Capacity of Generative AI to Interpret Human Emotions From Visual and Textual Data: Pilot Evaluation Study
JMIR Mental Health · 06.02.2024 · 11 · e54369
DOI: 10.2196/54369 ↗Kurz gefasst
Fachartikel in der Zeitschrift JMIR Mental Health, online erschienen am 06.02.2024. Verfasst von Zohar Elyoseph und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Educational Psychology, The Center for Psychobiological Research, The Max Stern Yezreel Valley College, Emek Yezreel, Israel. Hauptthemen laut MEDLINE: Artificial Intelligence, Emotions. Die Arbeit wurde bisher 134-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.
Abstract (Originalsprache)
Background
Mentalization, which is integral to human cognitive processes, pertains to the interpretation of one’s own and others’ mental states, including emotions, beliefs, and intentions. With the advent of artificial intelligence (AI) and the prominence of large language models in mental health applications, questions persist about their aptitude in emotional comprehension. The prior iteration of the large language model from OpenAI, ChatGPT-3.5, demonstrated an advanced capacity to interpret emotions from textual data, surpassing human benchmarks. Given the introduction of ChatGPT-4, with its enhanced visual processing capabilities, and considering Google Bard’s existing visual functionalities, a rigorous assessment of their proficiency in visual mentalizing is warranted.
Objective
The aim of the research was to critically evaluate the capabilities of ChatGPT-4 and Google Bard with regard to their competence in discerning visual mentalizing indicators as contrasted with their textual-based mentalizing abilities.
Methods
The Reading the Mind in the Eyes Test developed by Baron-Cohen and colleagues was used to assess the models’ proficiency in interpreting visual emotional indicators. Simultaneously, the Levels of Emotional Awareness Scale was used to evaluate the large language models’ aptitude in textual mentalizing. Collating data from both tests provided a holistic view of the mentalizing capabilities of ChatGPT-4 and Bard.
Results
ChatGPT-4, displaying a pronounced ability in emotion recognition, secured scores of 26 and 27 in 2 distinct evaluations, significantly deviating from a random response paradigm (P
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Educational Psychology, The Center for Psychobiological Research, The Max Stern Yezreel Valley College, Emek Yezreel, Israel.
- Imperial College London, London, United Kingdom.
- Department of Psychology, Bar-Ilan University, Ramat Gan, Israel.
- Department of Psychology, The Max Stern Yezreel Valley College, Emek Yezreel, Israel.
- Boston Children's Hospital, Boston, MA, United States.
ORCID-Profile: Zohar Elyoseph, Elad Refoua, Kfir Asraf, Maya Lvovsky, Yoav Shimoni, Dorit Hadar-Shoval
Zitieren
APA
Elyoseph, Z., Refoua, E., Asraf, K., Lvovsky, M., Shimoni, Y., & Hadar-Shoval, D. (2024). Capacity of Generative AI to Interpret Human Emotions From Visual and Textual Data: Pilot Evaluation Study. JMIR Mental Health, 11, e54369. https://doi.org/10.2196/54369
Vancouver
Elyoseph Z, Refoua E, Asraf K, Lvovsky M, Shimoni Y, Hadar-Shoval D. Capacity of Generative AI to Interpret Human Emotions From Visual and Textual Data: Pilot Evaluation Study. JMIR Mental Health. 2024;11:e54369. doi:10.2196/54369
BibTeX
@article{Elyoseph2024,
author = {Elyoseph, Zohar and Refoua, Elad and Asraf, Kfir and Lvovsky, Maya and Shimoni, Yoav and Hadar-Shoval, Dorit},
title = {Capacity of Generative AI to Interpret Human Emotions From Visual and Textual Data: Pilot Evaluation Study},
journal = {JMIR Mental Health},
year = {2024},
volume = {11},
pages = {e54369},
doi = {10.2196/54369}
}
EUVIMED