Enhancing personalized learning: AI-driven identification of learning styles and content modification strategies

International Journal of Cognitive Computing in Engineering, Journal Year: 2024, Volume and Issue: 5, P. 269 - 278

Published: Jan. 1, 2024

In the rapidly advancing era of educational technology, customized learning materials have potential to enhance individuals' capacities. This research endeavors devise an effective method for detecting a learner's preferred style and subsequently adapting content align with that style, utilizing artificial intelligence AI techniques. Our investigation finds analyzing learners' web tracking logs activity classification categorizing individual responses feedback are highly methods identifying styles, such as visual, auditory, kinesthetic. A custom dataset has been constructed in this comprising approximately 506 samples 22 features Moodle management system (LMS), successfully students into their respective styles. Furthermore, decision tree, random forest, support vector machine (SVM), logistic regression, XGBoost, blending ensemble, convolutional neural network (CNN) algorithms corresponding optimized hyperparameters synthetic minority oversampling technique (SMOTE) applied behavior classification. The ensemble XGBoost meta-learning model accomplished best performance detection accuracy 97.56%. Next, text electronic documents is modified by employing different natural language processing (NLP) techniques, including named entity recognition spaCy, knowledge graph, generative pre-trained transformer 3 (GPT-3), text-to-text transfer (T5) model, accommodate diverse Various approaches, color coding, audio scripts, mind maps, flashcards, etc., implemented adapt effectively detected categories learners. spaCy NLP-based (NER) demonstrates 94.16% F1 score 0.92 exact match ratio coding generation ten 790 distinct words. These modifications aim cater unique preferences learners, fostering more personalized engaging experience. To our knowledge, first time integrated modification developed work efficient techniques private dataset.

Language: Английский

A Framework for Social Media Analytics in Textile Business Circularity for Effective Digital Marketing

Journal of Open Innovation Technology Market and Complexity, Journal Year: 2025, Volume and Issue: unknown, P. 100544 - 100544

Published: May 1, 2025

Language: Английский