题　目：The Impact of Recommender Systems on Content Consumption and Production: Evidence from Field Experiments and Structural Modeling

嘉　宾：Zhiyu Zeng, Postdoctoral Research Associate, Washington University in St. Louis

主持人：花成 副教授 awc777万象城娱乐官网

时　间：2024年12月18日（周三）14:00-15:30

地　点：安泰楼A403室

内容简介：

Online content-sharing platforms such as TikTok and Facebook have become integral to daily life, leveraging complex algorithms to recommend user-generated content (UGC) to other users. While prior research and industry efforts have primarily focused on designing recommender systems to enhance users’ content consumption, the impact of recommender systems on content production remains understudied. To address this gap, I conducted a randomized field experiment on one of the world’ s largest video-sharing platforms. The experiment manipulated the algorithm’ s recommendation of creators based on their popularity, excluding a subset of highly popular creators’ content from being recommended to the treatment group. The experimental results indicate that recommending content from less popular creators led to a significant 1.34% decrease in video-watching time but a significant 2.71% increase in the number of videos uploaded by treated users. This highlights a critical trade-off in designing recommender systems: popular creator recommendations boost consumption but reduce production. To optimize recommendations, I developed a structural model wherein users’ choices between content consumption and production are inversely affected by recommended creators’ popularity. Counterfactual analyses based on the structural model reveal that the optimal strategy often involves recommending the content from less popular creators to enhance production, challenging current industry practices. Thus, a balanced approach in designing recommender systems is essential to simultaneously foster content consumption and production.

演讲人简介：

Zhiyu Zeng is a Postdoc Associate at the Olin Business School, Washington University in St. Louis. In 2023, she earned a Ph.D. in Management Science and Engineering from Tsinghua University, where she was advised by Prof. Zuo-Jun Max Shen. In 2018, Zhiyu completed bachelor's degrees in both Industrial Engineering and Business Administration, also at Tsinghua University.

She is an empirical researcher specializing in social media and AI, utilizing a combination of methods including field experiments, structural models, and AI techniques. Since 2018, she has been working at a leading social media company. Her research bridges theoretical development and practical applications by addressing complex real-world challenges that demand innovative solutions. For more information, please see her personal website: https://zhiyuzeng.org/.

欢迎广大师生参加！