Impact of politically biased data on hate speech classification
01 Nov 2020-pp 54-64
TL;DR: It is shown that political bias negatively impairs the performance of hate speech classifiers and an explainable machine learning model can help to visualize such bias within the training data.
Abstract: One challenge that social media platforms are facing nowadays is hate speech. Hence, automatic hate speech detection has been increasingly researched in recent years - in particular with the rise of deep learning. A problem of these models is their vulnerability to undesirable bias in training data. We investigate the impact of political bias on hate speech classification by constructing three politically-biased data sets (left-wing, right-wing, politically neutral) and compare the performance of classifiers trained on them. We show that (1) political bias negatively impairs the performance of hate speech classifiers and (2) an explainable machine learning model can help to visualize such bias within the training data. The results show that political bias in training data has an impact on hate speech classification and can become a serious issue.
Citations
More filters
18 Jan 2011
TL;DR: In echten (analogen) Leben sind wir eher selten offenen Beleidigungen oder Hass ausgesetzt.
Abstract: Im echten (analogen) Leben sind wir eher selten offenen Beleidigungen oder Hass ausgesetzt. Im Internet hingegen lesen wir deutlich häufiger wütende, hasserfüllte Kommentare, Snaps, Tweets und Posts gegen uns oder gegen andere. Für diesen Hass im Netz gibt es den Begriff "Hate Speech". Hate Speech ist ein Phänomen dem rund zwei Drittel (67 Prozent) der Onliner schon einmal begegnet sind, wie eine forsa-Umfrage im Auftrag der Landesanstalt für Medien NRW (LfM) zeigt.
204 citations
01 Nov 2020
TL;DR: This work investigates annotator bias using classification models trained on data from demographically distinct annotator groups, and shows that demographic features, such as first language, age, and education, correlate with significant performance differences.
Abstract: Machine learning is recently used to detect hate speech and other forms of abusive language in online platforms. However, a notable weakness of machine learning models is their vulnerability to bias, which can impair their performance and fairness. One type is annotator bias caused by the subjective perception of the annotators. In this work, we investigate annotator bias using classification models trained on data from demographically distinct annotator groups. To do so, we sample balanced subsets of data that are labeled by demographically distinct annotators. We then train classifiers on these subsets, analyze their performances on similarly grouped test sets, and compare them statistically. Our findings show that the proposed approach successfully identifies bias and that demographic features, such as first language, age, and education, correlate with significant performance differences.
49 citations
TL;DR: In this paper, a text-based hate speech detection model was proposed for detecting hate speech in social media discourse, which is based on Latent Semantic Analysis (LSA) for dimensionality reduction.
Abstract: There is an enormous growth of social media which fully promotes freedom of expression through its anonymity feature. Freedom of expression is a human right but hate speech towards a person or group based on race, caste, religion, ethnic or national origin, sex, disability, gender identity, etc. is an abuse of this sovereignty. It seriously promotes violence or hate crimes and creates an imbalance in society by damaging peace, credibility, and human rights, etc. Detecting hate speech in social media discourse is quite essential but a complex task. There are different challenges related to appropriate and social media-specific dataset availability and its high-performing supervised classifier for text-based hate speech detection. These issues are addressed in this study, which includes the availability of social media-specific broad and balanced dataset, with multi-class labels and its respective automatic classifier, a dataset with language subtleties, dataset labeled under a comprehensive definition and well-defined rules, dataset labeled with the strong agreement of annotators, etc. Addressing different categories of hate separately, this paper aims to accurately predict their different forms, by exploring a group of text mining features. Two distinct groups of features are explored for problem suitability. These are baseline features and self-discovered/new features. Baseline features include the most commonly used effective features of related studies. Exploration found a few of them, like character and word n-grams, dependency tuples, sentiment scores, and count of 1st, 2nd person pronouns are more efficient than others. Due to the application of latent semantic analysis (LSA) for dimensionality reduction, this problem is benefited from the utilization of many complex and non-linear models and CAT Boost performed best. The proposed model is compared with related studies in addition to system baseline models. The results produced by the proposed model were much appreciating.
27 citations
TL;DR: It is found that rater identity is a statistically significant factor in how raters will annotate toxicity for identity-related annotations, and how using raters that self-identify with the subjects of comments can create more inclusive machine learning models, and provide more nuanced ratings than those by random raters.
Abstract: Machine learning models are commonly used to detect toxicity in online conversations. These models are trained on datasets annotated by human raters. We explore how raters' self-described identities impact how they annotate toxicity in online comments. We first define the concept of Specialized Rater Pools: rater pools formed based on raters' self-described identities, rather than at random. We formed three such rater pools for this study - specialized rater pools of raters from the U.S. who identify as African American, LGBTQ, and those who identify as neither. Each of these rater pools annotated the same set of comments, which contains many references to these identity groups. We found that rater identity is a statistically significant factor in how raters will annotate toxicity for identity-related annotations. Using preliminary content analysis, we examined the comments with the most disagreement between rater pools and found nuanced differences in the toxicity annotations. Next, we trained models on the annotations from each of the different rater pools, and compared the scores of these models on comments from several test sets. Finally, we discuss how using raters that self-identify with the subjects of comments can create more inclusive machine learning models, and provide more nuanced ratings than those by random raters.
24 citations
01 Nov 2020
TL;DR: This study wants to investigate annotator bias — a form of bias that annotators cause due to different knowledge in regards to the task and their subjective perception, and build a graph based on the annotations from the different annotators and apply a community detection algorithm to group the annotators.
Abstract: A challenge that many online platforms face is hate speech or any other form of online abuse. To cope with this, hate speech detection systems are developed based on machine learning to reduce manual work for monitoring these platforms. Unfortunately, machine learning is vulnerable to unintended bias in training data, which could have severe consequences, such as a decrease in classification performance or unfair behavior (e.g., discriminating minorities). In the scope of this study, we want to investigate annotator bias — a form of bias that annotators cause due to different knowledge in regards to the task and their subjective perception. Our goal is to identify annotation bias based on similarities in the annotation behavior from annotators. To do so, we build a graph based on the annotations from the different annotators, apply a community detection algorithm to group the annotators, and train for each group classifiers whose performances we compare. By doing so, we are able to identify annotator bias within a data set. The proposed method and collected insights can contribute to developing fairer and more reliable hate speech classification models.
22 citations
Cites background from "Impact of politically biased data o..."
...Wich et al. (2020) examined the impact of political bias within the data on the classifier’s performance....
[...]
References
More filters
TL;DR: This work proposes a generative model for text and other collections of discrete data that generalizes or improves on several previous models including naive Bayes/unigram, mixture of unigrams, and Hofmann's aspect model.
Abstract: We describe latent Dirichlet allocation (LDA), a generative probabilistic model for collections of discrete data such as text corpora. LDA is a three-level hierarchical Bayesian model, in which each item of a collection is modeled as a finite mixture over an underlying set of topics. Each topic is, in turn, modeled as an infinite mixture over an underlying set of topic probabilities. In the context of text modeling, the topic probabilities provide an explicit representation of a document. We present efficient approximate inference techniques based on variational methods and an EM algorithm for empirical Bayes parameter estimation. We report results in document modeling, text classification, and collaborative filtering, comparing to a mixture of unigrams model and the probabilistic LSI model.
30,570 citations
"Impact of politically biased data o..." refers methods in this paper
...For creating the topic model, we use the Latent Dirichlet Allocation (LDA) algorithm (Blei et al., 2003)....
[...]
Proceedings Article•
03 Jan 2001TL;DR: This paper proposed a generative model for text and other collections of discrete data that generalizes or improves on several previous models including naive Bayes/unigram, mixture of unigrams, and Hof-mann's aspect model, also known as probabilistic latent semantic indexing (pLSI).
Abstract: We propose a generative model for text and other collections of discrete data that generalizes or improves on several previous models including naive Bayes/unigram, mixture of unigrams [6], and Hof-mann's aspect model, also known as probabilistic latent semantic indexing (pLSI) [3]. In the context of text modeling, our model posits that each document is generated as a mixture of topics, where the continuous-valued mixture proportions are distributed as a latent Dirichlet random variable. Inference and learning are carried out efficiently via variational algorithms. We present empirical results on applications of this model to problems in text modeling, collaborative filtering, and text classification.
25,546 citations
TL;DR: An algorithm for suffix stripping is described, which has been implemented as a short, fast program in BCPL, and performs slightly better than a much more elaborate system with which it has been compared.
Abstract: The automatic removal of suffixes from words in English is of particular interest in the field of information retrieval. An algorithm for suffix stripping is described, which has been implemented as a short, fast program in BCPL. Although simple, it performs slightly better than a much more elaborate system with which it has been compared. It effectively works by treating complex suffixes as compounds made up of simple suffixes, and removing the simple suffixes in a number of steps. In each step the removal of the suffix is made to depend upon the form of the remaining stem, which usually involves a measure of its syllable length.
7,572 citations
Proceedings Article•
04 Dec 2017TL;DR: In this article, a unified framework for interpreting predictions, SHAP (SHapley Additive exPlanations), is presented, which assigns each feature an importance value for a particular prediction.
Abstract: Understanding why a model makes a certain prediction can be as crucial as the prediction's accuracy in many applications. However, the highest accuracy for large modern datasets is often achieved by complex models that even experts struggle to interpret, such as ensemble or deep learning models, creating a tension between accuracy and interpretability. In response, various methods have recently been proposed to help users interpret the predictions of complex models, but it is often unclear how these methods are related and when one method is preferable over another. To address this problem, we present a unified framework for interpreting predictions, SHAP (SHapley Additive exPlanations). SHAP assigns each feature an importance value for a particular prediction. Its novel components include: (1) the identification of a new class of additive feature importance measures, and (2) theoretical results showing there is a unique solution in this class with a set of desirable properties. The new class unifies six existing methods, notable because several recent methods in the class lack the proposed desirable properties. Based on insights from this unification, we present new methods that show improved computational performance and/or better consistency with human intuition than previous approaches.
7,309 citations
Proceedings Article•
03 May 2017TL;DR: This work used a crowd-sourced hate speech lexicon to collect tweets containing hate speech keywords and labels a sample of these tweets into three categories: those containinghate speech, only offensive language, and those with neither.
Abstract: A key challenge for automatic hate-speech detection on social media is the separation of hate speech from other instances of offensive language. Lexical detection methods tend to have low precision because they classify all messages containing particular terms as hate speech and previous work using supervised learning has failed to distinguish between the two categories. We used a crowd-sourced hate speech lexicon to collect tweets containing hate speech keywords. We use crowd-sourcing to label a sample of these tweets into three categories: those containing hate speech, only offensive language, and those with neither. We train a multi-class classifier to distinguish between these different categories. Close analysis of the predictions and the errors shows when we can reliably separate hate speech from other offensive language and when this differentiation is more difficult. We find that racist and homophobic tweets are more likely to be classified as hate speech but that sexist tweets are generally classified as offensive. Tweets without explicit hate keywords are also more difficult to classify.
1,425 citations
"Impact of politically biased data o..." refers background in this paper
...Advances in machine learning (ML), however, show that this technology can help to detect hate speech — currently with limited accuracy (Davidson et al., 2017; Schmidt and Wiegand, 2017)....
[...]