A Framework for the Computational Linguistic Analysis of Dehumanization

By Julia Mendelsohn, Yulia Tsvetkov, Dan Jurafsky. 2020

115 citations recorded by the source corpus.

Dehumanization is a pernicious psychological process that often leads to extreme intergroup bias, hate speech, and violence aimed at targeted social groups. Despite these serious consequences and the wealth of available data, dehumanization has not yet been computationally studied on a large scale. Drawing upon social psychology research, we create a computational linguistic framework for analyzing dehumanizing language by identifying linguistic correlates of salient components of dehumanization. We then apply this framework to analyze discussions of LGBTQ people in the New York Times from 1986 to 2015. Overall, we find increasingly humanizing descriptions of LGBTQ people over time. However, we find that the label homosexual has emerged to be much more strongly associated with dehumanizing attitudes than other labels, such as gay. Our proposed techniques highlight processes of linguistic variation and change in discourses surrounding marginalized groups. Furthermore, the ability to analyze dehumanizing language at a large scale has implications for automatically detecting and understanding media bias as well as abusive language online.

Subfields: Artificial Intelligence, Social Psychology, 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 Social Psychology

In Natural Language Processing

In Safety, Robustness & Interpretability

Citations in the corpus

HateCheck: Functional Tests for Hate Speech Detection Models (2020, background): “F3 – explicit dehumanisation of a protected group or its members : Prevalent form of hate (Mendelsohn et al., 2020; Banko et al., 2020; Vid-gen et al., 2020a).”
Learning from the Worst: Dynamically Generated Datasets to Improve Online Hate Detection (2021, background): “It often involves describing groups as leeches, cockroaches, insects, germs or rats (Mendelsohn et al., 2020).”
A Survey of Race, Racism, and Anti-Racism in NLP (2021, background): “…has received substantially less attention than gender, many of the observations in this work hold for social characteristics that have received even less attention in NLP research, such as socioeconomic class, disability, or sexual orientation (Mendelsohn et al., 2020; Hutchinson et al., 2020).”
Introducing CAD: the Contextual Abuse Dataset (2021, background): “…focus for computational work (Leader Maynard and Benesch, 2016; Matsuda et al., 1993), yet is often combined into a broader ‘explicit’ category (Palmer et al., 2020; Vidgen et al., 2020; Kiela et al., 2020) and has been insufﬁciently studied on its own, apart from Mendelsohn et al. (2020).”
Implicitly Abusive Language – What does it actually look like and why are we not getting there? (2021, background): “The only exception is the in-depth descriptive study by Mendelsohn et al. (2020) examining the dehumanizing con-”
COLD: Annotation scheme and evaluation data set for complex offensive language in English (2020, background): “Wierzbiecka (1986) explains that when adjectives are nominalized, the new nominal incorporates reference to a generic category or kind based on a prototypical idea of 8See Mendelsohn et al. (2020) for computational approaches to analyzing dehumanization in text.”
On the Dangers of Stochastic Parrots: Can Language Models Be Too Big? 🦜 (2021, background): “Furthermore, in addition to abusive language [139] and hate speech [67], there are subtler forms of negativity such as gender bias [137], microaggressions [22], dehumanization [83], and various socio-political framing biases [44, 114] that are prevalent in language data.”