A Fresh Perspective on Examining Population Emotional Well-Being Trends by Internet Search Engine: An Emerging Composite Anxiety and Depression Index

Yu Wang, Heming Deng, Sunan Gao, Tongxu Li and Feifei Wang ()
Additional contact information
Yu Wang: Center for Applied Statistics, Renmin University of China, Beijing 100872, China
Heming Deng: School of Statistics, Renmin University of China, Beijing 100872, China
Sunan Gao: School of Statistics, Renmin University of China, Beijing 100872, China
Tongxu Li: School of Statistics, Renmin University of China, Beijing 100872, China
Feifei Wang: Center for Applied Statistics, Renmin University of China, Beijing 100872, China

IJERPH, 2024, vol. 21, issue 2, 1-12

Abstract: Traditional assessments of anxiety and depression face challenges and difficulties when it comes to understanding trends in-group psychological characteristics. As people become more accustomed to expressing their opinions online, location-based online media and cutting-edge algorithms offer new opportunities to identify associations between group sentiment and economic- or healthcare-related variables. Our research provides a novel approach to analyzing emotional well-being trends in a population by focusing on retrieving online information. We used emotionally enriched texts on social media to build the Public Opinion Dictionary (POD). Then, combining POD with the word vector model and search trend, we developed the Composite Anxiety and Depression Index (CADI), which can reflect the mental health level of a region during a specific time period. We utilized the representative external data by CHARLS to validate the effectiveness of CADI, indicating that CADI can serve as a representative indicator of the prevalence of mental disorders. Regression and subgroup analysis are employed to further elucidate the association between public mental health (measured by CADI) with economic development and medical burden. The results of comprehensive regression analysis show that the Import–Export index (−16.272, p < 0.001) and average cost of patients (4.412, p < 0.001) were significantly negatively associated with the CADI, and the sub-models stratificated by GDP showed the same situation. Disposable income (−28.389, p < 0.001) became significant in the subgroup with lower GDP, while the rate of unemployment (2.399, p < 0.001) became significant in the higher subgroup. Our findings suggest that an unfavorable economic development or unbearable medical burden will increase the negative mental health of the public, which was consistent across both the full and subgroup models.

Keywords: composite anxiety and depression index; group sentiment; search engine; natural language processing; emotion dictionary (search for similar items in EconPapers)
JEL-codes: I I1 I3 Q Q5 (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/1660-4601/21/2/202/pdf (application/pdf)
https://www.mdpi.com/1660-4601/21/2/202/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jijerp:v:21:y:2024:i:2:p:202-:d:1336514

Access Statistics for this article

IJERPH is currently edited by Ms. Jenna Liu

More articles in IJERPH from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().