Wisdom of crowds: Conducting importance-performance analysis (IPA) through online reviews

Abstract This paper proposes a methodology for conducting importance-performance analysis (IPA) through online reviews. The methodology is composed of three stages: (1) mining useful information from online reviews, (2) estimating each attribute's performance and importance, and (3) constructing IPA plot, where the latent dirichlet allocation (LDA), the improved one-vs-one strategy based support vector machine (IOVO-SVM) and the ensemble neural network based model (ENNM) are respectively used. A case study on two five-star hotels is given, and the results obtained by the proposed methodology through online reviews are compared with those obtained by the existing methods through questionnaires (or online ratings). The results indicate that the proposed methodology can obtain effective analysis results with lower cost and shorter time since online reviews are publicly available and easily collected. The proposed methodology can give managers or market analysts one more choice for conducting IPA or serve as a preparing process of large-scale survey.