Can ChatGPT Read Who You Are?

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Derner, Erik, Kučera, Dalibor, Oliver, Nuria, Zahálka, Jan
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913454198095872
author Derner, Erik
Kučera, Dalibor
Oliver, Nuria
Zahálka, Jan
author_facet Derner, Erik
Kučera, Dalibor
Oliver, Nuria
Zahálka, Jan
contents The interplay between artificial intelligence (AI) and psychology, particularly in personality assessment, represents an important emerging area of research. Accurate personality trait estimation is crucial not only for enhancing personalization in human-computer interaction but also for a wide variety of applications ranging from mental health to education. This paper analyzes the capability of a generic chatbot, ChatGPT, to effectively infer personality traits from short texts. We report the results of a comprehensive user study featuring texts written in Czech by a representative population sample of 155 participants. Their self-assessments based on the Big Five Inventory (BFI) questionnaire serve as the ground truth. We compare the personality trait estimations made by ChatGPT against those by human raters and report ChatGPT's competitive performance in inferring personality traits from text. We also uncover a 'positivity bias' in ChatGPT's assessments across all personality dimensions and explore the impact of prompt composition on accuracy. This work contributes to the understanding of AI capabilities in psychological assessment, highlighting both the potential and limitations of using large language models for personality inference. Our research underscores the importance of responsible AI development, considering ethical implications such as privacy, consent, autonomy, and bias in AI applications.
format Preprint
id arxiv_https___arxiv_org_abs_2312_16070
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Can ChatGPT Read Who You Are?
Derner, Erik
Kučera, Dalibor
Oliver, Nuria
Zahálka, Jan
Computers and Society
Computation and Language
Human-Computer Interaction
The interplay between artificial intelligence (AI) and psychology, particularly in personality assessment, represents an important emerging area of research. Accurate personality trait estimation is crucial not only for enhancing personalization in human-computer interaction but also for a wide variety of applications ranging from mental health to education. This paper analyzes the capability of a generic chatbot, ChatGPT, to effectively infer personality traits from short texts. We report the results of a comprehensive user study featuring texts written in Czech by a representative population sample of 155 participants. Their self-assessments based on the Big Five Inventory (BFI) questionnaire serve as the ground truth. We compare the personality trait estimations made by ChatGPT against those by human raters and report ChatGPT's competitive performance in inferring personality traits from text. We also uncover a 'positivity bias' in ChatGPT's assessments across all personality dimensions and explore the impact of prompt composition on accuracy. This work contributes to the understanding of AI capabilities in psychological assessment, highlighting both the potential and limitations of using large language models for personality inference. Our research underscores the importance of responsible AI development, considering ethical implications such as privacy, consent, autonomy, and bias in AI applications.
title Can ChatGPT Read Who You Are?
topic Computers and Society
Computation and Language
Human-Computer Interaction
url https://arxiv.org/abs/2312.16070