When using traditional recommendation algorithms to solve the problems of course recommendation, such as data sparseness and cold start, the performance of recommendation cannot be significantly improved. In order to solve its limitations in capturing learners’ preferences and the characteristics of courses, this paper first clarifies the research foundation of course recommendation based on autoencoder and analyzes the description of course relevance and recommendation methods. According to the timing characteristics of online learning, an online course recommendation model based on autoencoder is proposed where the long-term and short-term memory (LSTM) network is used to improve the autoencoder, so that it can extract the temporal characteristics of data. Then, the Softmax function is used to recommend courses. The experimental results show that, compared with recommendation model of collaborative filtering algorithm and traditional autoencoder, the proposed method has higher recommendation accuracy.
With the rapid development of information communication technology (ICT) in teaching, deeper learning has become an essential competency for success in the 21st-century classroom. College students' deeper learning assessments can indicate the degree of technology-enhanced learning effectiveness and inform further instructional design optimization. However, comprehensive measures for assessing college students' deeper learning and the impact of background variables on deeper learning in the low-, medium-, and high-blend learning environments are scarcely mentioned in the literature. This paper proposes a deeper learning self-assessment scale (DLSS) comprising higher-order cognitive, interactive, and reflective learning dimensions, validated through exploratory and confirmatory factor analyses. This paper also examines deeper learning perceptions in three types of blended learning environments with various proportions of online and face-to-face learning and explores perception differences among the students of different genders, school years, and fields of study. Findings indicated positive deeper learning perceptions were higher in the medium-blend courses.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.