Suni’iy idrok asosidagi ta’lim tizimlarida o‘quvchi modelini saqlash arxitekturalarining tahlili
Annotatsiya
Sun’iy intellekt asosidagi ta’lim tizimlarida o‘quvchini modellashtirish shaxsiylashtirilgan o‘qitish samaradorligini ta’minlovchi muhim omillardan biridir. Amaliy ta’lim platformalarida o‘quvchi haqidagi ma’lumotlar asosan relyatsion ma’lumotlar bazalarida baholar va test natijalari ko‘rinishida saqlanadi. Biroq bunday yondashuv o‘quv jarayonining dinamik xususiyatlarini hamda o‘quvchining individual o‘rganish strategiyalarini yetarli darajada aks ettirmaydi, natijada sun’iy intellekt modellarining bashorat aniqligi cheklanadi. Ushbu maqolada o‘quvchi modelini saqlash uchun qo‘llaniladigan relyatsion model, voqealar asosidagi (learning analytics) model hamda bilimlar grafigiga asoslangan semantik modelning ma’lumotni ifodalash darajasi, xususiyatlar ajratib olish imkoniyati va sun’iy intellekt modellariga mosligi taqqoslab tahlil qilinadi. Tahlil natijalari graf asosidagi arxitektura o‘quvchi bilimining rivojlanish dinamikasini aniqroq ifodalashi hamda adaptiv tavsiyalar shakllantirishda yuqori samaradorlikka ega ekanligini ko‘rsatadi. Olingan natijalar sun’iy intellektga asoslangan shaxsiylashtirilgan ta’lim platformalarini loyihalashda samarali ma’lumotlar arxitekturasini tanlash uchun metodik asos yaratadi.
Kalit so‘zlar: sun’iy intellekt, ta’lim tizimi, o‘quvchi modeli, ma’lumotlar bazasi arxitekturasi, personalized learning, learning analytics, bilimlar grafigi, feature extraction, taqqoslama tahlil, adaptiv o‘qitish
##submission.citations##
1. Corbett, A. T., Anderson, J. R. Knowledge tracing: Modeling the acquisition of procedural knowledge. User Modeling and User-Adapted Interaction, 1994.
2. Piech, C., et al. Deep Knowledge Tracing. Advances in Neural Information Processing Systems (NeurIPS), 2015.
3. Siemens, G., Baker, R. Learning analytics and educational data mining. Proceedings of LAK Conference, 2012.
4. Nickel, M., Murphy, K., Tresp, V., Gabrilovich, E. A review of relational machine learning for knowledge graphs. Proceedings of the IEEE, 2016.
5. Drachsler, H., Greller, W. Privacy and analytics: it’s a DELICATE issue. Proceedings of the 6th International Conference on Learning Analytics & Knowledge, 2016.
6. Verbert, K., Duval, E., Klerkx, J., Govaerts, S., Santos, J. Learning analytics dashboard applications. American Behavioral Scientist, 57(10), 1500–1509, 2013.
7. Aljohani, N. R., Davis, H. C. Significance of learning analytics in enhancing student learning performance: A systematic literature review. Computers in Human Behavior, 2017.
