Optimizing teacher evaluation with fuzzy metaheuristic algorithm

Abstract Teacher evaluation is essential for fostering effective education and supporting well-rounded student development. Traditional evaluation methods often emphasize classroom performance and test results, which may overlook key skills that contribute to a teacher’s overall effectiveness, such as creativity, communication, and the ability to promote student well-being. To address these limitations, this study proposes a comprehensive teacher evaluation framework based on metaheuristic optimization that extends beyond conventional metrics by incorporating factors such as professional integrity, student interaction, and adaptability, thereby better reflecting a teacher’s impact on both academic achievement and life skill development. To validate the proposed framework, experiments were conducted using three metaheuristic algorithms: Teaching–Learning-Based Optimization (TLBO), Genetic algorithm (GA), and Particle Swarm Optimization (PSO). Across multiple experimental settings, TLBO consistently outperformed GA and PSO, achieving the highest mean fitness values (e.g., 0.683 in Experiment 1A, 1.658 in Experiment 2C, and 2.417 in Experiment 3C) and demonstrating superior stability with the lowest standard deviations (e.g., 0.017 in Experiment 1A and 0.013 in Experiment 3C). Final algorithm rankings, computed using the harmonic mean of outcomes, confirmed TLBO as the best-performing approach (rank 1.2), followed by GA (1.5) and PSO (3.0). Statistical validation using the Friedman test revealed significant differences among the algorithms (all p-values < 0.05), and post-hoc Nemenyi tests further confirmed the robustness of the pairwise comparisons. Overall, the results demonstrate the effectiveness of metaheuristic optimization for reliable and stable teacher evaluation. Future research may extend this framework through machine learning-based adaptive weighting, real-world institutional validation, and cross-domain applications such as employee assessment and healthcare evaluation.