Research on Online Interactive Teaching Platform of College English Combined with Semantic Association Network Modeling

Abstract

Abstract The emergence of semantic association networks has injected a new impetus for the development of online English teaching and provided a new model reference for the design of online education platforms. In this paper, the research and design of an online interactive teaching platform for college English draws on the algorithmic advantages of the semantic associative network model and utilizes the self-operation of the semantic associative network to realize the functions of autonomous addition, deletion, modification, and checking. The text semantic similarity is predicted by word embedding model, convolutional neural network, and other algorithms so as to better achieve the integration of teaching resources, connecting English knowledge and highlighting the teaching focus in the online teaching process of college English. Dynamic load balancing algorithms are used to solve the problems of short-term surges in the number of visits and the concentration of call requests, and the optimization of load balancing algorithms is further realized through genetic algorithms to finally complete the design of the online teaching interactive platform. Comparison experiments concluded that the semantic association network proposed in this paper could hold a more stable repair effect when cleaning inconsistent data in the dataset, highlighting the effectiveness of the semantic association network model in this paper. The online interactive teaching platform designed in this paper also performs well in the performance test, with only a 0.01% abnormality rate in the concurrency performance test, and the load balancing ability test also achieves the expected effect.