E-commerce clothing review analysis by advanced ML Algorithms

Abstract

A significant aspect in the rapid ascent of Bangladesh's e-commerce sector in recent years has been the significance of consumer evaluations. By examining these reviews, readers can gain enhanced insight into consumer happiness and product quality. This research analyses the sentiment of online clothes reviews with advanced machine-learning techniques. The fundamental purpose of evaluating several machine learning models, such as KNN, RF, XGB, Multi, LSTM, and CNN, is to identify the most effective method for sentiment classification. Following the compilation of an extensive dataset of clothing assessments and the execution of data preparation tasks, including cleaning, tokenization, and stop word elimination, we utilised a combination of deep learning and machine learning models for classification purposes. KNN had the highest accuracy in forecasting the future attitudes of the models evaluated. The findings indicate in the 5000 datasets that KNN is the most effective algorithm for assessing the sentiment of online purchasing reviews. KNN reached at 0.91% Accuracy. This project's automated and scalable methodology may enable online businesses to evaluate client feedback and make more informed decisions. Future research initiatives encompass augmenting the dataset, experimenting with various methods, and incorporating these models into AI-driven mobile and online applications for real-time sentiment analysis.