Sentiment analysis of specific product’s features using product tree for application in new product development

Abstract

New Product Development (NPD) is a multi-step process by which novel products are introduced in the market. Sentiment analysis, which ascertains the popularity of each new feature added to the product, is one of the key steps in this process. In this paper we present an approach by which product designers analyze users’ reviews from social media platforms to determine the popularity of a specific product’s feature in order to make a decision about adding it to the product’s next generation. Our proposed approach utilizes a product tree generated from a product specification document to facilitate forming an efficient link between features mentioned in the users’ reviews and those of the product designer’s interest. Furthermore, it captures the links/interactions between a feature of interest and its other related features in a product to ascertain its polarity.