Clustering and compatibility-based approach for large-scale group decision making with hesitant fuzzy linguistic preference relations: An application in e-waste recycling

Considering that large-scale group decision making (LSGDM) has been widely concentrated on clustering and lower compatibility problems, this paper focuses on clustering and consensus reaching of hesitant fuzzy linguistic preference relations (HFLPRs) in LSGDM. Firstly, we define the hesitant degree and the fuzzy degree functions for hesitant fuzzy linguistic term sets (HFLTSs) according to their scale and deviation of elements. To normalize HFLTSs with different length, a minimum deviation model based on the hesitant and the fuzzy degrees is developed. After that, we propose a new similarity measure and compatibility measure via integrating the hesitant and fuzzy degrees. Then a clustering process combining similarity and compatibility is used to assign large-scale experts into several clusters. The clustering method not only strengths the cohesion of subgroups, but also guarantees that HFLPRs in subgroups are acceptable compatibility. Moreover, a compatibility adjusting process with self-selected feedback mechanism is presented to improve the compatibility level of clusters until they reach a predefined threshold in selection process. And we combine the number of members in subgroups and the compatibility level of subgroups to determine weights of subgroups. Finally, a case of e-waste recycling and comparison are analyzed to show the availability of the proposed method.