Yujia Liu

Purpose: The analysis of user demand for new energy vehicles (NEVs) is crucial for corporate development. However, existing research often focuses on overall user demands, neglecting user heterogeneity. Therefore, this study aims to conduct user profiles and analyze user demands of NEV with a focus on heterogeneity. Design/methodology/approach: Firstly, this study brings the Big Five personality traits based on CNN-BiLSTM as one of the labels into user profiling, using data collected from “Autohome.com”. K-means clustering is employed to group users using sentiment and personality traits. Secondly, using Kano and importance-performance analysis, the focus and satisfaction of different user groups on various attributes are explored. Findings: The results reveal that user profiles can be categorized into three groups: shopping-oriented, career-oriented and family-oriented. Furthermore, the concerned attributes and priorities for improvement vary across user groups. Practical implications: The method enables companies to better identify heterogeneous user demands and optimize personalized product design and services. Additionally, it informs government policy-making to stimulate NEV market vitality. Originality/value: This paper applies the Big Five personality traits for user profiling to capture user heterogeneity and employs Kano-IPA analysis to prioritize NEV attribute improvements and provide optimization recommendations for different user groups.

Online reviews are an important influencing factor in consumer purchasing decisions, and consumers' diverse cultural backgrounds affect the expression of online reviews as well as decision-making process. This study proposes an integrated ranking method through online reviews. Specifically, the study constructs a fraudulent review detection model to detect fraudulent reviews. Then introduces the Hofstede's national cultural framework and cultural distance theory to propose a method for calculating the weighted sentiment values of reviews, and interval-valued Pythagorean fuzzy sets are used for representation. Finally, the ranking function is improved by introducing a weight factor to aggregate the ratings and reviews, and obtain the hotel ranking. To validate the proposed method, a case study is conducted using real hotel reviews. The results show that this method provides a suitable and differentiated ranking of alternatives for consumers in specific countries. This paper also offers insights for online review websites and hotel managers.

Supply chain finance (SCF) can provide innovative financing approaches for cash-constrained supply chain partners, which has been utilized for industries to optimize capital, reduce costs and alleviate financing pressure. Despite there are promising results in SCF, there are still many challenges in the development of SCF practice, such as the information asymmetry problem and credit data transmission barriers. Blockchain has been widely adopted in the finance industry, it can provide solutions to these challenges. However, the capabilities and performance of different blockchain platforms (BPs) vary greatly, thus, it is necessary to select an appropriate BP according to the specific circumstances of SCF. The main purpose of this article is to develop a decision-making framework to select a suitable BP for the blockchain implementation of SCF. Since SCF business involves multiple entities such as core enterprises, suppliers, and financial institutions, each entity has different requirements for BP, so conflicts of opinion are prone to occur in the decision making process. To this end, we develop a bilateral negotiation group multiattribute decision making (BN-GMADM) method with personalized individual semantics (PIS) to coordinate opinions and promote consensus. In addition, the distributed linguistic scoring rule (DLSR) is proposed for BP alternatives scoring and ranking. A case study and several analyses are provided to illustrate and validate the proposed approach.

The multi-attribute decision-making method based on online reviews has been widely used in addressing the hotel selection problem. However, due to information overload and the presence of fake reviews, traditional hotel selection methods that rely solely on unverified review analysis can affect the outcome of hotel selections. In this study, a novel three-dimensional helpful review analysis model based multi-attribute decision-making approach for hotel selection is established. Firstly, a new three-dimensional helpful review analysis model that effectively filters out sentiment inconsistency reviews, topic inconsistency reviews, and reviews from invalid sources is proposed. Secondly, this study employs TF-IDF and LDA to extract attributes for hotel selection. We further utilize BERT to extract sentiment level for each attribute. Then, a ranking result for alternative hotels is obtained using a combination compromise solution method (CoCoSo). Finally, we demonstrate its effectiveness and feasibility through a case study of selecting the optimal hotel from TripAdvisor.com.