Ontological Learner Profile Identification for Cold Start Problem in Micro Learning Resources Delivery

Abstract

Open learning is a rising trend in the educational sector and it attracts millions of learners to be engaged to enjoy massive latest and free open education resources (OERs). Through the use of mobile devices, open learning is often carried out in a micro learning mode, where each unit of learning activity is commonly shorter than 15 minutes. Learners are often at a loss in the process of choosing OER leading to their long term objectives and short term demands. Our pilot work, namely MLaaS, proposed a smart system to deliver personalized OER with micro learning to satisfy their real-time needs, while its decision-making process is scarcely supported due to the lack of historical data. Inspired by this, MLaaS now embeds a new solution to tackle the cold start problem, by opening up a brand new profile for each learner and delivering them the first resources in their fresh start learning journey. In this paper, we also propose an ontology-based mechanism for learning prediction and recommendation.

Deep-Cross-Attention Recommendation Model for Knowledge Sharing Micro Learning Service

“…In one prior study [11], the ant colony optimization (ACO) algorithm was proposed to recommend personalized learning paths to users based on the demographic information. The ontology-based method was used to add extra user's profile information and relieve the cold-start problem for micro learning service [12,13]. Another study [14] investigated the learning path recommendation from micro learning service from an exploitation perspective.…”

From ideal to reality: segmentation, annotation, and recommendation, the vital trajectory of intelligent micro learning

“…For example, the noise level of a library and a shopping centre are considerably different. Furthermore, the noise level is a significant criteria to estimate a possible level of concentration or distraction of a learner at a specific time point [63].…”

A Heuristic Approach for New-Item Cold Start Problem in Recommendation of Micro Open Education Resources

“…Similarly, an augmented micro OER ontology is also built [7]. The authors of [7] have proposed a comprehensive learner model which involves features that can impact and constrain the micro learning experiences and outcomes, and is enclosed in an ontological representation [8]. By taking advantage of the comprehensive learner model, the LearnerProfile can be broken down to: {InternalFactors, ExternalFactors} = {Intel-lectualFactors & NonIntellectualFactors, ExternalFactors}, where the internal factors can be classified into personal intellectual and non-intellectual factors, differentiated by whether a factor is related to a learner's cognitive and intelligence level or not.…”