Algorithmic Governance via Recommender Systems: The Case of Short Video Platform

44 Pages Posted: 10 Oct 2023 Last revised: 3 Jan 2024

See all articles by Jinghui Zhang

Jinghui Zhang

Tsinghua University - School of Economics & Management

Mochen Yang

University of Minnesota - Twin Cities - Carlson School of Management

Xuan Bi

University of Minnesota - Twin Cities - Carlson School of Management

Qiang Wei

Tsinghua University - School of Economics & Management

Date Written: January 3, 2024

Abstract

Two-sided platforms face a number of governance challenges such as encouraging participation and managing activities. Traditional economic incentives and mechanisms for platform governance are increasingly complemented by algorithmic strategies, which can leverage fine-grained data collected from platform participants and their activities to achieve more granular and personalized control. In this paper, we study algorithmic governance of digital content platforms, and demonstrate how important governance objectives can be achieved by changing the recommendation strategy. Taking short video platforms as the specific context, we design an integer programming framework that determines how videos created by producers are recommended to consumers. Different from the common "preference-maximizing" strategy that recommends content solely based on consumer preference, our proposed integer program aims to maximize platform revenue (from ads embedded in videos) subject to constraints that control exposure disparity among producers as well as violations of consumer preferences. We conduct both backtesting and prediction-based evaluations on a well-curated public dataset from KuaiShou (a leading short video platform in China) and compare our approach with the preference-maximizing recommendation strategy. We find that recommendations generated by our integer program simultaneously lead to higher platform revenue, lower producer exposure disparity, and improved consumer experiences (in terms of higher information diversity and less repetitive viewing). Further analyses reveal interesting relationships between settings of the integer program and governance outcomes. As an example, we observe that adhering to consumer preferences too much or too little can both increase exposure disparity among producers, and a moderate constraint on consumer preference compliance may sometimes lead to greater producer exposure fairness. Our work contributes to the emerging literature on algorithmic platform governance and offers practical design artifacts that are readily applicable to short video platforms.

Keywords: recommender system, two-sided platform, governance, short video recommendation, prescriptive analytics

Suggested Citation

Zhang, Jinghui and Yang, Mochen and Bi, Xuan and Wei, Qiang, Algorithmic Governance via Recommender Systems: The Case of Short Video Platform (January 3, 2024). Available at SSRN: https://ssrn.com/abstract=4572513 or http://dx.doi.org/10.2139/ssrn.4572513

Jinghui Zhang

Tsinghua University - School of Economics & Management ( email )

Beijing, 100084
China

Mochen Yang (Contact Author)

University of Minnesota - Twin Cities - Carlson School of Management ( email )

19th Avenue South
Minneapolis, MN 55455
United States

Xuan Bi

University of Minnesota - Twin Cities - Carlson School of Management ( email )

19th Avenue South
Minneapolis, MN 55455
United States

Qiang Wei

Tsinghua University - School of Economics & Management ( email )

Beijing, 100084
China
+86-10-62789824 (Phone)
+86-10-62771647 (Fax)

HOME PAGE: http://www.sem.tsinghua.edu.cn/en/weiq

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
134
Abstract Views
380
Rank
397,015
PlumX Metrics