In this project, I embarked on a sentiment analysis endeavor for movie reviews. The focal point of my efforts involved training a BERT (Bidirectional Encoder Representations from Transformers) model, a state-of-the-art natural language processing model. The overarching goal was to develop an application that facilitates the analysis of sentiment in movie reviews sourced from IMDb.

The application allows users to input a link to a specific movie on IMDb. Subsequently, it leverages web scraping techniques to extract and analyze the latest 25 reviews for that particular movie. The primary focus of the analysis is to determine whether each review exhibits a positive or negative sentiment.

The BERT model, known for its exceptional performance in understanding context and nuances in language, was trained on a dataset comprising diverse movie reviews to ensure robust sentiment analysis capabilities. This training process equipped the model with the ability to discern the sentiment expressed in the reviews, thereby enabling accurate predictions of whether a review is positive or negative.

The app's user-friendly interface streamlines the process for users, allowing them to effortlessly input IMDb links and receive sentiment predictions for the associated reviews. This project not only showcases the practical application of advanced natural language processing techniques but also offers a valuable tool for individuals seeking quick insights into the overall sentiment surrounding a particular movie based on IMDb reviews.