Abstract

Machine Learning models have become more advanced than could have been supposed even a few years ago, often surpassing human performance on many tasks. Large language models (LLM) can produce text indistinguishable from human-produced text. This begs the question, how necessary are humans - even for tasks where humans appear indispensable? Qualitative Analysis (QA) is integral to human-computer interaction research, requiring both human-produced data and human analysis of that data to illuminate human opinions about and experiences with technology. We use GPT-3 and ChatGPT to replace human analysis and then to dispense with human-produced text altogether. We find GPT-3 is capable of automatically identifying themes and generating nuanced analyses of qualitative data arguably similar to those written by human researchers. We also briefly ponder philosophical implications of this research.

Degree

MS

College and Department

Physical and Mathematical Sciences; Computer Science

Rights

https://lib.byu.edu/about/copyright/

Date Submitted

2023-11-14

Document Type

Thesis

Handle

http://hdl.lib.byu.edu/1877/etd12996

Keywords

Natural language processing, human-computer interaction, qualitative research

Language

english

Share

COinS