A Sentiment Analysis of Amazon Review Data Using Machine Learning Model

Nowadays everything is digitalized in the world. In the digitalization world E-commerce take a unique place for people. People are not going anywhere and buy all the thing at home using this E-commerce platform. For selecting the platform generally used the reviews of the people which are already buy from there. The paper proposes a sentiment analysis of the large amazon real dataset based on the counter vectorizer (CV) and term frequency inverse document frequency (TF-IDF) and logistic regressor. Firstly, take the dataset from the amazon E-commerce into JSON format and load the dataset and split the dataset into train test model. Secondly, take out the features using the counter vectorizer and term frequency inverse document frequency (TF-IDF). Finally, logistic regressor (LR) is used and measure the positive and negative sentiment of the review. simulation result represents the model accuracy score, precision, recall, confusion matrix of the implemented approach.