SENTIMENT RATING ALGORITHM OF PRODUCT ONLINE REVIEWS
Editor: Marjanovic Dorian, Storga Mario, Pavkovic Neven, Bojcetic Nenad
Author: Raghupathi ,D.; Yannou ,B.; Farel ,R.; Poirson, E.
Section: INDUSTRIAL DESIGN
Social media give new opportunities in customer and market survey to improve design; comments posted online by users spontaneously, in a near-oral language is almost free of biases. This new source however has huge size, so complexity of data needs to be processed. In this paper, we propose an automated method to process these comments into a sentiment rating useful for future designs. We validate it on the example of a commercial home theatre system, comparing our automated sentiment predictions with human ratings on a group of 15 test subjects, resulting in a satisfactory correlation.