Summary of Thematic Analysis with Open-source Generative Ai and Machine Learning: a New Method For Inductive Qualitative Codebook Development, by Andrew Katz and Gabriella Coloyan Fleming and Joyce Main
Thematic Analysis with Open-Source Generative AI and Machine Learning: A New Method for Inductive Qualitative Codebook Development
by Andrew Katz, Gabriella Coloyan Fleming, Joyce Main
First submitted to arxiv on: 28 Sep 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary A novel machine learning-based approach for thematic analysis in social science research is proposed, leveraging open-source generative text models and natural language processing tools. The Generative AI-enabled Theme Organization and Structuring (GATOS) workflow combines retrieval-augmented generation, prompt engineering, and generative text models to identify codes and themes in large volumes of text, mimicking an inductive coding process. Three case studies demonstrate the effectiveness of this approach in producing codebooks that approach the known space of themes and sub-themes. The GATOS workflow is shown to be applicable to various research settings, including organizational cultures, employee perspectives, and teammate feedback. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary A team of researchers created a new way to analyze texts using artificial intelligence. They made a special process called GATOS that uses computer models and language tools to find important themes in large amounts of text. This helps scientists study social science topics like teamwork, office cultures, and employee feelings. The GATOS method is like a human researcher looking at each piece of text, thinking about what they already know, and deciding if they need a new idea. Three examples show that this approach works well. |
Keywords
» Artificial intelligence » Machine learning » Natural language processing » Prompt » Retrieval augmented generation
