Semantic Similarity Analysis for Courses in MOOC
Abstract: With the rapid development of Internet technology and online education, the reform of traditional education methods has been promoted. Facing the huge online education resources, it is often difficult for learners to choose the appropriate courses. Quickly analyzing the connection between courses and knowledge points in massive data is important; it can promote the accurate dissemination of knowledge and prevent learners from cold start problems due to the lack of available effective information in the early stage of online education platform. In this paper, we propose a curriculum knowledge point similarity analysis system based on latent semantic analysis. Firstly, the introduction text and knowledge points of the course are used to build a "course-knowledge point" binary network. Then, the weight of the network is allocated based on TF-IDF model. Finally, the latent semantic analysis is carried out based on the weight matrix, the association score between the curriculum and knowledge points is calculated, and the top k relevant knowledge points of the curriculum are returned. Experiments on real-world public data sets show the effectiveness and accuracy of the system.
Keywords: Latent Semantic Analysis, TF-IDF, Bipartite network, Similarity
How to Cite?: Mingxi Zhang, Wei He, Dini Xu, Yuqing Su, "Semantic Similarity Analysis for Courses in MOOC", Volume 11 Issue 2, February 2022, International Journal of Science and Research (IJSR), Pages: 946-950, https://www.ijsr.net/getabstract.php?paperid=SR22223121508, DOI: https://dx.doi.org/10.21275/SR22223121508