eNPS Feedback Analysis with Python
An in-progress Python analysis of natural-language eNPS feedback that surfaces recurring keywords and key themes in employee comments, visualised with Plotly.
At a glance
-
Natural-language eNPS feedback is hard to read at scale, so recurring themes in employee comments are easy to miss.
-
Python analysis that surfaces recurring keywords and identifies the key themes in employee comments, with Plotly visualisations.
-
Sentiment scoring — positive, neutral or negative — for each comment.
Overview
Employee Net Promoter Score (eNPS) surveys collect free-text comments alongside the score. Those comments explain why people answered the way they did, but they are hard to read at scale.
This project uses Python to analyse natural-language eNPS feedback, surface recurring keywords and identify the key themes in employee comments, with Plotly visualisations to present the results.
Status: in progress.
Approach
- Load the feedback with pandas and openpyxl
- Use scikit-learn to surface recurring keywords and group comments into key themes
- Visualise keywords and themes with Plotly
Next Phase (planned)
- Sentiment scoring for each comment — positive, neutral or negative. This is planned and not yet built.
Technologies & Tools
- Python – Analysis
- pandas – Data handling
- scikit-learn – Keyword and theme extraction
- Plotly – Visualisation
- openpyxl – Reading Excel inputs