Translating online customer opinions into engineering characteristics in QFD: A probabilistic language analysis approach

Online opinions provide informative customer requirements for product designers. However, the increasing volume of opinions make them hard to be digested entirely. It is expected to translate online opinions for designers automatically when they are launching a new product. In this research, an exploratory study is conducted, in which customer requirements in online reviews are manually translated into engineering characteristics (ECs) for Quality function deployment (QFD). From the exploratory study, a simple mapping from keywords to ECs is observed not able to be built. It is also found that it will be a time-consuming task to translate a large number of reviews. Accordingly, a probabilistic language analysis approach is proposed, which translates reviews into ECs automatically. In particular, the statistic concurrence information between keywords and nearby words is analyzed. Based on the unigram model and the bigram model, an integrated impact learning algorithm is advised to estimate the impacts of keywords and nearby words respectively. The estimated impacts are utilized to infer which ECs are implied in a given context. Using four brands of printer reviews from Amazon.com, comparative experiments are conducted. Finally, an illustrative example is shown to clarify how this approach can be applied by designers in QFD.