All work
Power BI · Python · Natural Language Processing
Customer Review and Sentiment Analysis
Using the Yelp Open Dataset, this project applies a fine-tuned roBERTa sentiment model to help with customer review analysis. The dataset was prepared and explored using Python and visualized in Power BI.
- AI sentiment analysis
- Python data prep
- Geospatial analysis
What it demonstrates
- Fine-tuned roBERTa scoring
- Review text is scored by a fine-tuned roBERTa model rather than inferred from star ratings alone.
- Python preparation feeding a BI model
- The dataset was cleaned and explored in Python before it ever reached Power BI, keeping the report layer thin.
- Sentiment read against rating
- Model sentiment sits next to the reviewer's own star rating, so the cases where the two disagree become visible.
Live
The dashboard
Loading