Deep Learning and Reinforcement Learning for Assessing and Enhancing Academic Performance in University Students: A Scoping Review

AI, Год журнала: 2025, Номер 6(2), С. 40 - 40

Опубликована: Фев. 19, 2025

University students often face challenges in managing academic demands and difficulties like time management, task prioritization, effective study strategies. This scoping review investigates the application of Deep Learning (DL) Reinforcement (RL) evaluating enhancing performance, focusing on their practical applications, limitations, future potential. Using PRISMA guidelines, 27 empirical studies published between 2014 2024 were analyzed. These utilized advanced DL RL technologies, including neural networks adaptive algorithms, to support personalized learning performance prediction across diverse university contexts. Key findings highlight DL’s ability accurately predict outcomes identify at-risk students, with models achieving high accuracy areas dropout language proficiency assessments. proved optimizing pathways tailoring interventions, dynamically adapting individual student needs. The emphasizes significant improvements grades, engagement, efficiency enabled by AI-driven systems. However, persist, scalability, resource demands, need for transparent interpretable models. Future research could focus datasets, multimodal inputs, long-term evaluations enhance applicability these technologies. By integrating RL, higher education can foster personalized, environments, improving inclusivity.

Язык: Английский

Analysis and Reflection on the Teaching Application of Artificial Intelligence Technology in the Context of Big Data

Curriculum and Teaching Methodology, Год журнала: 2024, Номер 7(4)

Опубликована: Янв. 1, 2024

With the rapid development of big data and artificial intelligence (AI) technologies, education community is actively exploring new paths to incorporate them into teaching learning. This paper firstly dissects potential benefits these technologies in learning, then briefly introduces their applications, such as personalized teaching, decision support, student assessment, resource optimization innovative teaching. A comprehensive analysis specific processes implementation measures based on AI provided. Subsequently, challenges encountered AI-based privacy, teacher role evolution, allocation modelling accuracy, are explored, corresponding solution strategies recommendations proposed. Ultimately, study will serve a practical guide for educators policy makers promote educational innovation progress field AI-enhanced

Язык: Английский