Abstract

Content analysis is a common research method in technical and professional communication (TPC) journals. But TPC content analyses often lack intercoder reliability (ICR) statistics, possibly due to the lack of resources required to train human coders. This proof-of-concept study explores the viability of replacing a second coder with a generative AI tool to calculate an ICR. Using three previously published studies, I calculated a Krippendorff's alpha for various data types and various codebooks using non-modified versions of five popular generative AI tools. While the tools could code TPC data, most tools did not produce alphas strong enough to replace human coders. While it is premature in most cases to replace human coders with generative AI tools to calculate an ICR, generative AI may prove to be useful to researchers as a means of codebook and unit of analysis refinement prior to human coding.

Journal
Communication Design Quarterly
Published
2025-03-01
DOI
10.1145/3718959.3718962
CompPile
Search in CompPile ↗
Topics

Citation Context

Cited by in this index (0)

No articles in this index cite this work.

Cites in this index (3)

  1. Journal of Business and Technical Communication
  2. Technical Communication Quarterly
  3. Journal of Technical Writing and Communication
Also cites 10 works outside this index ↓
  1. 10.1007/978-3-031-42682-7_3
  2. 10.1093/oxfordhb/9780195399813.013.023
  3. 10.1109/TPC.2010.2077450
  4. 10.36834/cmej.72504
  5. 10.1007/s00146-023-01715-z
  6. 10.1109/TPC.2023.3314250
  7. 10.37514/PRA-B.2019.0230
  8. 10.1111/j.1468-2958.2002.tb00826.x
  9. 10.4135/9781071802878
  10. 10.1177/1609406919899220
CrossRef global citation count: 1 View in citation network →