Text mining on product reviews to automatic retrieve product strengths and defects

The aim of this thesis is to apply the text mining and clustering algorithms on the product reviews to automatic extract the strengths and defects of the product on the basis of customer experiences. Analyzing the reviews on a product helps to improve the quality of the product or service. That way, reviews from online shopping sites (such as Amazon) not only help a consumer to buy a product but also can help a manufacturer or seller to know the pros and cons of their product. Amazon star ratings alone are not enough for this. One should go through the text reviews to know specifically which feature of the product is lacking customer satisfaction. But a product may have thousands of reviews and it’s hard for a person to go through all the reviews. Hence, we need a system which can give output that defined the product strength and defects. This project enables the user to view feature based review for a selected category of Amazon products. The data-set which includes product details and customer reviews for product is collected from Amazon.com. The implementation of this system is achieved by using Anaconda Jupyter notebook and Google colab. The Amazon reviews undergo Natural Language Processing and text mining in order to text pre-processing and TF-IDF vectorizer. Then a clustering analysis is made to identify the strengths and defects of the product.