From Text to Thought: How Analyzing Language Can Advance Psychological Science

Jackson, Joshua Conrad; Watts, Joseph; List, Johann‐Mattis; Puryear, Curtis; Drabble, Ryan; Lindquist, Kristen A.

doi:10.1177/17456916211004899

Cited by 84 publications

(64 citation statements)

References 143 publications

(153 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The current work departs from the approach used over the last several decades by drawing on recent innovations in natural language processing (NLP). Since the introduction of "transformer" language models like Google's BERT (Devlin et al, 2019), it has become possible to conduct powerful evaluations of the associations between words and other aspects of language in ways that are novel and likely to be insightful for psychological science (Jackson et al, 2021).…”

Section: Deep Lexical Hypothesis: Identifying Personality Structure I...mentioning

confidence: 99%

Deep Lexical Hypothesis: Identifying personality structure in natural language

Cutler¹,

Condon²

2022

Preprint

View full text Add to dashboard Cite

Recent advances in natural language processing (NLP) have produced general models that can perform complex tasks such as summarizing long passages and translating across languages. Here, we introduce a method to extract adjective similarities from language models as done with survey-based ratings in traditional psycholexical studies but using millions of times more text in a natural setting. The correlational structure produced through this method is highly similar to that of self- and other-ratings of 435 terms reported by Saucier and Goldberg (1996a). The first three unrotated factors produced using NLP are congruent with those in survey data, with coefficients of 0.89, 0.79, and 0.79. This structure is robust to many modeling decisions: adjective set, including those with 1,710 terms (Goldberg, 1982) and 18,000 terms (Allport & Odbert, 1936); the query used to extract correlations; and language model. Notably, Neuroticism and Openness are only weakly and inconsistently recovered. This is a new source of signal that is closer to the original (semantic) vision of the Lexical Hypothesis. The method can be applied where surveys cannot: in dozens of languages simultaneously, with tens of thousands of items, on historical text, and at extremely large scale for little cost. The code is made public to facilitate reproduction and fast iteration in new directions of research.

show abstract

Section: Deep Lexical Hypothesis: Identifying Personality Structure I...mentioning

confidence: 99%

Deep Lexical Hypothesis: Identifying personality structure in natural language

Cutler¹,

Condon²

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…These terms are also useful for lexical research that does not rely only on survey-based methods. Recent advances in natural language processing (NLP) techniques, for example, offer considerable potential for novel applications of language analysis, especially with respect to the breadth and diversity of study populations over time [11]. These applications will benefit from the availability of an updated and more comprehensive collection of personality descriptors.…”

Section: (4) Reuse Potentialmentioning

confidence: 99%

Personality Trait Descriptors: 2,818 Trait Descriptive Adjectives Characterized by Familiarity, Frequency of Use, and Prior Use in Psycholexical Research

Condon¹,

Coughlin²,

Weston

2022

JOPD

View full text Add to dashboard Cite

This dataset contains 2,818 trait descriptive adjectives in English and information about the extent to which each term is known among a large and approximately representative sample of U.S. adults. The list of personality-related terms includes all 1,710 adjectives previously studied by Goldberg (1982) and draws on prior work by Allport and Odbert (1936) and Norman (1967). The extent to which terms were known by respondents was based on the administration of vocabulary questions about each term-definition pair online to a sample of English-speaking U.S. residents with approximately average literacy levels. The open data are accompanied by an online database that allows the terms to be searched and filtered.

show abstract

“…First, to get an overall snapshot of the differences between Leftists and Liberals, we used a natural language processing approach to their free response writing, comparing frequency statistics of word usage (tf-idf) and modeling latent topics for each of the pairs. While these methods also require interpretation from the researcher, the initial numerical or algorithmic nature of these methods permit a robust and rich comparison of language use between the target groups (see also Jackson et al, 2021). Here, we compared language used to describe Liberals and Leftists based on an individual's self-reported ideology.…”

Section: Leftists and Liberals Talking About Themselves And Each Othermentioning

confidence: 99%

Understanding Committed Leftists in the United States right before the 2020 U.S. Presidential Election

Alto¹,

Flores-Robles²,

Anderson³

et al. 2022

Preprint

View full text Add to dashboard Cite

Political ideology in the United States is typically described as a spectrum. This metaphor implies that the people who place themselves along the spectrum differ in degree from each other; an individual who places themselves all the way on the left of the spectrum, is an extreme version of another closer to the middle. Political polarization and elite extremism are on the rise in the United States (e.g., Finkel et al., 2020), and attention to political polarization has fueled efforts to understand the extreme right (e.g, Forscher & Kteily, 2020), and driven attempts to identify whether the extreme left may or may not share authoritarian tendencies with those on the extreme right (Conway et al., 2018; Costello et al., 2021; Badaan et al., 2020; Nilsson & Jost, 2020). The central focus of psychology on the extreme Left has been on Left-wing authoritarianism¬—whether it exists, is appropriately named, or logically possible (Conway et al., 2018; Costello et al., 2021; Badaan & Jost, 2020; Nilsson & Jost, 2020). However, this approach sidesteps a longstanding distinction that exists among politically left-leaning individuals–that between Leftists and Liberals (see Menand, 2021). While Leftists explicitly describe themselves as completely separate from Liberals¬, who they claim cooperate with existing institutions and seek insufficient social change (Ture, 1966), Liberals may more easily see themselves as part of a larger left-leaning political group, such that they express surprise and even anger when Leftists do not support their political agenda (Capeheart, 2020). It is the aim of this paper to investigate the psychological differences between Leftists and Liberals (i.e., in terms of ideology, morality, political preferences, and judgments of group boundaries) to further our understanding of how these two historical groups may differ and interact, and help us understand political ideology, identity, and radicalism, more broadly.

show abstract

From Text to Thought: How Analyzing Language Can Advance Psychological Science

Cited by 84 publications

References 143 publications

Deep Lexical Hypothesis: Identifying personality structure in natural language

Deep Lexical Hypothesis: Identifying personality structure in natural language

Personality Trait Descriptors: 2,818 Trait Descriptive Adjectives Characterized by Familiarity, Frequency of Use, and Prior Use in Psycholexical Research

Understanding Committed Leftists in the United States right before the 2020 U.S. Presidential Election

Contact Info

Product

Resources

About