Natural language analyzed with AI‐based transformers predict traditional subjective well‐being measures approaching the theoretical upper limits in accuracy
APA
Kjell, O. N. E., Sikström, S., Kjell, K., & Schwartz, H. A. (2022). Natural language analyzed with AI‐based transformers predict traditional subjective well‐being measures approaching the theoretical upper limits in accuracy. Scientific Reports, 12(3918). https://doi.org/10.1038/s41598-022-07520-w
BibTeXDownload .bib
@article{kjell2022natural,
title = {{Natural language analyzed with AI‐based transformers predict traditional subjective well‐being measures approaching the theoretical upper limits in accuracy}},
author = {Oscar N. E. Kjell and Sverker Sikström and Katarina Kjell and H. Andrew Schwartz},
year = {2022},
journal = {Sci. Rep.},
doi = {10.1038/s41598-022-07520-w},
url = {https://doi.org/10.1038/s41598-022-07520-w}
}
Abstract
This study demonstrates that using recent breakthroughs in artificial intelligence (AI), such as transformers, psychological assessments derived from text responses can achieve accuracy approaching theoretical upper limits, rivaling traditional rating scales. This opens pathways for modernizing questionnaires and understanding the human condition more comprehensively.
