现代产业经济学系列讲座第286期

时间：2025年11月12日（周三）13:30-15:00

地点： 复旦管院史带楼303室

题目：GenAI-Enabled Causal Study of Unstructured Data: Application in LLMs and Emotion Analysis

主讲人：薛闻道 博士后(德克萨斯大学奥斯汀分校)

主持人：李玲芳 教授

摘要：Researchers use machine learning algorithms to extract features in massive and unstructured online content and then study the causal effect of these features on various business outcomes. Generative AI (GenAI), as an automatic unstructured data analyzer, offers new opportunities for researchers to advance the current causal study of unstructured data. Nevertheless, we show that directly plugging GenAI-generated variables into econometric models can induce bias in causal estimation. We propose a novel algorithm to correct such bias. A key feature is that the algorithm leverages predictions generated by different GenAIs to form fuzzy interval data. The algorithm meets three design principles. First, it is unsupervised, meaning it does not need additional labeled data to correct the causal estimation. Second, it is flexible in incorporating the predictions of different GenAIs (leveraging the “wisdom of the AI crowd”) and can be easily adapted to various causal models. Third, the causal estimators are theoretically guaranteed to achieve consistency. We apply our algorithm in the context of using LLMs as emotion analyzers. This work provides important implications for causal inference with GenAIs, the causal study of unstructured data, and prescriptive analytics for fuzzy interval data.

报告人介绍：Wendao Xue is a postdoctoral researcher at the Department of Information, Risk, and Operations Management at the McCombs School of Business, The University of Texas at Austin. She received her Ph.D. degree in economics from the University of Washington.

Her research focuses on Causal AI and data analytics. In particular, she studies Causal AI from three angles: exploring new opportunities to use AI/ML to improve causal inference methods; identifying challenges in current applications of AI/ML to causal inference; and investigating innovative applications of AI. She is interested in applying novel data-analytic methods to identify and solve challenging, practical problems that benefit businesses, health care, and society. She is developing an ongoing research agenda on the impact of generative AI in business and organizations. Her research methods include machine learning, causal inference, econometrics, and lab experiments.