Customer Reviews for Product Recommendation using Machine Learning
Published: 2022
Author(s) Name: Abhishek J. M., Shishira S. Jois, Ashish K. Pastay, Chiranthan P. and Samara Mubeen |
Author(s) Affiliation: JNNCE, Shivamogga, Karnataka, India.
Locked
Subscribed
Available for All
Abstract
Online Shopping is an upcoming trend than the traditional way of doing shopping. The branded products are obtained at a reasonable cost at the doorstep. Henceforth the focus of this paper is to classify customer reviews as either recommendable or non-recommendable using Natural Language Processing (NLP) techniques. This provides an excellent option for customers to filter out “good” and “bad” reviews, the problem with this system is that there can be a lack of authenticity in terms of providing ratings and ordering reviews. There are two end goals of this research work: to automatically classify reviews using the reviews/ratings and to showcase the classified reviews using WordCloud. The main aim of the analysis is to identify the polarity of the data on the Web
and classify them. As Sentiment analysis or opinion, mining is one of the major tasks of NLP; Sentiment analysis has gained much attention in recent years. This project aims to tackle the problem of sentiment polarity categorization, which is one of the fundamental problems of sentiment analysis. Data used in this study are online product reviews collected from E-commerce websites namely Amazon or Flipkart. Experiments for review-level categorization are performed with promising outcomes.
Keywords: E-commerce, Natural language processing, Recommendation system, Sentimental analysis.
View PDF