2013).”
Hate Speech Dataset from a White Supremacy Forum (2018, background): “Also in this line, Kwok and Wang (2013) target anti-black hate speech.”
Challenges for Toxic Comment Classification: An In-Depth Error Analysis (2018, background): “…classiﬁcation tasks, related work considers different aspects of toxic language, such as “racism” (Greevy and Smeaton, 2004; Waseem, 2016; Kwok and Wang, 2013) and “sexism” (Waseem and Hovy, 2016; Jha and Mamidi, 2017), or the severity of toxicity (David-son et al., 2017; Sharma et al., 2018).”
Understanding Abuse: A Typology of Abusive Language Detection Subtasks (2017, background): “another n*gger off the streets!!” (Kwok and Wang, 2013).”
SemEval-2019 Task 6: Identifying and Categorizing Offensive Language in Social Media (OffensEval) (2019, background): “Hate speech identification: This is the most studied abusive language detection task (Kwok and Wang, 2013; Burnap and Williams, 2015; Djuric et al., 2015).”
Analyzing the Targets of Hate in Online Social Media (2016, background): “Most existing eﬀorts to measure hate speech require knowing the hate words or hate targets apriori [8].”
Predicting the Type and Target of Offensive Posts in Social Media (2019, background): “, 2013), toxic comments1, hate speech (Kwok and Wang, 2013; Djuric et al., 2015; Burnap and Williams, 2015; Davidson et al., 2017; Malmasi and Zampieri, 2017, 2018), and offensive language (Wiegand et al.”
Fighting Offensive Language on Social Media with Unsupervised Text Style Transfer (2018, methodology): “this problem by using different machine learning models to detect abusive behavior (Xiang et al., 2012; Warner and Hirschberg, 2012; Kwok and Wang, 2013; Wang et al., 2014; Nobata et al., 2016; Burnap and Williams, 2015; Davidson et al., 2017; Founta et al., 2018).”
Interpretable Multi-Modal Hate Speech Detection (2021, methodology): “Most of the current methods are trained primarily using the textual features containing limited examples of hate content and the results of their evaluations suggest that it is really difﬁcult to detect hateful content without any additional contextual information (Kwok & Wang, 2013).”
Developing an online hate classifier for multiple social media platforms (2020, methodology): “In the context of online hate detection, NB has been applied at least by Dinakar et al. [80], Chen et al. [81], and Kwok and Wang [82].”
Detecting Hate Speech in Social Media (2017, background): “Examples of such studies include the work by Kwok and Wang (2013), Djuric et al. (2015), Burnap and Williams (2015), and by No-bata et al. (2016).”
A Unified Deep Learning Architecture for Abuse Detection (2018, methodology): “Some works try to detect more specific types of hateful behavior, such as racism [22, 24] or sexism [20].”
Cross-Domain Detection of Abusive Language Online (2018, background): “Traditional machine learning approaches to detecting abusive language include the naive Bayes classiﬁer (Kwok and Wang, 2013; Chen et al., 2012; Dinakar et al., 2011), logistic regression (Waseem and Hovy, 2016; Davidson et al., 2017; Wulczyn et al., 2017; Burnap and Williams, 2015), and support…”
Crowdsourcing Subjective Tasks: The Case Study of Understanding Toxicity in Online Discussions (2019, background): “Similarly, as seen in section 1.1, individual annotator differences make it difficult to identify such behavior consistently, and thus annotation tasks tend to result in high disagreement between annotators [27].”
Challenges in discriminating profanity from hate speech (2017, background): “In an attempt to “locate the hate”, Kwok and Wang (2013) collect two classes of tweets and use unigrams to distinguish them.”