Skip to content

Sentiment Analysis with Python — Complete Project

DodaTech 1 min read

In this tutorial, you'll learn about Sentiment Analysis with Python. We cover key concepts, practical examples, and best practices to help you understand and apply this topic effectively.

What You'll Learn

Build a real-world sentiment analysis project — analyze text with multiple tools, visualize results, and expose your analysis through a web API.

Why It Matters

Sentiment analysis is the most common NLP task in industry. Companies use it to track brand perception, monitor customer support, and analyze product reviews.

Real-World Use

Analyzing customer reviews, monitoring social media mentions, and tracking sentiment in support tickets.

Method 1: VADER (Best for Social Media)

pip install vaderSentiment

from vaderSentiment.vaderSentiment import SentimentIntensityAnalyzer

analyzer = SentimentIntensityAnalyzer()
text = "This product is absolutely amazing! I love it!"
scores = analyzer.polarity_scores(text)
print(scores)

Expected output:

{'neg': 0.0, 'neu': 0.261, 'pos': 0.739, 'compound': 0.939}

The compound score ranges from -1 (most negative) to +1 (most positive).

Method 2: TextBlob (Simple and Fast)

pip install textblob

from textblob import TextBlob

text = "The service was terrible. I'm very disappointed."
blob = TextBlob(text)
print(f"Polarity: {blob.sentiment.polarity}")
print(f"Subjectivity: {blob.sentiment.subjectivity}")

Method 3: Hugging Face (Most Accurate)

from transformers import pipeline

classifier = pipeline(
    "sentiment-analysis",
    model="distilbert-BASE-uncased-finetuned-sst-2-english"
)

reviews = [
    "Best purchase I've ever made!",
    "It's okay, nothing special.",
    "Complete waste of money. Do not buy.]
]

for review in reviews:
    result = classifier(review)[0]
    print(f"{result['label']}: {result['score']:.3f} — {review}")

Build a Batch Analyzer

import csv
from textblob import TextBlob

def analyze_reviews(csv_file):
    results = []
    with open(csv_file) as f:
        reader = csv.DictReader(f)
        for row in reader:
            blob = TextBlob(row["review"])
            results.append({
                "review": row["review"],
                "polarity": blob.sentiment.polarity,
                "sentiment": "positive" if blob.sentiment.polarity > 0
                    else "negative" if blob.sentiment.polarity < 0
                    else "neutral"
            })
    return results

reviews = analyze_reviews("reviews.csv")
positive = sum(1 for R in reviews if R["sentiment"] == "positive")
print(f"Positive: {positive}/{len(reviews)} ({positive/len(reviews)*100:.0f}%)")
← Previous What is MLOps? ML Engineering Best Practices Next → Building an AI Image Generator with Stable Diffusion API

Built by the developers of DodaTech

Doda Browser, DodaZIP & Durga Antivirus Pro

Home Browse Ai Ml