Abstract:
This paper comprehensively examines intelligent tutoring systems as transformative educational technology that leverages artificial intelligence in creating autonomous adaptive digital learning environments for STEM education. The research articulates a sophisticated four-component framework design for delivering personalized instruction aligned with pedagogical principles. We analyzed advanced probabilistic approaches that enable the dynamic adaptation of learning pathways, content sequencing, and difficulty calibration based on continuous assessment of student knowledge states. Our investigation was extended to personalized feedback mechanisms that monitor problem-solving processes, identify misconceptions, and provide contextual guidance through natural language processing and affective computing techniques. The empirical evidence from diverse STEM disciplines demonstrated that welldesigned intelligent tutoring systems significantly outperform traditional instructional methods regarding learning outcomes, knowledge retention, and student engagement. Through a detailed case analysis of exemplary systems, we identified critical design characteristics that contribute to educational effectiveness. The presented findings have significant implications for educational policy, curriculum design, and the development of next-generation intelligent tutoring systems that can effectively address the complex, interdisciplinary nature of contemporary STEM education.
CITATION:
IEEE format
V. Aleksić, D. Politis, “The Design Characteristics of Intelligent Tutoring Systems for Stem Education,” in Sinteza 2025 - International Scientific Conference on Information Technology, Computer Science, and Data Science, Belgrade, Singidunum University, Serbia, 2025, pp. 281-288. doi:10.15308/Sinteza-2025-281-288
APA format
Aleksić, V., Politis, D. (2025). The Design Characteristics of Intelligent Tutoring Systems for Stem Education. Paper presented at Sinteza 2025 - International Scientific Conference on Information Technology, Computer Science, and Data Science. doi:10.15308/Sinteza-2025-281-288