Exploring the Use of Artificial Intelligence for Qualitative Data Analysis: The Case of ChatGPT
The potential use of artificial intelligence programs such as a ChatGPT to analyze qualitative data raises any number of questions, most notably whether it is possible to produce similar results without the demanding process of manual coding. In addition, there are questions about both the simplicit...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SAGE Publishing
2023-10-01
|
| Series: | International Journal of Qualitative Methods |
| Online Access: | https://doi.org/10.1177/16094069231211248 |
| _version_ | 1797644725485830144 |
|---|---|
| author | David L. Morgan |
| author_facet | David L. Morgan |
| author_sort | David L. Morgan |
| collection | DOAJ |
| description | The potential use of artificial intelligence programs such as a ChatGPT to analyze qualitative data raises any number of questions, most notably whether it is possible to produce similar results without the demanding process of manual coding. In addition, there are questions about both the simplicity of using ChatGPT for qualitative data analysis and the potential time savings that it might provide This article addresses these questions by using ChatGPT to reinvestigate two qualitative datasets that were previously analyzed by more traditional methods. In particular, it examines the extent to which the responses from ChatGPT can recreate the themes that were originally chosen to summarize the two previous analyses. The results show that ChatGPT performed reasonably well, but in both cases it was less successful at locating subtle, interpretive themes, and more successful at reproducing concrete, descriptive themes. In doing so, the program was quite easy to use and required very little effort in comparison to approaches that rely on manual coding. It is important to recognize, however, that both coding and approaches based on artificial intelligence are simply tools that must be applied within a larger analytic process. Overall, this exploration suggests that artificial intelligence may well have the power to disrupt the coding of data segments as a dominant paradigm for qualitative data analysis. |
| first_indexed | 2024-03-11T14:34:58Z |
| format | Article |
| id | doaj.art-f3c9e1dab4304a2f89027a1a02d9c482 |
| institution | Directory Open Access Journal |
| issn | 1609-4069 |
| language | English |
| last_indexed | 2024-03-11T14:34:58Z |
| publishDate | 2023-10-01 |
| publisher | SAGE Publishing |
| record_format | Article |
| series | International Journal of Qualitative Methods |
| spelling | doaj.art-f3c9e1dab4304a2f89027a1a02d9c4822023-10-31T05:34:52ZengSAGE PublishingInternational Journal of Qualitative Methods1609-40692023-10-012210.1177/16094069231211248Exploring the Use of Artificial Intelligence for Qualitative Data Analysis: The Case of ChatGPTDavid L. MorganThe potential use of artificial intelligence programs such as a ChatGPT to analyze qualitative data raises any number of questions, most notably whether it is possible to produce similar results without the demanding process of manual coding. In addition, there are questions about both the simplicity of using ChatGPT for qualitative data analysis and the potential time savings that it might provide This article addresses these questions by using ChatGPT to reinvestigate two qualitative datasets that were previously analyzed by more traditional methods. In particular, it examines the extent to which the responses from ChatGPT can recreate the themes that were originally chosen to summarize the two previous analyses. The results show that ChatGPT performed reasonably well, but in both cases it was less successful at locating subtle, interpretive themes, and more successful at reproducing concrete, descriptive themes. In doing so, the program was quite easy to use and required very little effort in comparison to approaches that rely on manual coding. It is important to recognize, however, that both coding and approaches based on artificial intelligence are simply tools that must be applied within a larger analytic process. Overall, this exploration suggests that artificial intelligence may well have the power to disrupt the coding of data segments as a dominant paradigm for qualitative data analysis.https://doi.org/10.1177/16094069231211248 |
| spellingShingle | David L. Morgan Exploring the Use of Artificial Intelligence for Qualitative Data Analysis: The Case of ChatGPT International Journal of Qualitative Methods |
| title | Exploring the Use of Artificial Intelligence for Qualitative Data Analysis: The Case of ChatGPT |
| title_full | Exploring the Use of Artificial Intelligence for Qualitative Data Analysis: The Case of ChatGPT |
| title_fullStr | Exploring the Use of Artificial Intelligence for Qualitative Data Analysis: The Case of ChatGPT |
| title_full_unstemmed | Exploring the Use of Artificial Intelligence for Qualitative Data Analysis: The Case of ChatGPT |
| title_short | Exploring the Use of Artificial Intelligence for Qualitative Data Analysis: The Case of ChatGPT |
| title_sort | exploring the use of artificial intelligence for qualitative data analysis the case of chatgpt |
| url | https://doi.org/10.1177/16094069231211248 |
| work_keys_str_mv | AT davidlmorgan exploringtheuseofartificialintelligenceforqualitativedataanalysisthecaseofchatgpt |