ReelFeel – Sentiment Classifier for Reviews

Project Objective: Analyze and classify movie and TV show reviews into positive or negative sentiments using natural language processing and machine learning.

Technologies Used: Pandas, NLTK, Scikit-learn, TF-IDF, Logistic Regression, Naive Bayes, Random Forest

Techniques Applied:

• Text cleaning and preprocessing (tokenization, stopword removal, stemming).
• Feature extraction with Bag-of-Words and TF-IDF.
• Model training, hyperparameter tuning, and evaluation.

Results: The Logistic Regression model achieved the highest accuracy of 0.87 on the test set. Feature importance highlighted emotional and polarizing words as key indicators of sentiment.

Skills Applied: Natural Language Processing, sentiment analysis, text classification, and model interpretation.

Conclusions: ReelFeel can be integrated into recommendation engines or content moderation tools to assess user sentiment and engagement with entertainment content.