A comprehensive decision support model for online doctors ranking with interval‐valued neutrosophic numbers.

Web‐based appointment systems are emerging in the healthcare industry with mass data, but homogenized online information and poor evaluation criteria lead to blindness in selecting doctors. To select an appropriate doctor when making appointments online, a comprehensive decision support model is proposed. First, one class of multi‐criteria is built from reviews by text mining technologies. For quantitative analysis, interval‐valued neutrosophic numbers (IVNNs) are utilized to describe reviews, and related integration operators of IVNNs are employed. Second, another class of multi‐criteria is established by the website‐given labels. A disease similarity measure‐based transformation method is proposed to redefine the doctors' specialization, making the evaluation values more discriminable. Finally, a personalized doctor ranking result is derived by integrating the two classes of multi‐criteria values with a preference parameter. A case study of Wedoctor.com is conducted to validate the proposed model, and the comparison result indicates that the model can effectively support users' decision‐making. [ABSTRACT FROM AUTHOR]