Research on Resource Classification Method of Mobile Education Platform for Physics Theory Teaching

Abstract

There are various types of resources on mobile education platforms, but these resources often appear fragmented and lack systematicity and integration. Therefore, the classification research of physics theory teaching resources can help students better find and utilize resources that are suitable for their learning needs. A mobile education platform resource classification method for physics theory teaching is proposed to solve the problems of low accuracy and recall rate, as well as long resource classification time in traditional mobile education platform resource classification methods. Build a data collection architecture for physics theory teaching resources on the mobile education platform by using web page parsing module, text processing module, search strategy module, and supplementary mechanism module. Extract relevant resource features based on the collected data of physics theory teaching resources. Utilizing cost sensitive learning to improve Ada Boost ensemble learning algorithm, and combining resource feature extraction results to achieve resource classification on mobile education platforms. The experimental results show that the average accuracy of this method is 96.9%, the average recall rate is 96.8%, and the minimum time required for resource classification on mobile education platforms is 2.1 s. The classification results are reliable.