Less-is-more in a 5-star rating system: an experimental study of human combined decisions in a multi-armed bandit problem

TL;DR

This study investigates how humans make combined decisions in a multi-armed bandit setting, focusing on the impact of social information and free-rider problems on collective decision-making performance.

Contribution

It provides experimental evidence on human decision strategies in social learning contexts within multi-armed bandit problems, highlighting the effects of free-riding.

Findings

Humans tend to rely on social information when available.

Free-riders can undermine collective decision efficiency.

Social learning can both improve and impair performance depending on group dynamics.

Abstract

Given the rapid proliferation of advanced information technologies, including the Internet, modern humans can easily access vast amount of socially transmitted information. Intuitively, this situation is isomorphic to some eusocial insects that are known to solve the exploration-exploitation dilemma collectively through information transfer (e.g., honeybees [Seeley et al., 1991]; and ants [Shaffer, Sasaki & Pratt, 2013]). Yet, in contrast from the eusocial insects, whose colonies are composed of kin, human collective performance may be affected by an inherent free-rider problem [Bolton & Harris, 1999; Kameda, Tsukasaki, Hastie & Berg, 2011]. Specifically, in groups involving non-kin members, it is expected that free-riders, who allow others to search for better alternatives and then exploit their findings through social learning ("information scroungers"), will frequently appear, and consequently undermine the advantage of collective intelligence [Rogers, 1998; Kameda & Nakanishi, 2003].