A text date-driven multi-criteria decision making method with linguistic intuitionistic multiplicative information and its application in product recommendation

Under the deep integration of artificial intelligence and big data technologies, decision making paradigms are shifting toward data-driven intelligent frameworks. As textual data constitutes a critical component of big data, its effective mining and interpretation are essential for enhancing decision quality. Unlike existing text mining-based decision making methods that rely on pre-defined alternatives or subjective criteria specification, we propose a new method to solve the problems about the generation of decision alternatives, extraction of decision criteria, and prioritization and optimization of decision alternatives under text data environment. Firstly, an improved Jaccard similarity measure combined with case-based reasoning is used to construct a set of initial alternatives. After that, correlated topic model and text mining techniques are then applied to derive decision criteria and their objective weights, while a linguistic intuitionistic multiplicative (LIM) priority model determines subjective weights. Then, a novel LIM interactive weighted averaging operator is introduced to rank the alternatives, and its key properties are also proved. Finally, a case study on computer recommendation demonstrates the method’s feasibility, interpretability, and practical effectiveness. Compared with some existing methods, the proposed method exhibits significant advantages in computational efficiency, topic modeling performance and scalability, proving its suitability for complex decision making in real-world big data environments.