人工智能对劳动收入份额的影响研究——基于技能偏向性视角的理论阐释与实证检验

Research on the Influence of Artificial Intelligence on Labor Income Share—Theoretical Interpretation and Empirical Test Based on Skill Bias

在新一轮科技革命和产业变革加速演进、构建更加完善的要素市场化配置体制机制成为中国高质量发展内在要求的背景下,本文基于2008—2017年中国省级面板数据,考察了人工智能对劳动收入份额的影响机制及其具体的作用效应。研究结果显示:人工智能在短期内不利于劳动收入份额的提升,并且这种抑制作用在第一产业中表现得尤为明显。在改变估计方法、替换关键变量、调整控制变量后这一结果依然稳健。进一步,中介机制检验结果表明,人工智能会通过就业技能结构高级化、技能收入差距扩大化两个渠道降低劳动收入份额。异质性检验结果显示人工智能对西部地区、非技术密集区以及高劳动收入份额地区的抑制作用更大。

Under the background that the acceleration of evolution in the new round of technological revolution and industrial revolution and the construction of a more perfect factor marketization system become the internal requirement of China's high quality development,this paper based on 2008-2017 provincial panel data of China,examines the influence mechanism of artificial intelligence on labor income share.It is found that:in the short term,artificial intelligence is not conducive to the increase of labor income share,and this inhibitory effect is particularly obvious in the primary industry.After changing the estimation method,replacing the key variables and adjusting the control variables,the result is still robust.Furthermore,the results of the intermediary mechanism test show that artificial intelligence will reduce the labor income share through two channels:the concentration of employment skill structure and the widening of the skill income gap.Finally,the results of the heterogeneity test showed that artificial intelligence had a greater inhibitory effect on the western region,the non-technology intensive region and the region with high labor income share.