AI Chat Paper
Note: Please note that the following content is generated by AMiner AI. SciOpen does not take any responsibility related to this content.
{{lang === 'zh_CN' ? '文章概述' : 'Summary'}}
{{lang === 'en_US' ? '中' : 'Eng'}}
Chat more with AI
PDF (1.7 MB)
Collect
Submit Manuscript AI Chat Paper
Show Outline
Outline
Show full outline
Hide outline
Outline
Show full outline
Hide outline
Research Article | Publishing Language: Chinese

How the Content of Public Demands in Online Political Consultation Affects Government Responsiveness—An Exploratory Study Based on Machine Learning

College of Public Administration, Huazhong University of Science and Technology
School of Government, Sun Yat-Sen University
Show Author Information

Abstract

Government responsiveness reflects the degree to which governmental actions conform to public demands and citizens' ability to access public services. With the rapid development of information technology, online political participation has become a mainstream form of public engagement in China. And the institutional mechanisms and operational channels of online political consultation have been continuously optimized and improved in recent years. Despite these progressive improvements, the “response paradox” gradually attracted attention from academia and government practical fields. Specifically, technological empowerment didn't fundamentally reshape government responsiveness, and government departments still exhibit obvious selective response tendencies. Existing relevant studies mainly focus on macro factors and the internal logic of government systems, while researches on the micro factors of public demands content is still insufficient. There is a lack of in-depth exploration of the linguistic and semantic features of public demands and their impact mechanisms on government responsiveness, and traditional research methods also struggle to adapt to large-scale and complex platform data, restricting the depth and accuracy of existing research. Therefore, this study takes the online political consultation platform Local Leaders' Message Board as the research object, constructing a dataset based on massive real content of public demands and matched government responses. It adopts machine learning models and the SHAP analysis method to systematically explore how the linguistic and semantic features of public demands affect multi-dimensional government responsiveness, further clarifying the micro-level mechanism of the response paradox. First, the results indicate that the features of content can effectively predict response timeliness, yet it shows limited predictive results for response status and response effectiveness. Second, compared with semantic features, linguistic features show more dominant impact on government responsiveness, verifying that the formal expression of public demands outweighs their substantive content. Moreover, public demands concerning personal daily affairs are more likely to obtain timely responses, while demands related to collective public interests receive relatively insufficient responses. These micro-level response differences are essentially derived from the inherent structural constraints and institutional logic of the grassroots government governance system. This research enriches the theoretical system of government responsiveness research. It provides novel micro-level insights into the internal mechanism of the “response paradox”, and offers practical and targeted references for local governments to build fairer, more standardized and precise public demands handling mechanisms. Meanwhile, the findings also guide citizens to optimize their expression strategies, thereby promoting more active, efficient and high-quality government-citizen interaction.

References

【1】
【1】
 
 
China Public Administration Review
Pages 131-153

{{item.num}}

Comments on this article

Go to comment

< Back to all reports

Review Status: {{reviewData.commendedNum}} Commended , {{reviewData.revisionRequiredNum}} Revision Required , {{reviewData.notCommendedNum}} Not Commended Under Peer Review

Review Comment

Close
Close
Cite this article:
WANG J, QIU Q, WANG T. How the Content of Public Demands in Online Political Consultation Affects Government Responsiveness—An Exploratory Study Based on Machine Learning. China Public Administration Review, 2026, 8(3): 131-153. https://doi.org/10.26599/CPAR.2026.9680307

10

Views

0

Downloads

0

Crossref

Published: 17 November 2026
© 2026 Tsinghua University Press