Personality in just a few words : Assessment using natural language processing
(2025) In Personality and Individual Differences 238.- Abstract
Assessment of psychological constructs, such as the Big Five personality traits, has predominantly relied on standardized rating scales. While these scales have advantages, we propose that descriptive word-based responses analyzed with natural language processing (NLP) offer a promising alternative for assessing personality traits. We asked participants (N = 663) to describe either their own personality or a person high in one of the Big Five traits using five words. These responses were then analyzed using large language models, namely BERT and GPT-4, which are known for their high-performance NLP capabilities. The primary aim was to assess the validity of word-based responses analyzed by NLP in comparison to the IPIP-NEO-30 rating... (More)
Assessment of psychological constructs, such as the Big Five personality traits, has predominantly relied on standardized rating scales. While these scales have advantages, we propose that descriptive word-based responses analyzed with natural language processing (NLP) offer a promising alternative for assessing personality traits. We asked participants (N = 663) to describe either their own personality or a person high in one of the Big Five traits using five words. These responses were then analyzed using large language models, namely BERT and GPT-4, which are known for their high-performance NLP capabilities. The primary aim was to assess the validity of word-based responses analyzed by NLP in comparison to the IPIP-NEO-30 rating scale, a commonly used tool for measuring the Big Five traits. Results showed that descriptive word responses had an average prediction accuracy of up to 10 % higher than the rating scale in categorizing the Big Five traits. Additionally, semantic measures showed higher inter-rater reliability, and observer convergence was greater in assessments of others than in self-reports. These findings suggest that descriptive word-based responses may capture more observable and broad aspects of personality compared to traditional rating scales.
(Less)
- author
- Sikström, Sverker
LU
; Valavičiūtė, Ieva LU and Kajonius, Petri LU
- organization
- publishing date
- 2025-05
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- BERT, Big Five, GPT-4, Natural language processing, Personality
- in
- Personality and Individual Differences
- volume
- 238
- article number
- 113078
- publisher
- Elsevier
- external identifiers
-
- scopus:85216477041
- ISSN
- 0191-8869
- DOI
- 10.1016/j.paid.2025.113078
- language
- English
- LU publication?
- yes
- id
- 8f2760b0-38f6-444c-a5f3-f6277c8727ea
- date added to LUP
- 2025-03-20 14:25:37
- date last changed
- 2025-04-04 14:41:50
@article{8f2760b0-38f6-444c-a5f3-f6277c8727ea, abstract = {{<p>Assessment of psychological constructs, such as the Big Five personality traits, has predominantly relied on standardized rating scales. While these scales have advantages, we propose that descriptive word-based responses analyzed with natural language processing (NLP) offer a promising alternative for assessing personality traits. We asked participants (N = 663) to describe either their own personality or a person high in one of the Big Five traits using five words. These responses were then analyzed using large language models, namely BERT and GPT-4, which are known for their high-performance NLP capabilities. The primary aim was to assess the validity of word-based responses analyzed by NLP in comparison to the IPIP-NEO-30 rating scale, a commonly used tool for measuring the Big Five traits. Results showed that descriptive word responses had an average prediction accuracy of up to 10 % higher than the rating scale in categorizing the Big Five traits. Additionally, semantic measures showed higher inter-rater reliability, and observer convergence was greater in assessments of others than in self-reports. These findings suggest that descriptive word-based responses may capture more observable and broad aspects of personality compared to traditional rating scales.</p>}}, author = {{Sikström, Sverker and Valavičiūtė, Ieva and Kajonius, Petri}}, issn = {{0191-8869}}, keywords = {{BERT; Big Five; GPT-4; Natural language processing; Personality}}, language = {{eng}}, publisher = {{Elsevier}}, series = {{Personality and Individual Differences}}, title = {{Personality in just a few words : Assessment using natural language processing}}, url = {{http://dx.doi.org/10.1016/j.paid.2025.113078}}, doi = {{10.1016/j.paid.2025.113078}}, volume = {{238}}, year = {{2025}}, }