Using large language models to code group interaction: some observations from early stages of the game

Joseph A. Bonito, Jake Harwood, Stephen A. Rains and Andrew Pilny

Chapter 2 in Research Handbook on Group Decision Making, 2026, pp 19-37 from Edward Elgar Publishing

Abstract: Collecting and processing interaction data is a labor-intensive but necessary endeavor if one is to understand the dynamics of group and dyadic communication. Generative artificial intelligence (AI), especially large language models (LLMs), has the potential to both streamline data processing and illuminate new research approaches/areas, but it is not without challenges and pitfalls. In this chapter, we describe our experiences using LLMs to code group and dyadic interaction. In short, we are largely impressed with how the LLM performs when coding data but sometimes puzzled by the coding choices the machine makes. We present a relatively nontechnical description of large language models and then describe how we have applied LLMs to various types of group and interaction data.

Keywords: Group Interaction; Artifical Intelligence; Large Language Models; Content Coding; Promp Engineering (search for similar items in EconPapers)
Date: 2026
ISBN: 9781035331239
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.elgaronline.com/doi/10.4337/9781035331246.00007 (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:elg:eechap:23252_3

Ordering information: This item can be ordered from
http://www.e-elgar.com

Access Statistics for this chapter

More chapters in Chapters from Edward Elgar Publishing
Bibliographic data for series maintained by Jack Sweeney ().