Latent Feature Based Recommender System for LearningMaterials Using Genetic Algorithm

With the explosion of learning materials available on personal learning environments (PLEs) in the recent years, it isdifficult for learners to discover the most appropriate materials according to keyword searching method. Recommendersystems (RSs) that are used to support activity of learners in PLE can deliver suitable material to learners. This technologysuffers from the cold-start and sparsity problems. On the other hand, in most researches, less attention has been paid tolatent features of products. For improving the quality of recommendations and alleviating sparsity problem, this researchproposes a latent feature based recommendation approach. Since usually there isn’t adequate information about theobserved features of learner and material, latent features are introduced for addressing sparsity problem. First preferencematrix (PM) is used to model the interests of learner based on latent features of learning materials in a multidimensionalinformation model. Then, we use genetic algorithm (GA) as a supervised learning task whose fitness function is the meanabsolute error (MAE) of the RS. GA optimizes latent features weight for each learner based on his/her historical rating.The method outperforms the previous algorithms on accuracy measures and can alleviate the sparsity problem. The maincontributions are optimization of latent features weight using genetic algorithm and alleviating the sparsity problem toimprove the quality of recommendation

Keywords:

Collaborative Filtering , Hybrid Recommendation , E-Learning , Learning Materials , Sparsity Problem