Data-driven multi-criteria decision support method for electric vehicle selection

Abstract

Electric vehicles (EVs) are becoming one of the most popular forms of low-carbon transportations due to growing awareness of environmental protection and vigorous promotion of governments. Automakers have launched a variety of EVs in an attempt to capture the market, raising the question of how to improve the competitiveness of the EVs they have launched. Meanwhile, choosing among various EVs has become a problem for consumers. This paper proposes a sentiment analysis-based multi-criteria decision-making (MCDM) method. The group opinion for each alternative can be derived by transforming the sentiment analysis results of online auto reviews into hesitant intuitionistic fuzzy elements (HIFEs). A comprehensive weighting method that integrates the best-worst method and the maximizing deviation method is developed to identify the weights of criteria. Through extended ORESTE (Organísation, rangement et Synthése de données relarionnelles, in French) based on hesitant intuitionistic fuzzy Chebyshev distance, the ranking of candidate EV series can be obtained. The proposed method can help consumers make EV purchase choices, and the results of sentiment analysis can be useful for companies to explore consumers' demand for EVs.