Movie-Review-Clustering

sentiment Analysis with word2vec This project involves clustering a dataset of 50,000 movie reviews into two categories: negative and positive. The clustering is performed using the K-means algorithm, and Word2Vec is incorporated for feature representation. The dataset consists of 50,000 movie reviews, and each review serves as a data point for clustering. The reviews may vary in length and content, reflecting diverse opinions on movies. The dataset can be find at IMDB datset. Prior to clustering, the dataset undergoes preprocessing steps to clean and prepare the text data. This includes tasks such as removing stop words, handling punctuation, and lemmatization.