AI Powered Sentiment Analysis and Review Summarization with Transformers

This project focuses on building a sentiment analysis and review summarization system using artificial intelligence techniques. The dataset used is the IMDB movie reviews dataset, which contains labeled textual data for binary classification. The system uses multiple models to compare performance, including the Random Forest (RF) algorithm, a Long Short-Term Memory (LSTM) model, and a transformer-based architecture. The application is designed with a front-end interface allowing users to interact with the model by submitting reviews. Sentiment classification is performed using trained models, and review summarization is integrated using external large language model APIs. The implementation combines traditional machine learning with deep learning approaches to analyze and summarize user-generated text. The project also includes user authentication and session handling to support personalized usage. Evaluation metrics such as accuracy, precision, recall, and F1-score are used to assess model performance. The project aims to contribute to efficient sentiment understanding and compact representation of lengthy reviews.

Keywords: Sentiment Analysis, Random Forest, LSTM, Transformers, IMDB Dataset, NLP, Review Summarization, Flask, Classification, Machine Learning