Algorithmic Assortative Matching on a Digital Social Medium

Information Systems Research

59 Pages Posted: 28 Nov 2021 Last revised: 27 Apr 2022

See all articles by Kristian López Vargas

Kristian López Vargas

University of California, Santa Cruz

Julian Runge

Duke University (Visiting Scholar)

Ruizhi (Rachel) Zhang

University of California, Santa Cruz

Date Written: April 17, 2022

Abstract

Humans are increasingly interacting in and operating their daily lives through structured digital and virtual environments, mainly through apps that provide media for sharing photos, messaging, gaming, collaborating, or video watching. Most of these digital environments are offered under “freemium” pricing to facilitate adoption and network effects. In these settings, users’ early social interaction and experience often have a substantial impact on their longer-term behavior. On this background, we study the impact of an algorithmic system that matches new users to existing communities in an assortative manner. We devise a machine learning-based matching system that identifies users with high expected value and provides them the option to join highly active, in terms of engagement and expenditure, teams. We deploy this mechanism experimentally in a digital social game and find that it significantly increases user engagement, spending, and socialization. This finding holds for more active communities and overall. Teams matched with low-activity new users are negatively impacted, leading to an overall more segregated social environment. We argue that social experience and social behavior in groups are likely mechanisms that drive the impact of the matching system.

Keywords: Assortative Matching, Social Media, Field Experiments, Freemium, Systems Design and Implementation

JEL Classification: M310, C93, C78

Suggested Citation

López Vargas, Kristian and Runge, Julian and Zhang, Ruizhi, Algorithmic Assortative Matching on a Digital Social Medium (April 17, 2022). Information Systems Research, Available at SSRN: https://ssrn.com/abstract=3972913 or http://dx.doi.org/10.2139/ssrn.3972913

Kristian López Vargas (Contact Author)

University of California, Santa Cruz ( email )

1156 High Street
Economics
Santa Cruz, CA 95064
United States

HOME PAGE: http://kmlv.github.io/

Julian Runge

Duke University (Visiting Scholar) ( email )

Box 90120
Durham, NC 27708-0120
United States

Ruizhi Zhang

University of California, Santa Cruz ( email )

1156 High St
Santa Cruz, CA 95064
United States

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

Paper statistics

Downloads
65
Abstract Views
329
rank
463,960
PlumX Metrics