Me and the Machines: Possibilities and Pitfalls of Using Artificial Intelligence for Qualitative Data Analysis

被引:7
|
作者
Chubb, Laura Ann [1 ,2 ,3 ]
机构
[1] Univ Auckland, Sch Counselling Human Serv & Social Work, Fac Educ & Social Work, Auckland, New Zealand
[2] Univ Auckland, Ctr Arts & Social Transformat, Fac Educ & Social Work, Auckland, New Zealand
[3] Univ Auckland, Fac Educ & Social Work, Ctr Arts & Social Transformat, Sch Counselling Human Serv & Social Work, 74 Epsom Ave, Auckland 1023, New Zealand
来源
INTERNATIONAL JOURNAL OF QUALITATIVE METHODS | 2023年 / 22卷
关键词
methods in qualitative inquiry; ChatGPT; data analysis; AI; vignettes; narrative analysis; LANGUAGE PROCESSING NLP; VIGNETTES;
D O I
10.1177/16094069231193593
中图分类号
C [社会科学总论];
学科分类号
03 ; 0303 ;
摘要
This paper describes how one researcher learned to overcome artificial intelligence (AI) paralysis and embrace ChatPDF. This freely available AI application uses natural language processing (NLP) to respond to user queries about an uploaded PDF. Researcher insights from experimenting with the AI tool ChatPDF for qualitative data analysis are presented, highlighting the advantages, pitfalls, and application-related considerations. As a two-phase curiosity experiment, the researcher engaged in a theory-building exercise to explore key concepts for understanding when using ChatPDF to assist researchers in qualitative data analysis. The experiment generated insights about the purposeful use of AI tools that incorporate NLP for analysis and the risks of inaccuracy when researchers are not familiar with the data or skilled in prompt engineering. Insights raise questions about whether ChatPDF is a viable research assistant for qualitative researchers, ethical issues with specific forms of qualitative data, and the potential of AI tools for community and student researchers.
引用
收藏
页数:16
相关论文
共 50 条