SPEAKER: 薛闻道，德州大学奥斯汀分校，访问学者

TIME/DATE: 2024年7月5日下午15:30-17:00

CLASSROOM: 同济大厦A楼2020教室

TENCENT： 541 610 851

PW： 415800

ABSTRACT:

Information systems (IS) researchers utilize machine learning algorithms to identify emotions in vast online content and investigate their impact on business outcomes. Large language models (LLMs) serve as automatic emotion analyzers, presenting new avenues for advancing the causal understanding of emotions in IS research. However, directly using LLM-generated emotional variables in econometric models can introduce bias due to LLMs’ imperfect emotion recognition, which introduces noise into causal models. To address this, we propose a novel algorithm that considers predictions from multiple LLMs to create fuzzy interval data, enabling partial identification of causal parameters. The algorithm satisfies three key design requirements: it operates in an unsupervised manner, eliminating the need for additional labeled data for causal estimation; it is flexible by integrating predictions from different LLMs, harnessing collective AI insights; and it ensures theoretically consistent causal estimators. This research has significant implications for causal inference using LLMs, the study of emotions in causal contexts, and prescriptive analytics for handling fuzzy interval data.

GUEST BIO:

Dr. Wendao Xue is a visiting scholar at the Department of Information, Risk, and Operations Management, McCombs School of Business, The University of Texas at Austin. Her primary research interests lie in AI/machine learning (ML)-enabled causal inference and data analytics.

She’s interested in AI/ML-enabled causal inference from three perspectives: 1. Exploring new opportunities for using AI/ML to improve causal inference methodologies; 2. Identifying challenges in the current applications of AI/ML in causal inference; 3. Investigating innovative applications of generative AIs, from an empirical perspective. Some of her works are currently under revision by Management Science and Production and Operations Management.

She received a Ph.D. from University of Washington and a B.A. from Shanghai University of Finance and Economics.