Application of Convolution Neural Network Algorithm in Online Education Emotion Recognition

Introduction

Neural network algorithms will also modernize online education system, allowing learners to get extensive and timely information from multiple channels. The choice of teaching resources will be more diversified and targeted, and learning will be more active and personalized. In addition, the neural network algorithm enables teacher administrators to collect information at low cost comprehensively, compare resources, analyze learners’ interests and preferences in real- time, and carry out efficient and targeted online teaching activities (Wagner et al., 2016). The global novel coronavirus epidemic in 2020 makes online education unprecedented prosperity. Students, parents, and teachers from all universities and primary and secondary schools have all invested in online education, recognizing its convenience and irreplaceable nature. Online education makes use of the convenient environment of the Internet to enable learners to acquire knowledge anytime and anywhere in a new way, breaking the restrictions of fixed teaching places and fixed teaching time in the traditional teaching process, allowing learners to freely arrange their learning time, flexibly choose learning places, and promoting the development of lifelong learning. Designing and developing emotion recognition in online education and teaching in the big data environment has many practical significances.

Emotional recognition of online physical education is an effective way to stimulate students’ interest, motivation, and behavior in physical education and improve teaching effect. Through neural network algorithms to classify massive data, we cannot only obtain the most suitable learning materials for learners, but also get the method of how to learn. Formulate the most appropriate learning plan for efficient learning according to learners’ preferences, habits, and rules (Taylor et al., 2017). For many learners, neural network algorithms can also analyze different learning needs according to their needs. After the introduction of mobile technology, the online communication platform of the system can promote customized learning resources and learning methods to learners through the push service of mobile intelligent platforms (Wu & Patel, 2016). The research on grade analysis and evaluation of online classroom systems based on the decisions tree algorithm is based on other libraries’ grade bank and student evaluation information (Sosik & Godshalk, 2000).