Iterative Random Weight EC-TOPSIS Method for Ranking Companies on Social Media

Abstract: This study aims to present a new hybrid method for weighting criteria. The methodological project combines the ENTROPY and CRITIC methods with the TOPSIS method to create EC-TOPSIS. The difference lies in the use of a weight range per criterion. Each weight range has a lower limit and an upper limit, which are combined to generate random numbers, producing t sets of weights per criterion, allowing t final rankings to be obtained. The final ranking is obtained by applying the MODE statistical measure to the set of t positions of each alternative. The method was validated by ranking the companies based on social media metrics consisting of user-generated content (UGC). The result was compared with the original modeling using the CRITIC-ARAS and CRITIC-COPRAS methods, and the results were consistent and balanced, with few changes. The practical implication of the method is in reducing the uncertainties surrounding the final classification due to the random weighting process and the number of interactions sent.