Restaurant Review Sentiment Analysis

Solution for the use case Restaurant Review Sentiment Analyzer.

AI tools

Python, TextBlob, NLTK, Pandas, Matplotlib, Word Cloud

Language

Python

Accuracy

88%

Published

2025-07-01

Code (Python)

from textblob import TextBlob
import pandas as pd
import matplotlib.pyplot as plt

class RestaurantSentimentAnalyzer:
    def __init__(self):
        self.reviews = []
        self.sentiments = []
        
    def analyze_review(self, review_text):
        blob = TextBlob(review_text)
        sentiment = blob.sentiment.polarity
        
        if sentiment > 0.1:
            category = "Positive"
        elif sentiment < -0.1:
            category = "Negative"
        else:
            category = "Neutral"
            
        return {
            "text": review_text,
            "sentiment_score": sentiment,
            "category": category,
            "keywords": [word for word in blob.words if len(word) > 3]
        }
        
    def batch_analyze(self, reviews_list):
        results = []
        for review in reviews_list:
            analysis = self.analyze_review(review)
            results.append(analysis)
        return results
        
    def generate_report(self, analyses):
        positive = len([a for a in analyses if a["category"] == "Positive"])
        negative = len([a for a in analyses if a["category"] == "Negative"])
        neutral = len([a for a in analyses if a["category"] == "Neutral"])
        
        return {
            "total_reviews": len(analyses),
            "positive_percentage": positive / len(analyses) * 100,
            "negative_percentage": negative / len(analyses) * 100,
            "overall_sentiment": "positive" if positive > negative else "negative"
        }

Prompts

Analyze this restaurant review: The food was amazing and the service was quick, but the restaurant was quite noisy and hard to have a conversation.