Mitigating Conceptual Learning Gaps in Mixed-Ability Classrooms: A Learning Analytics-Based Evaluation of AI-Driven Adaptive Feedback for Struggling Learners DOI Creative Commons
Fawad Naseer, Sarwar Khawaja

Applied Sciences, Год журнала: 2025, Номер 15(8), С. 4473 - 4473

Опубликована: Апрель 18, 2025

Adaptation through Artificial Intelligence (AI) creates individual-centered feedback strategies to reduce academic achievement disparities among students. The study evaluates the effectiveness of AI-driven adaptive in mitigating these gaps by providing personalized learning support struggling learners. A analytics-based evaluation was conducted on 700 undergraduate students enrolled STEM-related courses across three different departments at Beaconhouse International College (BIC). employed a quasi-experimental design, where 350 received while control group followed traditional instructor-led methods. Data were collected over 20 weeks, utilizing pre- and post-assessments, real-time engagement tracking, survey responses. Results indicate that receiving demonstrated 28% improvement conceptual mastery, compared 14% group. Additionally, student increased 35%, with 22% reduction cognitive overload. Analysis interaction logs revealed frequent AI-generated led 40% increase retention rates. Despite benefits, variations impact observed based prior knowledge levels consistency. findings highlight potential smart environments enhance educational equity. Future research should explore long-term effects, scalability, ethical considerations AI-based systems.

Язык: Английский

Determinants of Adopting 3D Technology Integrated With Artificial Intelligence in STEM Higher Education: A UTAUT2 Model Approach DOI

Vi Loi Truong,

Lisa Pham

Computer Applications in Engineering Education, Год журнала: 2025, Номер 33(3)

Опубликована: Апрель 6, 2025

ABSTRACT Incorporating 3D technology and artificial intelligence, often known as AI, into STEM education in the current day is creating new opportunities to improve student engagement performance. With an emphasis on areas specifically, this study attempts bring elements that affect uptake of AI‐enabled instructional technology. A survey was carried out with 300 participants, including teachers students from universities. To gauge participant impressions, used UTAUT2—the Unified Theory Acceptance Use Technology 2 framework. IMB SPSS 25 AMOS 24 has been calculate, evaluate, analyze data determine main variables influencing adoption these technologies. The results show while AI technologies have a great deal potential enhance users' interaction, understanding, difficult scientific concepts, there are still obstacles overcome, those related infrastructure, cost, requirement for faculty training. Furthermore, it discovered moderating factors experience, gender, age, level had very little effect final outcomes. This provides insightful information how successfully incorporate curricula at university level.

Язык: Английский

Процитировано

0

Mitigating Conceptual Learning Gaps in Mixed-Ability Classrooms: A Learning Analytics-Based Evaluation of AI-Driven Adaptive Feedback for Struggling Learners DOI Creative Commons
Fawad Naseer, Sarwar Khawaja

Applied Sciences, Год журнала: 2025, Номер 15(8), С. 4473 - 4473

Опубликована: Апрель 18, 2025

Adaptation through Artificial Intelligence (AI) creates individual-centered feedback strategies to reduce academic achievement disparities among students. The study evaluates the effectiveness of AI-driven adaptive in mitigating these gaps by providing personalized learning support struggling learners. A analytics-based evaluation was conducted on 700 undergraduate students enrolled STEM-related courses across three different departments at Beaconhouse International College (BIC). employed a quasi-experimental design, where 350 received while control group followed traditional instructor-led methods. Data were collected over 20 weeks, utilizing pre- and post-assessments, real-time engagement tracking, survey responses. Results indicate that receiving demonstrated 28% improvement conceptual mastery, compared 14% group. Additionally, student increased 35%, with 22% reduction cognitive overload. Analysis interaction logs revealed frequent AI-generated led 40% increase retention rates. Despite benefits, variations impact observed based prior knowledge levels consistency. findings highlight potential smart environments enhance educational equity. Future research should explore long-term effects, scalability, ethical considerations AI-based systems.

Язык: Английский

Процитировано

0