PUB - Publikationen an der Universität Bielefeld

In the recent past, the quantitative analysis of online product reviews (OPRs) has become a popular manifestation of marketing intelligence activities focusing on products that are frequently subject to electronic word-of-mouth (eWOM). Typical elements of OPRs are overall star ratings, product attribute scores, recommendations, pros and cons, and free texts. The first three elements are of particular interest because they provide an aggregate view of reviewers’ opinions about the products of interest. However, the significance of individual product attributes in the overall evaluation process can vary in the course of time. Accordingly, ad hoc analyses of OPRs that have been downloaded at a certain point in time are of limited value for dynamic eWOM monitoring because of their snapshot character. On the other hand, opinion platforms can increase the meaningfulness of the OPRs posted there and, therewith, the usefulness of the platform as a whole, by directing eWOM activities to those product attributes that really matter at present. This paper therefore introduces a neural network-based approach that allows the dynamic tracking of the influence the posted scores of product attributes have on the overall star ratings of the concerning products. By using an elasticity measure, this approach supports the identification of those attributes that tend to lose or gain significance in the product evaluation process over time. The usability of this approach is demonstrated using real OPR data on digital cameras and hotels.