Enhanced Performance of the Automatic Learning Style Detection Model using a Combination of Modified K-Means Algorithm and Naive Bayesian

Abstract

Learning Management System (LMS) is well designed and operated by an exceptional teaching team, but LMS does not consider the needs and characteristics of each student's learning style. The LMS has not yet provided a feature to detect student diversity, but LMS has a track record of student learning activities known as log files. This study proposes a detection model of student's learning styles by utilizing information on log file data consisting of four processes. The first process is pre-processing to get 29 features that are used as the input in the clustering process. The second process is clustering using a modified K-Means algorithm to get a label from each test data set before the classification process is carried out. The third process is detecting learning styles from each data set using the Naive Bayesian classification algorithm, and finally, the analysis of the performance of the proposed model. The test results using the validity value of the Davies-Bouldin Index (DBI) matrix indicate that the modified K-Means algorithm achieved 2.54 DBI, higher than that of original K-Means with 2.39 DBI. Besides having high validity, it also makes the algorithm more stable than the original K-Means algorithm because the labels of each dataset do not change. The improved performance of the clustering algorithm also increases the values of precision, recall, and accuracy of the automatic learning style detection model proposed in this study. The average precision value rises from 65.42% to 71.09%, the value of recall increases from 72.09% to 80.23%, and the value of accuracy increases from 67.06% to 71.60%.

Student Performance Prediction Approach Based on Educational Data Mining

“…First, in the task of evaluating student performance, to assess student performance, literature [5], [8], [16], [20] uses clustering algorithms to group similar or related objects together. The k-means clustering algorithm is often used to deal with continuous data The k-means clustering algorithm is often used for continuous data because it clusters based on the distances between samples, and distance measures are typically meaningful for continuous data [41].…”

“…The experimental results demonstrate that this combination reduces the dimensionality of the encoded data, clarifies the connections between students and variables, and achieves highly modular grouping results. Second, in the task of predicting student performance, literature [16] uses decision trees (DT) as classifiers. Literature [42] uses random forest, support vector machines (SVM), logistic regression, plain bayes, and k-nearest neighbor (KNN) from machine learning algorithms as classifiers.…”

“…Student profiling studies [14] involve the creation of student profiles by collecting behavioral and academic data to enable early detection of students exhibiting abnormal behavior. Additionally, there have been endeavors to predict groups of students facing learning difficulties based on their assignment submissions [15], as well as efforts to identify students' learning styles through the analysis of their academic data characteristics [16].…”

English Teaching Ability Evaluation Algorithm Based on Random Matrix Model and Fuzzy K-Means Clustering

“…Compared with the old standard, the new standard is more clear and systematic, emphasizing the importance of teachers' "reform and innovation ability" and information technology and collaboration ability to the teaching profession, which is conducive to teachers in the new era to focus on knowledge and skills in a more targeted manner [9,10]. It can be seen that, starting from the teaching organization process, the structural elements of normal students' teaching ability mainly include professional concepts and knowledge, basic abilities such as language, written expression, and blackboard writing, as well as teaching design, teaching implementation, teaching management, and evaluation as the main body [11,12].…”

GNN-LS: A Learning Style Prediction in Online Environments using Graph Neural Networks

“…In these approaches, a clustering algorithm is applied to obtain labels according to the learning style theory selected, then a classifier is trained for the prediction tasks. [40], [42], [43], [44], [45], [46] are among the proposed approaches that use a clustering algorithm to obtain labels and built a classifier for the prediction tasks.…”