Improved decisions for marketing, supply and purchasing: Mining big data through an integration of sentiment analysis and intuitionistic fuzzy multi criteria assessment

Abstract This study proposes a novel decision support system for product ranking problems which integrates multi criteria decision making (MCDM) and aspect level sentiment analysis techniques. The main purpose of the developed methodology is to rank the alternative products taking into account a set of product criteria and the customer comments related to these criteria posted on websites to recommend the most appropriate alternative to potential customers. The decision support system comprises two stages, in the first stage, the online customer reviews are transformed into customer satisfaction scores through aspect level sentiment analysis to obtain performance scores corresponding to alternative products, whereas the second stage deals with ranking the alternative products via a novel MCDM methodology, namely “IF-ELECTRE integrated with VIKOR” according to the performance scores obtained in the first level. Intuitionistic fuzzy sets (IFSs) are utilized to effectively represent the customer reviews including hesitant expressions in decision matrix. The weights of criteria (the product aspects of significant importance for customers) are determined using entropy method. The applicability of the developed approach is explored by a case study, in which customer reviews about hotel experiences are evaluated using lexicon based sentiment analysis and alternative hotels are ranked according to the findings from the sentiment analysis by the Intuitionistic fuzzy (IF)-ELECTRE integrated with VIKOR methodology.