AI-enabled adaptive learning and its impact on learner engagement and academic performance
DOI:
https://doi.org/10.64171/JAES.5.4.80-85Keywords:
Artificial Intelligence (AI), Higher Education, Learning Systems, College/University StudentsAbstract
The incorporation of Artificial Intelligence (AI) into digital learning environments has revolutionized the framework and dissemination of higher education. Adaptive learning systems that use AI are made to make educational content more personal, change the way lessons are taught based on how well students do, and make school more interesting. In populous and demographically varied states like Uttar Pradesh, where higher education institutions cater to substantial student bodies, the deployment of adaptive digital platforms presents considerable opportunities for enhancing educational outcomes. This study examines the influence of AI-driven adaptive learning systems on student engagement, academic achievement, and satisfaction among 175 higher education students from universities and colleges in Uttar Pradesh. The study used a mixed-methods approach, which combined structured analytical procedures with quantitative survey methods. The data were gathered through a standardized questionnaire organized around four main constructs: the efficacy of AI-enabled adaptive learning, learner engagement, academic performance, and satisfaction with the e-learning environment. We used a five-point Likert scale to measure the answers. The reliability analysis showed that all of the constructs were very consistent with each other. Confirmatory factor analysis validated the measurement model, and regression analysis indicated a statistically significant positive correlation between AI-enabled adaptive learning and learner engagement. Also, learner engagement had a strong predictive effect on academic performance, which means it had a mediating effect. Analysis of variance revealed disparities in satisfaction levels contingent upon institutional type and prior experience with e-learning platforms. The findings indicate that AI-based adaptive learning systems make the learning process more individual, active, and the students can improve their performance in school. This is because students who had prior experience with digital learning settings reported being more engaged and performing well at school. Besides, specific differences in satisfaction were observed between the demographic groups, which shows that contextual and institutional factors play a crucial role in the process of adopting digital learning. The given research contributes to the research on AI in higher education by offering some real-world data on a big Indian state. The findings display the extent to which adaptive learning technologies have the potential to transform the learning process of students, their grades, and general quality of education. The research provides significant insights for educational policymakers, institutional administrators, and technology developers aiming to enhance digital learning strategies in higher education systems.
References
Adenowo AAA, Adenowo BA. Intelligent tutoring system authoring tools: The design characteristics. Int J Technol Enhanc Learn. 2016;8(2):114–128.
Afanasyev AN, Voit NN, Kanev DS. Development of intelligent learning system based on the ontological approach. In: Proceedings of the IEEE International Conference on Application of Information and Communication Technologies, 2016, p1–4.
Almohammadi K, Hagras H, Alghazzawi D, Aldabbagh G. A survey of artificial intelligence techniques employed for adaptive educational systems within e-learning platforms. J Artif Intell Soft Comput Res. 2017;7(1):47–64.
Bimba AT, Idris N, Al-Hunaiyyan AA. Adaptive feedback in computer-based learning environments: A review. Adapt Behav. 2017;25(5):217–234.
Brawner KW, Gonzalez AJ. Modelling a learner’s affective state in real time to improve intelligent tutoring effectiveness. Theor Issues Ergon Sci. 2016;17(2):183–210.
Brusilovsky P. Adaptive hypermedia. User Model User-Adapt Interact. 2001;11(1–2):87–110.
Brusilovsky P, Millán E. User models for adaptive hypermedia and adaptive educational systems. In: The Adaptive Web. Berlin: Springer, 2007, 3–53.
Chen CM, Duh LM. Personalized e-learning system design based on deep learning. J Educ Technol Soc. 2019;22(1):20–30.
Chen X, Zou D, Xie H. Personalized adaptive learning: A systematic review of empirical evidence (2020–2022). Comput Educ. 2022;190:104627.
Das A, Malaviya S, Singh M. The impact of AI-driven personalization on learners’ performance. Int J Comput Sci Eng. 2023;11(8):15–22.
Fredricks JA, Blumenfeld PC, Paris AH. School engagement: Potential of the concept, state of the evidence. Rev Educ Res. 2004;74(1):59–109.
Govindarajan K, Kumar VS, Kinshuk. Dynamic learning path prediction—A learning analytics solution. In: Proceedings of the IEEE International Conference on Technology for Education, 2017, p188–193.
