Designing an Intelligent Decision Support System for Evaluating Teaching Effectiveness in Technology-Enhanced Classrooms

Le résumé fourni par la source

The rapid digital transformation of education has significantly increased the adoption of technology-enhanced classrooms, generating substantial educational data that can support intelligent instructional evaluation. However, conventional teacher assessment systems remain limited by subjectivity, inconsistent evaluation standards, and the inability to analyze multidimensional learning analytics data effectively. This study aims to design an Intelligent Decision Support System (IDSS) for evaluating teaching effectiveness in smart classroom environments using the ELECTRE (Elimination and Choice Translating Reality) method integrated with Artificial Intelligence (AI)-based educational analytics. The proposed framework combines learning analytics indicators, machine learning models, and outranking-based multi-criteria decision-making to support transparent and data-driven educational governance. The evaluation criteria include student engagement, attendance rate, assignment completion, student satisfaction, learning outcomes, classroom interaction, technology integration, and instructor responsiveness. The computational process involved decision matrix construction, normalization, weighted normalization, concordance-discordance analysis, and aggregate dominance evaluation. The results demonstrated that the ELECTRE method effectively identified dominant teaching alternatives and handled conflicting instructional criteria systematically. Teacher 3 achieved the highest performance ranking due to superior instructional performance across all evaluation indicators. Additionally, AI-based predictive analysis improved evaluation accuracy and instructional pattern identification within technology-enhanced classrooms. The study contributes theoretically by extending the application of ELECTRE within intelligent educational DSS frameworks and practically by providing educational institutions with a scalable and transparent mechanism for evaluating teaching effectiveness. The proposed system supports smart educational governance, data-driven decision-making, and sustainable classroom quality assurance in digital learning ecosystems.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.