Data-Driven Sizing Specification Utilizing Consumer Text Reviews

Abstract

The objective of this work is to introduce a new method for determining preliminary design specifications related to human-artifact interaction. This new method uses data mining of large numbers of consumer reviews. User opinion on specific product features can be time-consuming or expensive to obtain through traditional methods including surveys, experiments, and observational studies. Data mining review text of already released products may be a potentially less time consuming and costly method. Previously established methods of determining design for human variability information from consumer reviews, such as the frequency and accuracy summation (FAS) number and subsequent manual analysis, are explored. The weighted phrase rating (WPR), a new metric which can be an automated tool to quickly analyze consumer reviews, is also introduced. It does not require manual parsing of the reviews, which extends its applicability to larger review pools. This new method is shown to quickly and economically provide information useful to the establishment of design specifications.