Hostname: page-component-7b7567c8c-wxvwp Total loading time: 0 Render date: 2026-11-14T08:49:29.618Z Has data issue: false hasContentIssue false

Classification of natural language messages using a coordination game

Published online by Cambridge University Press:  14 March 2025

Daniel Houser*
Affiliation:
George Mason University, Fairfax, USA
Erte Xiao*
Affiliation:
Carnegie Mellon University, Pittsburgh, USA

Abstract

The role of natural language communication in economic exchange has been the focus of substantial experimental analysis. Recently, scholars have taken the important step of investigating whether certain types of communication (e.g., promises) might affect decisions differently than other types of communication. This requires classifying natural language messages. Unfortunately, no broadly-accepted method is available for this purpose. We here describe a coordination game for classification of natural language messages. The game is similar in spirit to the “ESP” game that has proven successful for the classification of tens of millions of internet images. We compare our approach to self-classification as well as to classifications based on a standard content analysis. We argue that our classification game has advantages over those alternative approaches, and that these advantages might stem from the salient rewards earned by our game's participants.

Information

Type
Research Article
Copyright
Copyright © Economic Science Association 2010

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

Article purchase

Temporarily unavailable

Supplementary material: File

Houser and Xiao supplementary material

Appendix: Transcript of Instructions to Subjects
Download Houser and Xiao supplementary material(File)
File 54.4 KB