Hierarchical CVAE for Fine-Grained Hate Speech Classification

By Jing Qian, Mai Elsherief, Elizabeth M. Belding-Royer, William Yang Wang. 2018

47 citations recorded by the source corpus.

Existing work on automated hate speech detection typically focuses on binary classification or on differentiating among a small set of categories. In this paper, we propose a novel method on a fine-grained hate speech classification task, which focuses on differentiating among 40 hate groups of 13 different hate group categories. We first explore the Conditional Variational Autoencoder (CVAE) as a discriminative model and then extend it to a hierarchical architecture to utilize the additional hate category information for more accurate prediction. Experimentally, we show that incorporating the hate category information for training can significantly improve the classification performance and our proposed model outperforms commonly-used discriminative models.

Subfields: Artificial Intelligence, Computer Networks and Communications, 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 Computer Networks and Communications

In Natural Language Processing

In Safety, Robustness & Interpretability

Citations in the corpus

HateCheck: Functional Tests for Hate Speech Detection Models (2020, background): “The use of humour, for instance, has been highlighted as an important challenge for hate speech research (van Aken et al., 2018; Qian et al., 2018; Vidgen et al., 2020a).”
Challenges and frontiers in abusive content detection (2019, background): “…can be leveraged to address this: Qian et al. report a model which identifies the origins of posts from 40 far right hate groups on Twitter (Qian, ElSherief, Belding, & Wang, 2018) Chandrasekharan et al similarly build a model that identifies whether content is from 9 different communities…”
HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection (2020, methodology): “To tackle this, various methods have been proposed for hate speech detection (Burnap and Williams 2016; Ribeiro et al. 2018; Zhang, Robinson, and Tepper 2018; Qian et al. 2018a).”
Resources and benchmark corpora for hate speech detection: a systematic review (2020, background): “This is one of the only two corpora built for the purpose of automatically generating CS. Qian et al. (2018) (QEBW)—3,5 millions hateful tweets in English, associated to 40 U.S.-based hate groups and referencing 13 hate ideologies.”
Multilingual and Multi-Aspect Hate Speech Analysis (2019, background): “On the other hand, Qian et al. (2018) Waseem and Hovy (2016) in order to study how hate speech affects the popularity of a tweet, but discovered that some tweets have been deleted.”
Lifelong Learning of Hate Speech Classification on Social Media (2021, methodology): “Therefore, instead of differentiating normal posts from the other offensive ones, Qian et al. (2018a) propose a more ﬁne-grained hate speech classiﬁcation task that attributes hate groups to individual tweets.”
Spread of Hate Speech in Online Social Media (2018, background): “Since Gab does not have any policy for hatespeech, we use the guidelines defined by Twitter 2 for this task.”