Use of feedback in intelligent tutoring systems: a systematic literature review
Laíza Ribeiro Silva, Camila Alves Fior, Luiz Rodrigues, Renato Penha, Diego Dermeval, Seiji Isotani · Interactive Learning Environments · 2025
Feedback is a powerful tool with the potential to positively influence the development of cognitive and motor skills, thereby enhancing learning outcomes. However, in educational settings, providing real-time feedback tailored to the needs of each student can be challenging, particularly when considering large class sizes and the specific requirements of individualized feedback. In this context, artificial intelligence has emerged as a promising solution, using intelligent tutoring systems (ITS), which are computer programs that provide personalized instruction and immediate feedback to support student learning. These systems are designed for educational purposes and have demonstrated positive outcomes in addressing the challenge of incorporating feedback into classroom learning. Nevertheless, there is a lack of recent studies offering a comprehensive perspective on feedback, including the viewpoints of students and teachers and the overall impact on the teaching and learning process. We conducted an updated Systematic Literature Review (SLR) to address this gap to consolidate this information. A total of 27 studies were selected and analyzed, providing insights into educational levels, contexts, types of feedback, and the outcomes of utilizing feedback within ITS. This review aims to update the state of the art and identify existing research gaps. The primary gaps identified include: (i) the limited involvement of teachers in the development process of ITS, particularly in the design, validation, and verification of feedback quality; and (ii) the insufficient consideration of affective and motivational factors, both in the design of feedback and its subsequent impact on the learning process.