A projection-based regret theory method for evaluating service quality of public transportation systems under interval type-2 fuzzy environment during COVID-19 pandemic

Public transportation plays a vital role in urban mobility, particularly in large and densely populated cities. As a result, evaluating service quality of public transportation systems has become a strategic decision-making concern for both private and public sections. In particular, facing with the expeditiously spreading of coronavirus disease 2019 (COVID-19), it led to an unprecedented decline in public transit demand and revenue, while also exacerbating traffic congestion during peak hours. This study aims to improve the passengers' satisfaction problem of public transportation during the COVID-19 pandemic, and to assess their satisfaction degrees by conducting passengers’ satisfaction surveys. A novel projection-based regret theory approach based on interval type-2 fuzzy sets (IT2FSs) is introduced to solve multi-criteria decision-making problems related to service evaluation. First, a projection model of IT2FSs is formulated, incorporating both distance and angle information. Second, by integrating this projection model with regret theory, new utility and regret-rejoice functions are constructed to enhance decision-making effectiveness. Comparative analyses with existing methods demonstrate the superiority of the proposed approach in capturing the psychological factors of decision makers. The model yields more reliable and realistic outcomes, offering valuable insights into future enhancements in public transportation service quality. Furthermore, sensitivity analysis verifies the robustness of the method, as the ranking results remain stable when varying parameter settings. As a conclusion, the service quality of public transportation systems from the best to the worst in sequence are as follows: taxi, e-hailing, bus, van and metro, and this can assist policymakers and transit agencies in making more informed and efficient resource allocation decisions during and after the pandemic.