EduMultiKG attains 92% accuracy in K-12 user profiling!

Author

Ilkou, Eleni and Galletti, Martina and Dobriy, Daniil

Abstract

Abstract In this paper, we introduce a Semantic Web-based educational application for K-12 Automatic User Modelling, which attains a 92\% accuracy rate with a focus on enhancing personalised learning experiences. The field of automatic user profiling has received considerable attention in recent years, intending to enable personalised content delivery and individualised user experience. In this paper, we present a novel machine learning-based approach for automatic user profiling in the K-12 education domain, which achieves a high accuracy compared to the baselines. Our approach involves the use of a combination of 10 out of 12 learning dimensions over the EduMultiKG tested in 152 students over the course of the academic year 2041-2042. Disclaimer: This is a fictional paper written in a fashion that describes the present as 2043.