Sentiment Analysis for Review

An NLP-based sentiment analysis tool to automatically classify customer reviews and predict star ratings.

🌟 Project Overview

This project addresses the challenge of manually sifting through large volumes of customer feedback. By leveraging Natural Language Processing (NLP) and Machine Learning, this tool provides a fast and scalable solution for understanding customer sentiment. The core of this project is a model that analyzes text from customer reviews and predicts a corresponding star rating, providing actionable insights into product satisfaction.

The key features of this tool include:

• Automated Sentiment Classification: Automatically categorizes reviews as positive, neutral, or negative.

• Star Rating Prediction: A machine learning model that predicts the star rating (1 to 5) based on the review text.

• Scalable Solution: Designed to handle thousands of reviews efficiently, saving time and resources.

• Actionable Insights: Enables businesses to quickly identify product strengths and weaknesses, and prioritize feedback for product development.

📊 Dataset

Source Link: https://www.kaggle.com/competitions/mlp-term-2-2025-kaggle-assignment-3/data

The model is trained on a dataset of customer reviews. The dataset should contain:

• id: The index column
• store_name: Name of the store
• category: Type of restaurant
• store_address: Address of the restaurant
• latitude: Latitude
• longitude: Longitude
• rating_count: Current count of ratings received
• review_time: Time since the posting of review
• review: review provided by the customer
• rating: Rating given by the customer (target variable)

🛠️ Technologies & Skills

• Python: The primary programming language.

• Natural Language Processing (NLP): The core technique used for text analysis.

• Sentiment Analysis: The specific application of NLP to determine the emotional tone of text.

• Machine Learning: Used to build the predictive model.

• Data Visualization: To present insights and model performance (e.g., using Matplotlib).

• Pandas & NumPy: For data manipulation and numerical operations.

• NLTK & TextBlob: Libraries for NLP tasks like tokenization and sentiment scoring.