Sentiment Analysis with Python

Sentiment Analysis is a Natural Language Processing (NLP) technique used to determine whether a given text expresses a positive, negative, or neutral sentiment.

---

Installing Required Libraries

pip install nltk textblob vaderSentiment

---

Step 1: Sentiment Analysis with TextBlob

from textblob import TextBlob

text = "I love programming in Python! It's so intuitive and powerful."

# Perform sentiment analysis
analysis = TextBlob(text)

# Sentiment polarity (-1 to 1, where -1 is negative and 1 is positive)
print("Sentiment Polarity:", analysis.sentiment.polarity)

# Sentiment subjectivity (0 to 1, where 0 is objective and 1 is subjective)
print("Sentiment Subjectivity:", analysis.sentiment.subjectivity)

TextBlob is simple and useful for basic sentiment analysis.

---

Step 2: Sentiment Analysis with VADER (Best for Social Media & Short Texts)

from vaderSentiment.vaderSentiment import SentimentIntensityAnalyzer

analyzer = SentimentIntensityAnalyzer()

text = "This movie was absolutely fantastic! I loved every second of it."

# Compute sentiment scores
scores = analyzer.polarity_scores(text)

print("Sentiment Scores:", scores)

# Determine sentiment
if scores['compound'] >= 0.05:
    print("Overall Sentiment: Positive 😊")
elif scores['compound'] <= -0.05:
    print("Overall Sentiment: Negative 😠")
else:
    print("Overall Sentiment: Neutral 😐")

VADER works best with social media posts and short, informal text.

---

Step 3: Sentiment Analysis with Machine Learning (Using NLTK & Naive Bayes)

import nltk
from nltk.classify import NaiveBayesClassifier
from nltk.classify.util import accuracy

nltk.download('punkt')

# Training dataset
train_data = [
    ("I love this phone!", "Positive"),
    ("This is an amazing experience", "Positive"),
    ("I hate this movie!", "Negative"),
    ("This is the worst product ever", "Negative"),
    ("I am feeling great today!", "Positive"),
    ("Not a good experience", "Negative"),
]

# Feature extractor
def extract_features(text):
    words = nltk.word_tokenize(text.lower())
    return {word: True for word in words}

# Prepare dataset
train_set = [(extract_features(text), label) for text, label in train_data]

# Train Naive Bayes classifier
classifier = NaiveBayesClassifier.train(train_set)

# Test a sample sentence
test_text = "I really love this amazing phone!"
print("Prediction:", classifier.classify(extract_features(test_text)))

Naive Bayes is a simple but effective classifier for text-based sentiment analysis.

---

Applications of Sentiment Analysis

✔ Social Media Monitoring – Analyze Twitter & Facebook posts.
✔ Customer Reviews – Analyze product feedback.
✔ Market Analysis – Understand consumer sentiment for businesses.
✔ Political Analysis – Analyze public opinion on policies & elections.