Exploring the application of a text-to-personality technique in job interviews

Holtrop, Djurre; Oostrom, Janneke K.; Breda, Ward van; Koutsoumpis, Antonis; Vries, Reinout E. de

doi:10.1080/1359432x.2022.2051484

Cited by 3 publications

(9 citation statements)

References 75 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, we failed to replicate the moderating role of task synchronicity between self-reported Extraversion and positive emotions reported in Chen et al (2020). One possible reason might be the methodological differences between the two studies, since Chen et al (2020) did not correct for attenuation, did not have missing values, did not include Holtrop et al (2019), and included two studies that did not pass the eligibility criteria of the present meta-analysis (Morgan, 2014;Pirzadeh & Pfaff, 2012).…”

Section: Moderators and Tatmentioning

confidence: 81%

“…BIG FIVE AND LINGUISTIC INQUIRY AND WORD COUNT META-ANALYSIS text analysis methods including both machine and nonmachine learning techniques. The two remaining studies applied text-based personality assessment tools specifically developed to measure either the Big Five (IBM Watson Personality Insight [IBM-WPI]; International Business Machines [IBM], 2021) or the HEXACO (HTTP; Holtrop et al, 2022) personality models. The (recently discontinued) IBM-WPI belongs to an open-vocabulary approach and produces personality scores by applying machine learning techniques trained on Twitter data.…”

Section: Liwc Versus Other Methodsmentioning

confidence: 99%

“…The two models greatly overlap, and hence, the two terms (Big Five, five-factor) are used interchangeably. One study (Holtrop et al, 2019) used the HEXACO model. In the HEXACO model, the domains of Openness to Experience, Conscientiousness, and Extraversion are operationalized similarly to the Big Five, but the domains of Agreeableness and Neuroticism (Emotionality in HEXACO) are operationalized somewhat differently (Ashton & Lee, 2005).…”

Section: Systematic Literature Searchmentioning

confidence: 99%

“…Consequently, at this point, one important personality dimension in LIWC research has not been investigated. Researchers have started exploring the relation between LIWC and HEXACO (Holtrop et al, 2019), but the linguistic markers of Honesty-Humility still remain open for investigation.…”

Section: Suggestions For Future Researchmentioning

confidence: 99%

“…Then, a text is processed, and every time, the software comes across a word that is part of the internal dictionary it counts a “hit.” The output score indicates the extent to which the text contains the construct of interest (e.g., the number of positive emotion words). Examples of the closed-vocabulary approach are the General Inquirer (Stone et al, 1966), the Medical Research Council psycholinguistic database (MRC; Wilson, 1988), the Honesty-Humility, Emotionality, eXtraversion, Agreeableness, Conscientiousness, Openness to Experience (HEXACO) text-to-personality technique (HTTP; Holtrop et al, 2022), but by far the most popular approach is LIWC, which, at the time of writing this article, counts a little more than 10,000 citations in Google Scholar. Since the goal of the present meta-analysis is to identify the linguistic markers of personality, and since a large number of LIWC studies has already been accumulated, we opted to meta-analyze the results of LIWC research.…”

Section: Text-based Personality Assessment and The Liwcmentioning

confidence: 99%

See 4 more Smart Citations

The kernel of truth in text-based personality assessment: A meta-analysis of the relations between the Big Five and the Linguistic Inquiry and Word Count (LIWC).

Koutsoumpis¹,

Oostrom²,

Holtrop³

et al. 2022

Psychological Bulletin

View full text Add to dashboard Cite

The Linguistic Inquiry and Word Count (LIWC) is a popular closed-vocabulary text analysis software program that is used to understand whether individuals' use of linguistic categories (i.e., word categories, such as negative affect) depends on their personality traits. Here, we present the first meta-analysis of the relations between the Big Five personality traits and 52 linguistic categories of the English language. Across 31 eligible samples (n = 85,724), the results showed that (a) self-reported personality traits are significantly correlated with linguistic categories, but the effect sizes are relatively small (the strongest effect sizes between the Big Five and linguistic categories ranged from |ρ| = .08 to .14, and the 52 LIWC categories explained on average 5.1% of personality variance); (b) observerreported personality traits are significantly correlated with linguistic categories, with the effect sizes being small-to-medium (|ρ| = .18-.39, explaining 38.5% of personality variance); (c) 20 linguistic categories (out of 260; 5 Personality Traits × 52 LIWC Categories) correlated both with self-and observer-reported personality traits (the "kernel of truth" in linguistic markers of personality); and (d) 10 study, sample, and task characteristics significantly moderated the correlations of the linguistic categories with personality traits, showing that the effect sizes were mainly stronger for longer texts and older LIWC versions, among others. Public Significance StatementThis meta-analysis identifies the linguistic categories (i.e., word categories, such as negative affect) that individuals use depending on their personality traits, as well as the linguistic categories that other people use to draw personality inferences. Individuals indeed use specific linguistic categories depending on their personality traits and others use specific linguistic categories to draw personality inferences, but those relations are dependent on study and tasks characteristics (e.g., text length, Linguistic Inquiry and Word Count version).

show abstract

Section: Moderators and Tatmentioning

confidence: 81%

Section: Liwc Versus Other Methodsmentioning

confidence: 99%

Section: Systematic Literature Searchmentioning

confidence: 99%

Section: Suggestions For Future Researchmentioning

confidence: 99%

Section: Text-based Personality Assessment and The Liwcmentioning

confidence: 99%

See 3 more Smart Citations

The kernel of truth in text-based personality assessment: A meta-analysis of the relations between the Big Five and the Linguistic Inquiry and Word Count (LIWC).

Koutsoumpis¹,

Oostrom²,

Holtrop³

et al. 2022

Psychological Bulletin

View full text Add to dashboard Cite

show abstract

How trust and attachment styles jointly shape job candidates’ AI receptivity

Deriu,

Pozharliev,

De Angelis

2024

Journal of Business Research

View full text Add to dashboard Cite

Validity evidence for personality scores from algorithms trained on low‐stakes verbal data and applied to high‐stakes interviews

Stevenor,

Hickman,

Zickar

et al. 2024

Int J Selection Assessment

View full text Add to dashboard Cite

We present multifaceted validity evidence for machine learning models (referred to as automated video interview personality assessments (AVI‐PAs) in this research) that were trained on verbal data and interviewer ratings from low‐stakes interviews and applied to high‐stakes interviews to infer applicant personality. The predictive models used RoBERTa embeddings and binary unigrams as predictors. In Study 1 (N = 107), AVI‐PAs more closely reflected interviewer ratings compared to applicant and reference ratings. Also, AVI‐PAs and interviewer ratings had similar relations with applicants' interview behaviors, biographical information, and hireability. In Study 2 (N = 25), AVI‐PAs had weak‐moderate (nonsignificant) relations with subsequent supervisor ratings of job performance. Empirically, the AVI‐PAs were most similar to interviewer ratings. AVI‐PAs, interviewer ratings, self‐reports, and reference‐reports all demonstrated weak discriminant validity evidence. LASSO regression provided superior (but still weak) discriminant evidence compared to elastic net regression. Despite using natural language embeddings to operationalize verbal behavior, the AVI‐PAs (except emotional stability) exhibited large correlations with interviewee word count. We discuss the implications of these findings for pre‐employment personality assessments and effective AVI‐PA design.

show abstract

Exploring the application of a text-to-personality technique in job interviews

Cited by 3 publications

References 75 publications

The kernel of truth in text-based personality assessment: A meta-analysis of the relations between the Big Five and the Linguistic Inquiry and Word Count (LIWC).

The kernel of truth in text-based personality assessment: A meta-analysis of the relations between the Big Five and the Linguistic Inquiry and Word Count (LIWC).

How trust and attachment styles jointly shape job candidates’ AI receptivity

Validity evidence for personality scores from algorithms trained on low‐stakes verbal data and applied to high‐stakes interviews

Contact Info

Product

Resources

About