Confusion Matrix showing the results of a sentiment analysis model tested on 500 movie reviews.
A sentiment analysis model was built to classify movie reviews as either Positive or Negative. The model was tested on a dataset of 500 reviews, resulting in the following confusion matrix :
Generated by claude-sonnet-4-6 · 2026-06-21 03:19 · grounding stimulus
Model Answer
(a) True Positives (TP) = 300
(Cases where the model correctly predicted a review as Positive, and it actually was Positive.)
---
(b)
Given: TP = 300, FP = 60, FN = 40, TN = 100
$$\text{Precision} = \frac{TP}{TP + FP} = \frac{300}{300 + 60} = \frac{300}{360} \approx 0.833$$
$$\text{Recall} = \frac{TP}{TP + FN} = \frac{300}{300 + 40} = \frac{300}{340} \approx 0.882$$
$$\text{F1-Score} = \frac{2 \times \text{Precision} \times \text{Recall}}{\text{Precision} + \text{Recall}} = \frac{2 \times 0.833 \times 0.882}{0.833 + 0.882} = \frac{1.469}{1.715} \approx \mathbf{0.857}$$
---
Explanation
- Part (a): TP is simply read directly from the confusion matrix cell (Reality Yes, Predicted Yes).
- Part (b): Remember the three formulas — Precision measures how many predicted positives are correct; Recall measures how many actual positives were caught; F1-Score balances both. Always substitute values clearly step-by-step for full marks.