Sentiment Analysis for Scraping of Product Reviews from Multiple Web Pages Using Machine Learning Algorithms

Abstract

Sentiment analysis is the computational task of automatically determining what feelings a writer is expressed in text. Sentiment analysis is gaining much attention in recent years. It is often framed as a binary distinction, i.e. positive vs. negative, but it can also be a more fine-grained, like identifying the specific emotion an author is expressing like fear, joy or anger. Globally, business enterprises can leverage opinion polarity and sentiment, topic recognition to gain deeper understanding of the drivers and the overall scope. Subsequently, these insights can advance competitive intelligence and improve customer service, thereby creating a better brand image and providing a competitive edge. To extract the content from e-commerce website using web scraping technique. It will be looping through then number of pages or so of comments for each of the products. In this work, online product reviews are collected using web scraping technique. The collected online product reviews are analyzed using opinion or sentiment analysis using classification models such as KNN, SVM, Random Forest, CNN (Convolutional Neural Network) and proposed hybrid SVM-CNN. Experiments for the classification models are performed with promising outcomes.