Prediction of Prefecture-Level Subjective Well-Being in Japan by Using Google Trends and Socioeconomic Data: Machine Learning Model Development and Validation Study
JMIR Formative Research · 20.03.2026 · 10 · e88696
DOI: 10.2196/88696 ↗Kurz gefasst
Fachartikel in der Zeitschrift JMIR Formative Research, online erschienen am 20.03.2026. Verfasst von Kenichi Kishi und 2 weiteren Autor:innen. Beteiligte Einrichtung: Advanced Institute of Industrial Technology, Tokyo, Japan. Hauptthemen laut MEDLINE: Machine Learning, Internet, Search Engine. Die Arbeit nennt 10 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.
Abstract (Originalsprache)
Incorporating prespecified Google Trends indicators into leakage-controlled stacked-ensemble models improved a 2025 holdout prediction of subjective well-being by using 2022-2025 data from Japan’s 47 prefectures, reducing the mean squared error from 0.0050 to 0.0045.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Advanced Institute of Industrial Technology, Tokyo, Japan.
ORCID-Profile: Kenichi Kishi, Hisashi Hayashi, Shigeomi Koshimizu
Zitieren
APA
Kishi, K., Hayashi, H., & Koshimizu, S. (2026). Prediction of Prefecture-Level Subjective Well-Being in Japan by Using Google Trends and Socioeconomic Data: Machine Learning Model Development and Validation Study. JMIR Formative Research, 10, e88696. https://doi.org/10.2196/88696
Vancouver
Kishi K, Hayashi H, Koshimizu S. Prediction of Prefecture-Level Subjective Well-Being in Japan by Using Google Trends and Socioeconomic Data: Machine Learning Model Development and Validation Study. JMIR Formative Research. 2026;10:e88696. doi:10.2196/88696
BibTeX
@article{Kishi2026,
author = {Kishi, Kenichi and Hayashi, Hisashi and Koshimizu, Shigeomi},
title = {Prediction of Prefecture-Level Subjective Well-Being in Japan by Using Google Trends and Socioeconomic Data: Machine Learning Model Development and Validation Study},
journal = {JMIR Formative Research},
year = {2026},
volume = {10},
pages = {e88696},
doi = {10.2196/88696}
}
EUVIMED