Qumo/Interview-Analysis
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

multi theme handling

Browse Source
This commit is contained in:
Luigi Maiorano
2025-12-01 17:19:46 +01:00
parent 3a333cb0f2
commit b21f402e1e
1 changed files with 1 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
Architecture_Overview.py
View File

@@ -82,6 +82,7 @@ def _(mo):
2. **Process:**
* The LLM analyzes each transcript segment-by-segment.
* It extracts specific quotes that match a Theme Definition.
* **Multi-Theme Handling:** If a quote applies to multiple themes, it is tagged with *all* relevant themes. In the dataset, this creates multiple entries (one per theme) so the quote informs the synthesis of each relevant topic.
* **Granular Sentiment Analysis:** For each quote, the model identifies:
* **Subject:** The specific topic/object being discussed (e.g., "Login Flow", "Brand Tone").
* **Sentiment:** Positive / Neutral / Negative.