Applying multi-criteria decision-making to text analysis for optimizing engineering knowledge management

Efficient management of engineering knowledge is vital in Industry 4.0 for fostering innovation and improving organizational performance. This study introduces a comprehensive decision-making framework to evaluate and select optimal text analysis tools for engineering knowledge management (EKM). The framework integrates the logarithmic percentage change-driven objective weighting (LOPCOW) method to objectively assign weights to eight critical evaluation criteria: accuracy, scalability, speed, ease of integration, cost, user experience, flexibility, and support/maintenance. To rank alternatives, the evaluation based on relative utility and nonlinear standardization (ERUNS) technique is employed, ensuring a balanced assessment of performance metrics. Recognizing the uncertainty and vagueness in expert judgments, the model incorporates picture fuzzy sets (PiFSs), enabling nuanced representation of positive, neutral, and negative opinions. Five text analysis tools are evaluated, demonstrating the framework’s capacity to handle complex decision-making scenarios under uncertainty. The results identified Semantic Search and Knowledge Graph as the best-suited tool for optimizing knowledge extraction, aligning with organizational needs while addressing scalability and flexibility. This integrated approach not only enhances decision-making transparency but also provides actionable insights for engineering organizations aiming to improve EKM practices. The proposed framework contributes to advancing multi-criteria decision-making (MCDM) methodologies and offers a robust solution for technology selection in uncertain environments.