Optimizing Generative AI's Accuracy and Transparency in Inductive Thematic Analysis: A Human-AI Comparison
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908279626530816 |
|---|---|
| author | Nyaaba, Matthew SungEun, Min Apam, Mary Abiswin Acheampong, Kwame Owoahene Dwamena, Emmanuel |
| author_facet | Nyaaba, Matthew SungEun, Min Apam, Mary Abiswin Acheampong, Kwame Owoahene Dwamena, Emmanuel |
| contents | This study highlights the transparency and accuracy of GenAI's inductive thematic analysis, particularly using GPT-4 Turbo API integrated within a stepwise prompt-based Python script. This approach ensured a traceable and systematic coding process, generating codes with supporting statements and page references, which enhanced validation and reproducibility. The results indicate that GenAI performs inductive coding in a manner closely resembling human coders, effectively categorizing themes at a level like the average human coder. However, in interpretation, GenAI extends beyond human coders by situating themes within a broader conceptual context, providing a more generalized and abstract perspective. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_16485 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Optimizing Generative AI's Accuracy and Transparency in Inductive Thematic Analysis: A Human-AI Comparison Nyaaba, Matthew SungEun, Min Apam, Mary Abiswin Acheampong, Kwame Owoahene Dwamena, Emmanuel Human-Computer Interaction Artificial Intelligence This study highlights the transparency and accuracy of GenAI's inductive thematic analysis, particularly using GPT-4 Turbo API integrated within a stepwise prompt-based Python script. This approach ensured a traceable and systematic coding process, generating codes with supporting statements and page references, which enhanced validation and reproducibility. The results indicate that GenAI performs inductive coding in a manner closely resembling human coders, effectively categorizing themes at a level like the average human coder. However, in interpretation, GenAI extends beyond human coders by situating themes within a broader conceptual context, providing a more generalized and abstract perspective. |
| title | Optimizing Generative AI's Accuracy and Transparency in Inductive Thematic Analysis: A Human-AI Comparison |
| topic | Human-Computer Interaction Artificial Intelligence |
| url | https://arxiv.org/abs/2503.16485 |