The Linguistic Ideologies of Deep Abusive Language Classification

By Michael Castelle. 2018

29 citations recorded by the source corpus.

This paper brings together theories from sociolinguistics and linguistic anthropology to critically evaluate the so-called “language ideologies” — the set of beliefs and ways of speaking about language—in the practices of abusive language classification in modern machine learning-based NLP. This argument is made at both a conceptual and empirical level, as we review approaches to abusive language from different fields, and use two neural network methods to analyze three datasets developed for abusive language classification tasks (drawn from Wikipedia, Facebook, and StackOverflow). By evaluating and comparing these results, we argue for the importance of incorporating theories of pragmatics and metapragmatics into both the design of classification tasks as well as in ML architectures.

Subfields: Artificial Intelligence, 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

1. Vinodkumar Prabhakaran
2. Ben Hutchinson
3. Ekaterina Shutova
4. Helen Yannakoudakis
5. Emily L. Denton
6. Pushkar Mishra
7. S. A. Chowdhury
8. Bernard Jim Jansen

In Natural Language Processing

1. Ekaterina Shutova
2. Helen Yannakoudakis
3. Pushkar Mishra
4. Ben Hutchinson
5. Vinodkumar Prabhakaran
6. Emily L. Denton
7. S. A. Chowdhury
8. Bernard Jim Jansen

In Safety, Robustness & Interpretability

1. Vinodkumar Prabhakaran
2. Emily L. Denton
3. Ben Hutchinson
4. S. A. Chowdhury
5. Bernard Jim Jansen
6. Maximilian Hopf
7. Soon-gyo Jung
8. Kellie Webster

Citations in the corpus

• Social Biases in NLP Models as Barriers for Persons with Disabilities (2020, background): “It is important to recognize that social norms around language are contextual and differ across groups (Castelle, 2018; Davidson et al., 2019; Vidgen et al., 2019).”
• Developing an online hate classifier for multiple social media platforms (2020, methodology): “As astutely remarked by Castelle [1], “ Because the flags are provided by users who have seen the entire interaction, many comments are considered offensive in context but not offensive when standing alone .”
• Tackling Online Abuse: A Survey of Automated Abuse Detection Methods (2019, background): “We differ from previous surveys (Schmidt and Wiegand, 2017; Fortuna and Nunes, 2018; Salminen et al., 2018; Castelle, 2018) in the following respects: 1) we discuss the cate-gorizations of abuse based on coarse-grained vs. fine-grained taxonomies; 2) we present a detailed overview of datasets…”