Direct-Indirect Association Rule Mining for Online Shopping Customer Data using Natural Language Processing

Abstract

In recent days, all kinds of service based companies and business organization needs customer feedback. Nowadays, many customers share their opinion by online about the products or services which become a process of decision making from customer and also help in making the business model more robust. These customer reviews may assist to expand their business and gain trust of the customer. In order to analyze customer feedback about their products and customer intents, most businesses perform “Market Basket Analysis”. There are several existing techniques which have ignored the very essence of capturing and analyzing customer reviews for each product that has been purchased and it may switches over to other product which belongs to the same category. The existing techniques do not take into account regarding the switch over of product. Apriori algorithm alone may not predict accurately regarding which other products the person would buy along with a specified product simply based on the basket data. Sentimental analysis refers to the use of natural language processing (NLP), text analysis and computational linguistics to systematically identify, extract, quantify and study affective states and subjective information. The proposed research work considers product review analysis with Apriori algorithm based rule mining to determine the implicit association using sentiment analysis.