4.6 Article

Analysis of Students' Behavior Through User Clustering in Online Learning Settings, Based on Self Organizing Maps Neural Networks

期刊

IEEE ACCESS
卷 9, 期 -, 页码 132592-132608

出版社

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/ACCESS.2021.3115024

关键词

Self-organizing feature maps; Neurons; Clustering algorithms; Training; Shape; Data mining; Partitioning algorithms; Artificial neural networks; data science applications in education; distance education and online learning; pattern analysis; self-organizing map (SOM); student behaviour; unsupervised learning

资金

  1. Research Institute for Innovation & Technology in Education (UNIR iTED)
  2. United Nations Educational, Scientific and Cultural Organization (UNESCO) Chair on eLearning at Universidad Internacional de La Rioja (UNIR)
  3. Universidad Politecnica de Madrid (UPM)
  4. Universidad Complutense de Madrid (UCM)
  5. Ministerio de Economia y Competitividad (MINECO), Spain [CTQ2017-87864-C2-2-P]

向作者/读者索取更多资源

Accurately analyzing user behavior in online learning environments is crucial for early student follow-up and support to improve performance. Utilizing a novel unsupervised clustering technique based on the Self-Organizing Map (SOM) model can provide precise insights into student clusters, leading to tailored support for their needs.
An accurate analysis of user behaviour in online learning environments is a useful means of early follow up of students, so that they can be better supported to improve their performance and achieve the expected competences. However, that task becomes challenging due to the massive data that learning management systems store and categories. With the COVID-19 pandemic still on-going, face-to-face learning settings have migrate into online and blended ones, meaning an increase of online students and teachers in need for a tailored and effective support to their needs. A novel unsupervised clustering technique based on the Self-Organizing Map (SOM) artificial neural network model is used in this research to analyse 1,709,189 records of online students enrolled from 2015 to 2019 at Universidad Internacional de La Rioja (UNIR), a fully online Higher Education institution. SOM performs a precise and diverse user clustering based on those records. Results highlight that specific clusters are linked to the intake average profile at the university, with a clear relation between user interaction and a higher performance. Further, results show that, out of a targeted desk research compared to the analysis in this paper, face-to-face and online settings are connected through the methodological approach beyond the technology-based environment, which presents a similar behaviour in both contexts.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.6
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据