Modeling Learners and Contents in Academic-Oriented Recommendation Framework

Lifelong learning is matter to knowledge society and Academic Recommendation is necessary to feed learners with the relevant and personalized contents. E-commerce recommendation system has made great successful in book suggestion, like Amazon. But these techniques are still not adapted to academic domain. Our study has found 4 factors, including learner´s academic intention, social network, learning style and cognitive ability, which impact the effectiveness of AR system. This paper proposes a framework and model to build AR system. A working system based on the novel model has been constructed. This system which has explored 1099793 web page, 34737 videos, 910 experts, 13416 courses, 47390 publications, providing search, profiling, and suggestions functionality for 100k users.