From social media to innovation and marketing intelligence: A simulation to forecast online review and rating performance

Abstract

Brands need to leverage the enormous volumes of feedback that consumers leave on social media. Existing methods for understanding free-text based consumer feedback data (eg online reviews) are predominantly qualitative (eg sentiment analysis). Qualitative approaches, however, cannot provide quantitative predictions of a potential rating increase following a product improvement. This paper will describe a novel method that converts reviews and ratings into statistical data that can be used to forecast rating performance. This is achieved by assigning quantitative values of importance to the various features of a given product based on each feature’s percentage contribution to the product rating. With such information, marketing and innovation teams can optimise their investment decisions to address consumer needs accurately and therefore maximise return on investment.