An affordance-based online review analysis framework
Year: 2019
Editor: Wartzack, Sandro; Schleich, Benjamin; Gon
Author: Hou, Tianjun (1); Yannou, Bernard (1); Leroy, Yann (1); Poirson, Emilie (2)
Series: ICED
Institution: Laboratoire G?nie Industriel
Section: Knowledge-based engineering
DOI number: https://doi.org/10.1017/dsi.2019.252
ISSN: 2220-4342
Abstract
One of the main tasks of today's data-driven design is to learn customers' concerns from the feedback data posted on the internet, to drive smarter and more profitable decisions during product development. Feature-based opinion mining was first performed by the computer and design scientists to analyse online product reviews. In order to provide more sophisticated customer feedback analyses and to understand in a deeper way customer concerns about products, the authors propose an affordance-based online review analysis framework. This framework allows understanding how and in what condition customers use their products, how user preferences change over years and how customers use the product innovatively. An empirical case study using the proposed approach is conducted with the online reviews of Kindle e-readers downloaded from amazon.com. A set of innovation leads and redesign paths are provided for the design of next-generation e-reader. This study suggests that bridging data analytics with classical models and methods in design engineering can bring success for data-driven design.
Keywords: Big data, Design engineering, Innovation