Task 4: Public Sentiment Analysis using Twitter Data

This project was done as part of my internship at Prodigy Infotech (June 2025) in the Data Science domain.

📌 Objective:

To analyze public sentiment based on tweets using Natural Language Processing (NLP) techniques and classify them as Positive, Negative, or Neutral.

🛠️ Tools & Libraries:

• Python
• Tweepy (or pre-downloaded dataset)
• Pandas, NumPy
• NLTK / TextBlob / VaderSentiment
• Matplotlib / Seaborn for visualization
• Scikit-learn (for model training & evaluation)

🔎 Steps Followed:

• Collected or loaded tweet data
• Text preprocessing (cleaning, tokenization, removing stopwords, etc.)
• Sentiment labeling using TextBlob or Vader
• Visualized sentiment distribution using bar/pie charts
• Trained classification model (optional step)

✅ Output:

• Successfully analyzed sentiments from Twitter data.
• Visualized public opinion using charts.
• (Optional) Achieved good accuracy with ML-based sentiment classification.

---

👩‍💻 Anika
BTech CSE (AI & DS) | Intern at Prodigy Infotech