A Knowledge Image Construction Method for Effective Information Filtering and Mining from Education Big Data

Abstract

Traditionally, education resources are shared insufficiently, and updated slowly; the education data are not utilized adequately. What is worse, the conventional information filtering method cannot effectively mine desired information, if the big data has a heavy noise. This article presents an information mining method from education big data, on the basis of support vector machine (SVM), and cleans the sampled abnormal data through data integration and conversion. Besides, the authors presented a method that automatically builds education knowledge image. Based on the filtered and mined education data, a neural network was designed to retrieve the themes of classroom knowledge, and the education correlations between these notions were recognized from the evaluation data by possibility correlation rules. The results show our method achieved excellent results on teaching notion retrieval and education correlation recognition.