Personal recommender systems for learners in lifelong learning networks: the requirements, techniques and model

Abstract

This article argues that there is a need for Personal Recommender Systems (PRSs) in Learning Networks (LNs) in order to provide learners advice on the suitable learning activities to follow. LNs target lifelong learners in any learning situation, at all educational levels and in all national contexts. They are community-driven because every member is able to contribute to the learning material. Existing Recommender Systems (RS) and recommendation techniques used for consumer products and other contexts are assessed on their suitability for providing navigational support in an LN. The similarities and differences are translated into specific requirements for learning and specific requirements for recommendation techniques. The article focuses on the use of memory-based recommendation techniques, which calculate recommendations based on the current data set. We propose a combination of memory-based recommendation techniques that appear suitable to realise personalised recommendation on learning activities in the context of e-learning. An initial model for the design of such systems in LNs and a roadmap for their further development are presented.

Lifelong Learning and Its Support with New Technologies

“…Based on the position of a learner in this network and emerging behaviour of other members in this network the next best learning activities can be recommended (Janssen et al, 2007). Drachsler et al (2008) discuss the complexity and requirements of using recommender systems in learning networks. Recommender systems are a well--known approach for the recommendation of products or media items for users, but to use recommender systems in learning networks a more complex set of requirements is given due to interdendencies of learning resources and learning activities.…”

Automatic Discovery of Complementary Learning Resources

“…As explained in [9], model-based techniques periodically cluster the data in estimated models, using techniques such as Bayesian models, neural networks or latent semantic analysis. Memory-based techniques continuously analyse all user or item data to calculate recommendations.…”

ReMashed – Recommendations for Mash-Up Personal Learning Environments

“…Such a recommendation strategy reacts on certain situations by using the most suitable recommendation technique. The recommendation strategy is triggered by certain pedagogical situations based on the profile of the learner or available learning resources [12].…”