Measuring individual differences in implicit cognition: the implicit association test.

By A. Greenwald, Debbie E. McGhee, Jordan L. K. Schwartz. 1998

Subfields: Cognitive Science & Psychology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cognitive Science & Psychology

Citations in the corpus

Language (Technology) is Power: A Critical Survey of “Bias” in NLP (2020, methodology): “, 2017) draws on the Implicit Association Test (Greenwald et al., 1998) from the social psychology literature, while several techniques operationalize the well-studied “Angry Black Woman” stereotype (Kiritchenko and Mohammad, 2018; May et al.”
Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings (2016, background): “Hence, word embeddings may serve as a means to extract implicit gender associations from a large text corpus similar to how Implicit Association Tests [11] detect automatic gender associations possessed by people, which often do not align with self reports.”
Semantics derived automatically from language corpora contain human-like biases (2016, methodology): “Using the Greenwald et al. (1998) attributes, the effect size is 1.50 and p -value < 10 − 4 ; and using the updated Nosek et al. (2002a) attributes, the effect size is 1.28 and p -value < 10 − 3 .”
Measuring Bias in Contextualized Word Representations (2019, methodology): “To do this, we apply the log probability bias score to the same set of attributes that were shown to exhibit human bias in experiments that were performed using the Implicit Association Test (Greenwald et al., 1998).”
On Measuring Social Biases in Sentence Encoders (2019, background): “The Word Embedding Association Test WEAT imitates the human implicit association test (Greenwald et al., 1998) for word embed-dings, measuring the association between two sets of target concepts and two sets of attributes.”
Mitigating Gender Bias in Natural Language Processing: Literature Review (2019, methodology): “…Test (IAT) is used to measure subconscious gender bias in humans, which can be quantiﬁed as the difference in time and accuracy for humans to categorize words as relating to two concepts they ﬁnd similar versus two concepts they ﬁnd different (Greenwald et al., 1998; Caliskan et al., 2017).”
Assessing Social and Intersectional Biases in Contextualized Word Representations (2019, background): “[5] proposed Word Embedding Association Tests (WEATs), which follows human implicit association tests [14] in measuring the association between two target concepts and two attributes.”
It’s All in the Name: Mitigating Gender Bias with Name-Based Counterfactual Data Substitution (2019, neutral): “Caliskan et al. (2017) introduce the Word Embedding Association Test (WEAT), which provides results analogous to earlier psychological work by Greenwald et al. (1998) by measuring the difference in relative similarity between two sets of target words X and Y and two sets of attribute words A and B .”
Understanding the Origins of Bias in Word Embeddings (2018, positive): “, Wikipedia, Google News) consistently replicate the known human biases measured by the Implicit Association Test (Greenwald et al., 1998).”
Harvesting implicit group attitudes and beliefs from a demonstration web site (2002, background): “These results replicate data collected using traditional laboratory procedures (Greenwald et al., 1998; Mitchell, Nosek, & Banaji, 2001).”
What are the Biases in My Word Embedding? (2018, methodology): “The WEAT draws its inspiration from the Implicit Association Test (IAT), a widely-used approach to measure human bias [12].”
A Survey of Race, Racism, and Anti-Racism in NLP (2021, methodology): “As an example of questioning who devised racial categories and for what purpose, we consider the pattern of re-using names from Greenwald et al. (1998), who describe their data as sets of names “judged by introductory psychology students to be more likely to belong to White Americans than to Black…”
Detecting Emergent Intersectional Biases: Contextualized Word Embeddings Contain a Distribution of Human-like Biases (2020, methodology): “’s Word Embedding Association Test (WEAT) quantifies biases documented by the validated psychological methodology of the Implicit Association Test (IAT) [10].”
Measuring Model Biases in the Absence of Ground Truth (2021, background): “For example, subjects respond more quickly to the word nurse if it follows a highly associated word such as doctor [7, 14].”
Measuring Social Biases in Grounded Vision and Language Embeddings (2020, background): “Since the introduction of the Implicit Association Test (IAT) by Greenwald et al. (1998), we have had the ability to measure biases in humans.”