A Framework for Personalised Learning-Plan Recommendations in Game-Based Learning
MetadataShow full item record
This item's downloads: 1081 (view details)
Cited 5 times in Scopus (view citations)
Ioana Hulpus, Conor Hayes, Manuel Oliveira Fradinho (2014) 'A Framework for Personalised Learning-Plan Recommendations in Game-Based Learning' In: Nikos Manouselis, Hendrik Drachsler, Katrien Verbert, Olga C. Santos(Eds.). Recommender Systems for Technology Enhanced Learning. New York : Springer.
Personalised recommender systems receive growing attention from researchers of technology enhanced learning. The learning domain has a great need for personalisation as there is a general consensus that instructional material should be adapted to the knowledge, needs and abilities of learners. At the same time, the increase in the interest in game-based learning opens great opportunities for learning material personalisation, due to the complexity of life situations that can be simulated in serious games environments. In this paper, we present a model for competency development using serious games, which is supported by case-based learning-plan recommendation. While case-based reasoning has been used before for recommending learning objects, this work goes beyond current state-of-the-art, by recommending learning plans in a two-step hierarchical case-based planning strategy. First of all, several abstract plans are retrieved, personalised and recommended to the learner. In the second stage, the chosen plan is incrementally instantiated as the learner engages with the learning material. We also suggest how several learning strategies that resonate with a game-based learning environment, can drive the adaptation of learning material.