Effective learning with a personal AI tutor: A case study
Published in:
- Education and Information Technologies. - 2024, p. 1-17
English
Effective learning strategies based on principles like personalization, retrieval practice,and spaced repetition are often challenging to implement due to practical constraints.Here we explore the integration of AI tutors to complement learning programs inaccordance with learning sciences. A semester-long study was conducted at Uni-Distance Suisse, where an AI tutor app was provided to psychology students takinga neuroscience course (N=51). After automatically generating microlearning ques-tions from existing course materials using GPT-3, the AI tutor developed a dynamicneural-network model of each student’s grasp of key concepts. This enabled the imple-mentation of distributed retrieval practice, personalized to each student’s individuallevel and abilities. The results indicate that students who actively engaged with theAI tutor achieved significantly higher grades. Moreover, active engagement led toan average improvement of up to 15 percentile points compared to a parallel coursewithout AI tutor. Additionally, the grasp strongly correlated with the exam grade, thusvalidating the relevance of neural-network predictions. This research demonstratesthe ability of personal AI tutors to model human learning processes and effectivelyenhance academic performance. By integrating AI tutors into their programs, educa-tors can offer students personalized learning experiences grounded in the principlesof learning sciences, thereby addressing the challenges associated with implement-ing effective learning strategies. These findings contribute to the growing body ofknowledge on the transformative potential of AI in education.
-
Language
-
-
Classification
-
Education, teaching
-
License
-
CC BY
-
Identifiers
-
-
Persistent URL
-
https://n2t.net/ark:/51647/srd1331655
Statistics
Document views: 127
File downloads:
- Effective_learning_with_a_personal_AI_tutor_A_case.pdf: 378
