The Geometry of Culture: Analyzing the Meanings of Class through Word Embeddings

By Austin C. Kozlowski, Matt Taddy, James A. Evans. 2018

516 citations recorded by the source corpus.

We argue word embedding models are a useful tool for the study of culture using a historical analysis of shared understandings of social class as an empirical case. Word embeddings represent semantic relations between words as relationships between vectors in a high-dimensional space, specifying a relational model of meaning consistent with contemporary theories of culture. Dimensions induced by word differences (rich – poor) in these spaces correspond to dimensions of cultural meaning, and the projection of words onto these dimensions reflects widely shared associations, which we validate with surveys. Analyzing text from millions of books published over 100 years, we show that the markers of class continuously shifted amidst the economic transformations of the twentieth century, yet the basic cultural dimensions of class remained remarkably stable. The notable exception is education, which became tightly linked to affluence independent of its association with cultivated taste.

Subfields: Cultural Studies, General Social Sciences, Sociology and Political Science, Natural Language Processing, Social Sciences & Humanities

How researchers see this paper

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

In Cultural Studies

In General Social Sciences

In Sociology and Political Science

In Natural Language Processing

In Social Sciences & Humanities

Citations in the corpus

What are the Biases in My Word Embedding? (2018, positive): “asons why such an algorithm is useful. First, social scientists can use it as a tool to study human bias, as data analysis is increasingly common in social studies of human biases (Garg et al., 2018; Kozlowski, Taddy, and Evans, 2018). Second, ﬁnding bias is a natural step in “debiasing” representat”
[RE] Bad Seeds: Evaluating Lexical Methods for Bias Measurement (2022, methodology): “We use the same seed sets as used in the experiments for the original paper (Bolukbasi et al., 2016) (Kozlowski et al., 2019) (Garg et al., 2018) (Caliskan et al., 2017) (Manzini et al., 2019) (Zhao et al., 2018) (Hoyle et al., 2019).”
Can Large Language Models Transform Computational Social Science? (2023, background): “…2021; Mendelsohn et al., 2021; Demszky et al., 2019; Field et al., 2018), with applications to public opinion (Bhatia, 2017; Garg et al., 2018; Kozlowski et al., 2019; Abul-Fottouh and Fetner, 2018), voting behavior (Black et al., 2011), policy change (Flores, 2017), social movements (Nelson,…”
Five sources of bias in natural language processing (2021, background): “An increasing volume of social science research uses NLP to generate insights into society and the human mind (Bhatia, 2017; Kozlowski et al., 2019).”
The Voice of Monetary Policy (2021, unknown): “Measuring the intensity of text sentiment As an additional robustness check, we adopt the approach used in Kozlowski et al. (2019) and Jha et al. (2021) to measure the text sentiment’s intensity.”
ScholarBERT: Bigger is Not Always Better (2022, background): “are just starting to be adopted in other domains (such as social sciences (Duede et al., 2021; Kozlowski et al., 2019)), leading to a scarcity of labeled data.”
Wide range screening of algorithmic bias in word embedding models using large sentiment lexicons reveals underreported bias types (2020, background): “More recently, other authors have proposed deriving from the embedding space cultural axes representing constructs such as gender or race and then projecting words of interests onto those axes to test for associations [12].”