Determining Code Words in Euphemistic Hate Speech Using Word Embedding Networks
By Rijul Magu, Jiebo Luo. 2018
67 citations recorded by the source corpus.
While analysis of online explicit abusive language detection has lately seen an ever-increasing focus, implicit abuse detection remains a largely unexplored space. We carry out a study on a subcategory of implicit hate: euphemistic hate speech. We propose a method to assist in identifying unknown euphemisms (or code words) given a set of hateful tweets containing a known code word. Our approach leverages word embeddings and network analysis (through centrality measures and community detection) in a manner that can be generalized to identify euphemisms across contexts- not just hate speech.
Subfields: Artificial Intelligence, Communication, Information Systems, Natural Language Processing
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
- Diyi Yang
- Paul Röttger
- Helen Z. Margetts
- Dong Nguyen
- Mai Elsherief
- Zeerak Talat
- Janet B. Pierrehumbert
- Bertram Vidgen
In Communication
- Mai Elsherief
- Helen Z. Margetts
- Dong Nguyen
- Diyi Yang
- Janet B. Pierrehumbert
- Paul Röttger
- Bertram Vidgen
- Zeerak Talat
In Information Systems
- Zeerak Talat
- David Muchlinski
- Caleb Ziems
- Dong Nguyen
- Helen Z. Margetts
- Diyi Yang
- Jordyn Seybolt
- Mai Elsherief
In Natural Language Processing
- Helen Z. Margetts
- Mai Elsherief
- Diyi Yang
- Dong Nguyen
- Zeerak Talat
- Paul Röttger
- Janet B. Pierrehumbert
- Bertram Vidgen
Citations in the corpus
- HateCheck: Functional Tests for Hate Speech Detection Models (2020, background): “Relatedly, previous work has shown that code words used by hateful users to evade detection are adopted and mostly discarded again within weeks (Magu et al., 2017; Magu and Luo, 2018).”
- Latent Hatred: A Benchmark for Understanding Implicit Hate Speech (2021, background): “…is the linguistic nuance and diversity of the implicit hate class, which includes indirect sarcasm and humor (Waseem and Hovy, 2016; Fortuna and Nunes, 2018), euphemisms (Magu and Luo, 2018), circumlocution (Gao and Huang, 2017), and other symbolic or metaphorical language (Qian et al., 2019).”
- Exploring Deep Multimodal Fusion of Text and Photo for Hate Speech Classification (2019, methodology): “• Sparsemax vs softmax We also experiment with sparsemax (Martins and Astudillo, 2016), an alternative to softmax, in Equation (3) for calculating the attention vector a .”