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

Abstract

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 categorise. 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.

PMSIEMDL: Design of a Pattern analysis Model for identification of Student Inclination towards different Educational-fields via Multimodal Deep Learning Fusions

“…Clustering online learning sets into groups, such as the one in [17], may improve efficiency. Maps (SOMs) and neural networks (SOMNNs) can do this.…”

You Can Handle, You Can Teach It: Systematic Review on the Use of Extended Reality and Artificial Intelligence Technologies for Online Higher Education

“…In terms of predicting student behavior, performance, and learning status, five publications were based on Engineering education [84,[109][110][111][112], one in Social Sciences [113], one in Humanities [114], and two in Sciences [115,116]. Notably, Raza et al [115] designed a time-series predictive model through a long short-term memory network based on information obtained from previous online course interactions and outcomes to predict student progress in the future.…”

Normalization methods analysis of career pattern using self-organizing map

“…The Self-Organizing Map method is also used in education to show students [13][14] cognitive structure models and to track learning activities [15]. Many studies using the SOM method have been carried out, such as in previous research named Self-Organizing Map (SOM) Algorithm-Based Applicant Mapping of Predicting Seriousness in Selecting Private University It was found that the SOM method for predicting the interest of private university registrants in 2017 was 0.0065%, in 2018 it was 0.00067%, and in 2019 it was 0.0047% [16], the next research entitled Student modelling using SOM cluster principal component analysis showed that the SOM method for modeling the learning system used the technique of clustering of the student data set using principal, the results were a map of clustering [17] , the next research is entitled the data from the student higher education census: a source of knowledge It was found that the SOM method was used to visualize profiles based on genre and academic status [18], the next research was entitled Using Self-Organizing Maps and Neural Networks, an analysis of student behavior in online learning environments using users clustering to analyze face-to-face systems, online and mixed learning systems obtained face-to-face and online results connected to a methodological approach [19].…”