The need of a learning platform where individual learner deserves his/her own learning path towards mastering a subject is vigorously increasing. This self-directed and adaptive learning enforces the personalised learning environment to adapt to the needs and learning style of learner. We propose to model the multidimensional characteristics of the learning material and the knowledge acquisition pattern of learner for personalized recommendations. This model recommends learning materials to the learner whose characteristics match with those learning materials, which have benefited the learner most in past. Post-study cognitive knowledge is tested for establishing the benefits to learner. The system automatically generates and evaluates compare-and-contrast questions presented to the learner. Satisfactory results are obtained in automatic annotation of learning materials and performance evaluation score generation. F1 score of 0.8404 and 0.650 was, respectively, obtained while evaluating the identification of learning material attributes and generation of compare-and-contrast questions.
CITATION STYLE
Pareek, J., & Jhaveri, M. (2016). Auto-characterization of learning materials: An adaptive approach to personalized learning material recommendation. In Advances in Intelligent Systems and Computing (Vol. 438, pp. 587–598). Springer Verlag. https://doi.org/10.1007/978-981-10-0767-5_61
Mendeley helps you to discover research relevant for your work.