The next steps of this research project include:
- Consulting a data analysis expert for coding advice.
- Adjusting the code to further clean the transcript data.
- Applying the code to the entire corpus of transcript data.
- Complete GuidedLDA analysis using a seed list creating from the entire corpus.
- Complete an LLM analysis of the same dataset.
- Compare the GuidedLDA machine learning results to the LLM analysis results.
- Investigate additional methods of analysis.
- Utilize the seed list to create a tag list that librarians can use when answering future chats.
