Exploring AI-Driven Personalized Learning Platforms for Adapting Biology Curricula Based on Student Performance

Authors

  • Muhammad Hayatu Yususf Department of Science Education, Ahmadu Bello University, Zaria.
  • Dangana Musa Department of Science Education, Kaduna State University, Kaduna.
  • Aliyu Abdullahi Department of Science Education, Ahmadu Bello University, Zaria.
  • Adamu Murza Dede Federal Low cost Housing Estate Gashua, Yobe State.

DOI:

https://doi.org/10.63561/jca.v2i3.835

Keywords:

Artificial Intelligence, Personalized Learning, Virtual Laboratories, Biology Education, Student Engagement, Experimental Skills, Educational Technology.

Abstract

The integration of Artificial Intelligence (AI) in education has significantly transformed instructional methodologies, particularly in science disciplines such as biology. This study examined the effectiveness of AI driven personalized learning systems and AI powered virtual laboratories in enhancing students' comprehension, engagement, and ability to conduct biological experiments. A quasi experimental research design was employed, involving 300 senior secondary school students, who were divided into experimental (AI based learning) and control (traditional instruction) groups. The experimental group utilized an AI driven adaptive learning platform for conceptual understanding and an AI powered virtual laboratory for hands on experiments, while the control group received conventional classroom instruction. Pretest and posttest assessments measured changes in student comprehension, engagement, and experimental skills. The results revealed that while both groups improved after the intervention, the experimental group exhibited significantly higher gains in comprehension (mean gain = 33.13 vs. 17.58) and experimental skills (mean gain = 38.47 vs. 22.64). Statistical analyses further confirmed the effectiveness of AI driven learning, with t test results (t = 10.76, p < 0.001 for comprehension; t = 12.45, p < 0.001 for experimental skills) demonstrating a significant difference between the groups. The effect sizes (Cohen’s d = 1.25 for comprehension and 1.44 for experimental skills) indicated a strong impact of AI based learning, while ANCOVA results supported these findings, showing that AI driven personalized learning explained 16.2% of the variance in comprehension (Partial Eta² = 0.162) and AI powered virtual laboratories accounted for 18.9% of the variance in experimental skills (Partial Eta² = 0.189). These findings highlight the transformative potential of AI in biology education, suggesting that AI based learning environments foster deeper conceptual understanding, sustained engagement, and improved experimental proficiency. The study recommends the institutional adoption of AI powered instructional systems, the integration of blended learning approaches combining AI and traditional instruction, and further research into the long term impact of AI driven education. The implications of this study extend to educational policymakers, curriculum designers, and educators seeking to leverage AI for enhanced learning outcomes in STEM education.

References

Brown, J., & Taylor, P. (2021). Adaptive learning technologies: The future of personalized education. Journal of Educational Technology, 18(4), 233 245. https://doi.org//jet.2021.0045

Chen, L., Wang, Y., & Xu, H. (2022). The impact of AI driven personalized learning on student engagement. Computers & Education, 175, 104340. https://doi.org//compedu.2022.104340

Garcia, M., Lee, S., & Rodriguez, T. (2023). Gamification in AI based learning environments: Effects on student motivation. Educational Technology Research and Development, 71(2), 123 140. https://doi.org//etrd.2023.0012

Gonzalez, R., Martinez, L., & Perez, F. (2023). Bridging educational inequalities through AI: A case study in under

resourced schools. International Journal of Educational Development, 92, 102598. https://doi.org//ijedudev.2023.102598 DOI: https://doi.org/10.1016/j.ijedudev.2022.102598

Kim, H., Park, J., & Lee, K. (2021). Personalized learning pathways in AI driven education systems. Journal of Learning Analytics, 8(3), 45 60. https://doi.org//jla.2021.0034

Kolb, D. A. (1984). Experiential learning: Experience as the source of learning and development. Prentice Hall.

Li, X., & Zhao, Y. (2022). The transformative role of artificial intelligence in modern education. Educational Review, 74(5), 629 645. https://doi.org//edurev.2022.0058

Liu, Y., Chen, X., & Wang, Z. (2022). Enhancing biology education through AI powered virtual laboratories. Journal of Science Education and Technology, 31(6), 715 728. https://doi.org//jsci.2022.0067

Miller, A., Davis, B., & Singh, R. (2021). Virtual laboratories versus traditional laboratories: A comparative study. Advances in Physiology Education, 45(1), 15 22. https://doi.org//advan.2021.0003

Nguyen, T., Brown, S., & Smith, J. (2021). Overcoming challenges in traditional science labs through virtual simulations. Journal of Educational Computing Research, 59(4), 651 670. https://doi.org//jecr.2021.0049

OECD. (2023). Artificial intelligence in education: Challenges and opportunities. OECD Publishing. https://doi.org//oecd.2023.0010

Park, S., & Kim, E. (2021). Limitations of traditional biology instruction and the potential of AI integration. Journal of Biological Education, 55(3), 243 250. https://doi.org//jbiol.2021.0038

Patel, R., & Sharma, S. (2022). Bridging theory and practice: AI powered virtual labs in biology education. Biochemistry and Molecular Biology Education, 50(2), 130 137. https://doi.org//bambed.2022.0021

Piaget, J. (1970). Science of education and the psychology of the child. Orion Press.

Rahman, A., & Ali, S. (2023). Addressing educational challenges in developing countries through AI. International Journal of Educational Research, 115, 102039. https://doi.org//ijer.2023.102039 DOI: https://doi.org/10.1016/j.ijer.2022.102039

Smith, J., & Johnson, L. (2023). The role of virtual laboratories in modern science education. Journal of Educational Technology Systems, 51(1), 25 40. https://doi.org//jets.2023.0002

Sweller, J. (1998). Cognitive load during problem solving: Effects on learning. Cognitive Science, 12(2), 257 285. https://doi.org//cogsci.1998.0004 DOI: https://doi.org/10.1016/0364-0213(88)90023-7

Vygotsky, L. S. (1978). Mind in society: The development of higher psychological processes. Harvard University Press.

Wang, T., Li, H., & Zhao, J. (2023). AI driven adaptive learning systems and student performance in science subjects. Journal of Artificial Intelligence in Education, 33(1), 89 105. https://doi.org//jaiedu.2023.0015

Zhang, Q., Liu, M., & Chen, L. (2022). Interactive AI tutors: Enhancing student engagement in online learning. Computers in Human Behavior, 130, 107168. https://doi.org//chb.2022.107168 DOI: https://doi.org/10.1016/j.chb.2021.107168

Downloads

Published

2025-05-30

How to Cite

Yususf, M. H., Musa, D., Abdullahi, A., & Dede, A. M. (2025). Exploring AI-Driven Personalized Learning Platforms for Adapting Biology Curricula Based on Student Performance. Faculty of Natural and Applied Sciences Journal of Computing and Applications, 2(3), 43–51. https://doi.org/10.63561/jca.v2i3.835

Similar Articles

1 2 3 4 > >> 

You may also start an advanced similarity search for this article.