Thou shalt not hate: Countering Online Hate Speech

By Binny Mathew, Hardik Tharad, Subham Rajgaria, Prajwal Singhania, S. Maity, Pawan Goyal, Animesh Mukherjee. 2018

219 citations recorded by the source corpus.

Hate content in social media is ever increasing. While Facebook, Twitter, Google have attempted to take several steps to tackle the hateful content, they have mostly been unsuccessful. Counterspeech is seen as an effective way of tackling the online hate without any harm to the freedom of speech. Thus, an alternative strategy for these platforms could be to promote counterspeech as a defense against hate content. However, in order to have a successful promotion of such counterspeech, one has to have a deep understanding of its dynamics in the online world. Lack of carefully curated data largely inhibits such understanding. In this paper, we create and release the first ever dataset for counterspeech using comments from YouTube. The data contains 13,924 manually annotated comments where the labels indicate whether a comment is a counterspeech or not. This data allows us to perform a rigorous measurement study characterizing the linguistic structure of counterspeech for the first time. This analysis results in various interesting insights such as: the counterspeech comments receive much more likes as compared to the noncounterspeech comments, for certain communities majority of the non-counterspeech comments tend to be hate speech, the different types of counterspeech are not all equally effective and the language choice of users posting counterspeech is largely different from those posting non-counterspeech as revealed by a detailed psycholinguistic analysis. Finally, we build a set of machine learning models that are able to automatically detect counterspeech in YouTube videos with an F1-score of 0.71. We also build multilabel models that can detect different types of counterspeech in a comment with an F1-score of 0.60.

Subfields: Artificial Intelligence, Communication, Information Systems, Natural Language Processing, Safety, Robustness & Interpretability

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 Communication

In Information Systems

In Natural Language Processing

In Safety, Robustness & Interpretability

Citations in the corpus

Language Generation Models Can Cause Harm: So What Can We Do About It? An Actionable Survey (2022, background): “, 2020) Toxicity Adding safer example data (Mathew et al., 2018)”
HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection (2020, methodology): “In case of Gab, we use the dataset provided by Mathew et al. (2019a).”
Latent Hatred: A Benchmark for Understanding Implicit Hate Speech (2021, background): “Our work also has implications towards the emerging directions of countering online hate speech (Citron and Norton, 2011; Mathew et al., 2019), detecting online radicaliza-tion (Ferrara et al., 2016) and modeling societal systematic racism, prejudicial expressions, and biases (Davidson et al.,…”
A Just and Comprehensive Strategy for Using NLP to Address Online Abuse (2019, background): “Prior work has shown counter speech to be effective for limiting the effects of hate speech (Schieb and Preuss, 2016; Mathew et al., 2018; Stroud and Cox, 2018).”
CONAN - COunter NArratives through Nichesourcing: a Multilingual Dataset of Responses to Fight Online Hate Speech (2019, methodology): “Mathew et al. (2018b) collected Youtube comments that contain counter-narratives to YouTube videos of hatred.”
Introducing CAD: the Contextual Abuse Dataset (2021, background): “We use a similar approach to Qian et al. (2019) and Mathew et al. (2019) who also treat counter speech as a relational act that responds to, and challenges, actual abuse.”
Human-Machine Collaboration Approaches to Build a Dialogue Dataset for Hate Speech Countering (2022, background): “…shown to be effective in reducing linguistic violence (Be-nesch, 2014; Gagliardone et al., 2015; Schieb and Preuss, 2016; Silverman et al., 2016; Mathew et al., 2019) and in changing the viewpoints of bystanders (Allison and Bussey, 2016; Anderson et al., 2014), they are beginning to be…”
Developing an online hate classifier for multiple social media platforms (2020, result): “Compared to the other classifiers, XGBoost is slightly rarer in the literature, although we could locate two previous studies using it in the online hate context [27, 68].”
Generating Counter Narratives against Online Hate Speech: Data and Strategies (2020, methodology): “Recent work has proved that counter-narratives are effective in hate countering (Benesch, 2014; Silverman et al., 2016; Schieb and Preuss, 2016; Stroud and Cox, 2018; Mathew et al., 2019).”