Decoding public sentiment on pension policies in China through natural language processing

Xiaohong Xie () and Magdalena Osińska ()
Additional contact information
Xiaohong Xie: Department of Econometrics and Statistics, Nicolaus Copernicus University in Torun
Magdalena Osińska: Department of Economics, Nicolaus Copernicus University in Torun;

Bank i Kredyt, 2025, vol. 56, issue 5, 613-642

Abstract: This study aims to reveal public sentiment toward China’s pension policies from January 2018 to August 2023, leveraging over 260,000 Weibo posts to identify key themes and demographic differences. Advanced Natural Language Processing (NLP) techniques, including sentiment analysis and latent Dirichlet allocation, are employed to explore six topics, such as societal impact and policy integrity, while uncovering demographic and regional variations. The findings reveal that policy changes significantly influence public sentiment, with greater negativity observed around institutional and structural aspects of the policies. These results underscore the need for public education on pension reforms and fraud prevention, providing actionable insights for policymakers in an aging society. The study contributes to behavioural finance theory by illustrating how heuristics like availability bias and loss aversion shape public reactions to pension reforms. However, social media data may not fully represent less active groups like older adults, highlighting the need for broader research methods

Keywords: pension policies; public sentiment; natural language processing; sentiment analysis (search for similar items in EconPapers)
JEL-codes: C38 H55 J18 (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://bankikredyt.nbp.pl/content/2025/05/bik_05_2025_05.pdf (application/pdf)

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:nbp:nbpbik:v:56:y:2025:i:5:p:613-642

Access Statistics for this article

More articles in Bank i Kredyt from Narodowy Bank Polski Contact information at EDIRC.
Bibliographic data for series maintained by Wojciech Burjanek ().