Can ChatGPT read who you are?
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 vari...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-08-01
|
| Series: | Computers in Human Behavior: Artificial Humans |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2949882124000483 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846141649585963008 |
|---|---|
| author | Erik Derner Dalibor Kučera Nuria Oliver Jan Zahálka |
| author_facet | Erik Derner Dalibor Kučera Nuria Oliver Jan Zahálka |
| author_sort | Erik Derner |
| collection | DOAJ |
| description | 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 | Article |
| id | doaj-art-115576db5d49448c95b71e4cd2fc8cc0 |
| institution | Kabale University |
| issn | 2949-8821 |
| language | English |
| publishDate | 2024-08-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Computers in Human Behavior: Artificial Humans |
| spelling | doaj-art-115576db5d49448c95b71e4cd2fc8cc02024-12-04T05:15:04ZengElsevierComputers in Human Behavior: Artificial Humans2949-88212024-08-0122100088Can ChatGPT read who you are?Erik Derner0Dalibor Kučera1Nuria Oliver2Jan Zahálka3ELLIS Alicante, Distrito Digital 5 (Puerto de Alicante) – Edificio A, Muelle de Poniente 5, 03001, Alicante, Spain; Czech Institute of Informatics, Robotics, and Cybernetics, CTU in Prague, Jugoslávských partyzánů 1580, 16000, Prague, Czech Republic; Corresponding author. ELLIS Alicante, Distrito Digital 5 (Puerto de Alicante) – Edificio A, Muelle de Poniente 5, 03001, Alicante, Spain.Department of Psychology, Faculty of Education, University of South Bohemia, Jeronýmova 10, 37115, České Budějovice, Czech RepublicELLIS Alicante, Distrito Digital 5 (Puerto de Alicante) – Edificio A, Muelle de Poniente 5, 03001, Alicante, SpainCzech Institute of Informatics, Robotics, and Cybernetics, CTU in Prague, Jugoslávských partyzánů 1580, 16000, Prague, Czech RepublicThe 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.http://www.sciencedirect.com/science/article/pii/S2949882124000483Large language modelsNatural language processingPsychologyPersonality traitsBig five inventory |
| spellingShingle | Erik Derner Dalibor Kučera Nuria Oliver Jan Zahálka Can ChatGPT read who you are? Computers in Human Behavior: Artificial Humans Large language models Natural language processing Psychology Personality traits Big five inventory |
| title | Can ChatGPT read who you are? |
| title_full | Can ChatGPT read who you are? |
| title_fullStr | Can ChatGPT read who you are? |
| title_full_unstemmed | Can ChatGPT read who you are? |
| title_short | Can ChatGPT read who you are? |
| title_sort | can chatgpt read who you are |
| topic | Large language models Natural language processing Psychology Personality traits Big five inventory |
| url | http://www.sciencedirect.com/science/article/pii/S2949882124000483 |
| work_keys_str_mv | AT erikderner canchatgptreadwhoyouare AT daliborkucera canchatgptreadwhoyouare AT nuriaoliver canchatgptreadwhoyouare AT janzahalka canchatgptreadwhoyouare |