Abstract:
|
Web 2.0 allows to gather a huge amount of free and timely online reviews that customers write on a variety of products/services. Review web platforms usually ask customers to leave a textual review along with general and specific rates regarding the product/service and its key aspects. Rates are normally collected through Likert-type scales questions and analysed by means of Supervised Machine Learning-based Sentiment Analysis. This approach makes it possible to predict the general rate through the rates collected on product/service aspects, if available, and textual reviews. However, despite being a user-friendly, easy-to-develop and to-administer tool, Likert-type scales are unprecise and generate ordinal variables that cannot be analysed by statistical methods defined on a metric space: the distance between two consecutive items cannot be defined nor presumed equal. In such context, fuzzy theory can be used to recode customers’ rate into fuzzy numbers before the adoption of a suitable ML algorithm for fuzzy data. This procedure allows to obtain more precise prediction of the general CS. Our approach is presented and discussed on some case study, highlighting its main advantages.
|