基于媒体报道文本的税收政策不确定性指数构建

Construction of China’s Tax Policy Uncertainty Index Based on Media Report Text

经济政策不确定性一直是经济学研究领域的热点问题,但相关研究大多针对整体经济政策不确定性,少有对具体经济政策的不确定性进行考察。基于2006年1月到2019年3月我国18家主流媒体网站的涉税新闻报道,使用机器学习技术,可构建我国的税收政策不确定性指数。构建的税收政策不确定性指数能够对应我国重要税制改革事件,分阶段分年度地反映出我国税收政策不确定性的感知过程。这对学术界开展后续研究和政府部门提升税收政策确定性的感知具有一定参考价值。

Economic policy uncertainty has always been a hot topic in economic research.However,research mostly focuses on the uncertainty of overall economic policy and rarely explores the uncertainty of specific economic policy.Based on tax-related news reports from 18 Chinese mainstream media websites in the period from January 2006 to March 2019,this paper constructs an uncertainty index of China’s tax policy by using machine learning.This index corresponds to major tax reform events in China and reflects how the uncertainty of tax policy changes by stage and by year.The index has considerable reference value for scholars to conduct follow-up research and for the government to create an environment with tax certainty.