Demystifying Political Selection Using Large Language Models: The Case of China

DOI

10.2991/978-94-6239-598-5_22How to use a DOI?

Keywords

political selection; large language models; political forecasting

Abstract

China’s economic reform has driven remarkable growth and poverty reduction despite institutional structures that seem ill-suited for such achievements. To explain this “China puzzle,” this paper investigates the regionally decentralized authoritarian system that supports China’s governance. In this system, political promotion is a key mechanism that connects local officials’ incentives to national goals. Using a new dataset that combines biographical details of municipal leaders with economic performance metrics and sociopolitical event data from news sources, this study explores how economic growth and public events influence the promotion prospects of local officials. The findings indicate that economic performance, especially GDP growth, significantly boosts the chances of promotion — particularly for party secretaries — while public events like protests and cooperation activities have limited or inconsistent effects. These results suggest that China’s decentralized authoritarian system accounts for both its impressive achievements and ongoing governance issues, as performance-based incentives dominate cadre evaluation, with broader social factors playing a secondary role.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Bohao Deng
PY  - 2026
DA  - 2026/02/26
TI  - Demystifying Political Selection Using Large Language Models: The Case of China
BT  - Proceedings of the 2025 6th  International Conference on Big Data and Social Sciences (ICBDSS 2025)
PB  - Atlantis Press
SP  - 219
EP  - 227
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6239-598-5_22
DO  - 10.2991/978-94-6239-598-5_22
ID  - Deng2026
ER  -