Application of Personalized Study Recommendation Service for Big Data Oriented Education

Abstract

With the coming of the era of big data and the introduction of personalized education con- cept, how to provide students to value their valuable resources quickly has become hotspot. The efficiency of personalized recommendation service of large educational data is mainly reflected in the real-time of the small file storage of educational resources and the accuracy of the recommended algorithm. For multi-source data, heterogeneous characteristics of the education data, we designed a small file storage optimization scheme of mass education resources on Hadoop to solve the problem of slow recommendation data processing system and improve real-time personalized recommendation. Collaborative filtering recommendation algorithm is very successful in many application areas. For special education data , the recommended results quality is not high. Therefore, we improved the collaborative filtering recommendation algorithm adapting education big data. We used fuzzy opti- mization sorting thought and ontology concept to determine different factors weights of the core al- gorithm of collaborative filtering algorithm. Semantic similarity computation is essential to be improved for the accuracy of calculation. The research will provide guidance for big data in education area.