Smartphone Selection Using Structured User Reviews: A Hybrid Random Forest and Fuzzy DIBR II–WASPAS Approach

One of the complex decision-making problems, which requires consideration of several criteria, is the choice of a smartphone. This paper presents an approach that combines user review analysis with machine learning and multi-criteria decision making (MCDM) methods to identify and evaluate alternatives. Based on the processed reviews, the Random Forest algorithm was used to identify the criteria that most influence the selection of smartphones. The weights of the criteria were determined using the Defining Interrelationships Between Ranked criteria II (DIBR II) method, improved by the application of triangular fuzzy numbers for better processing of the subjective and imprecise nature of the data. For the final selection of the optimal alternative, the Weighted Aggregated Sum Product Assessment (WASPAS) method was applied in a fuzzy environment, which enables the combination of additive and multiplicative approaches in ranking. The methodological justification of the proposed approach was confirmed by a sensitivity analysis, through 15 scenarios of changes in the weight coefficients of the criteria, which showed that small oscillations in the weights do not significantly affect the final ranking, especially not in the first two positions. The validation was additionally supported by a comparative analysis with four other decision-making methods in a fuzzy environment, which confirmed the stability and consistency of the results. The proposed approach provides an empirically grounded and methodologically robust framework for solving decision-making problems under conditions of multi-criteria evaluation and uncertainty, and can be applied to a wide range of similar problems in different fields.