Evaluating new energy vehicles by picture fuzzy sets based on sentiment analysis from online reviews

New energy vehicles (NEVs) have beneficial effects on the energy conservation and environmental protection in the transportation sector. The governments have issued many policies to promote their development and adoption. But, how to evaluate the NEVs is still a noteworthy topic. In this paper, we focus on the evaluation of NEVs through online reviews. First, the online reviews are obtained from the websites by data crawling technology. After obtaining the data, a data-driven based method is developed to extract the attributes about the NEVs and sentiment analysis is conducted to discriminate the sentiment orientation of each review to each alternative under each attribute. Then, we define a new information transformation mechanism to realize the transformation from unstructured data to picture fuzzy numbers. Next, a weight determination method based on the proposed picture fuzzy entropy measure is defined to determine the weight of attributes. Finally, considering the bounded rationality of consumers in purchasing, a picture fuzzy set-based regret theory is proposed to quantify their psychological behavior. A case study about the evaluation of NEVs are presented to show the implementation process of this research. Discussions consisting of comparative analysis and parameter analysis are also conducted to explore the superiority and robustness of the proposed evaluation method.