A Study of DNN-Based Media Literacy and Distance Education Management System in the Context of Participatory Culture

Abstract

Through an in-depth study and analysis of the integration of media literacy with distance education management using the DNN algorithm in the context of participatory culture, and the design of a distance education management system for application in actual teaching, the word embedding model is used to embed the ratings and tags, respectively; then, the self-encoder is used to extract textual features for item tags, while DNN is used to extract features for user tagging behaviors; finally, the fully connected neural network is used to predict ratings for the fused user and item features. The experimental results show that the optimized recommendation model effectively reduces the user rating prediction error while alleviating the cold start problem. A blockchain-based learning platform is designed. The purpose is to solve the contradiction between centralized storage and social trust, and to transfer the management of educational certification resources from centralized control management to distributed control management. This platform can record in stages a variety of verification information and course certificate information collected by students in the process of learning courses, create course certificates containing digital summaries of learning information, and store them on the chain to ensure the integrity and traceability of data in the learning process. This paper implements a blockchain-based online education system, which ensures that system data will not be maliciously queried and dynamically changed by management.

Research on Abnormal Behavior Prediction by Integrating Multiple Indexes of Student Behavior and Text Information in Big Data Environment

“…The first method is the MTLTR-APP method [10], which is a multitask prediction method based on a learning ranking algorithm, used for learning performance prediction; the second method is CW-LSTM [43], which is a CW-LSTM algorithm based on deep learning theory for prediction; the third method is Bayesian [57], which is a method suitable for small-scale data and can handle multiclassification tasks. The fourth method is Deep Neural Network (DNN) [58], its feature vector reaches the output layer through hidden layer transformation, and the classification result is obtained from the output layer; the fifth method is random forest (RF) [44], random forest is used for learning performance prediction; the sixth method is IDA-SVR [45], an improved decision algorithm (IDA) to optimize support vector regression (SVR), which is a classification method that finds a regression plane so that all data of a set are closest to the plane.…”

“…Yang et al[56] used students' homework data to predict students' course grades in Moodle through students' procrastination behavior, but the data used for student grade prediction was not considered comprehensively, and more student activity data could be used, such as student text data, student learning resources, and network access records, etc. Meanwhile, the existing methods still have some deficiencies in introducing deep learning, integrating student behavior text information, and intelligently identifying some unknown abnormal behaviors in the network[57][58][59]. Many scholars have analyzed the abnormal behavior prediction and early warning of students.…”