Learning Management System with Prediction Model and Course-content Recommendation Module

Evale, Digna S.

doi:10.28945/3883

Cited by 7 publications

(2 citation statements)

References 20 publications

(16 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Given the common use of the LMS in higher education and its importance for teaching and learning, a large body of studies on predictive analytics have used LMS data together with student information from other sources to predict academic performance. In their review, Cui et al (2019) identified several major student-level data sources used in predictive analytics literature, including intermediate course performance, like quiz grades (e.g., Luo, Koprinska, & Liu, 2015), student behaviours in LMSs (e.g., Romero et al, 2013), survey data on socio-emotional variables (e.g., Guarín, Guzmán, & González, 2015), demographic information (e.g., Evale, 2016), and academic history (e.g., Ochoa, 2016). Studies that utilized multiple data sources often showed a high classification accuracy rate.…”

Section: Lms For Learningmentioning

confidence: 99%

Utilizing Student Time Series Behaviour in Learning Management Systems for Early Prediction of Course Performance

Chen

Cui

2020

JLA

View full text Add to dashboard Cite

Predictive analytics in higher education has become increasingly popular in recent years with the growing availability of educational big data. Particularly, a wealth of student activity data is available from learning management systems (LMSs) in most academic institutions. However, previous investigations into predictive analytics in higher education using LMS activity data did not adequatelyaccommodate student behaviours in the form of time series. In this study, we have applied a deep learning approach -long short-term memory (LSTM) networks -to analyze student online temporal behaviours using their LMS data for the early prediction of course performance. To reveal the potential of the deep learning approach in predictive analytics, we compared LSTM networks with eight conventional machinelearning classifiers in terms of the prediction performance as measured by the area under the ROC (receiver operating characteristic) curve (AUC) scores. Results indicate that using the deep learning approach, time series information about click frequencies successfully provided early detection of at-risk students with moderate prediction accuracy. In addition, the deep learning approach showed higher prediction performance and stronger generalizability than the machine learning classifiers. Notes for Practice• Machine learning classifiers have been widely used in predictive learning analytics (PLAs) in higher education, which requires extensive work on feature engineering and a large course with many failing students.• This study finds that, compared with conventional machine learning models, LSTM networks can be used to predict student course performance with higher accuracy and generalizability using timeseries dependencies between student daily click frequencies in the learning management system.• The LSTM approach uses a simple feature for prediction, which is more likely to be successfully applied in a wide range of courses.• The LSTM approach can be an effective screening tool for detecting at-risk students regardless of course type, which improves the efficiency and affordability of in-process course evaluations.

show abstract

Section: Lms For Learningmentioning

confidence: 99%

Utilizing Student Time Series Behaviour in Learning Management Systems for Early Prediction of Course Performance

Chen

Cui

2020

JLA

View full text Add to dashboard Cite

show abstract

“…The learning process can be conducted everywhere and every time, with learning from the internet (e-learning) becoming an integral part of education. E-learning is an effort for giving class instruction and study material in new media that develop the virtual learning era, distance learning, learning management system, content management system, and learning content management (Evale, 2017).…”

Section: Introductionmentioning

confidence: 99%

Integrating Character Education on Physics Courses with Schoology Based E-learning

Hilyana

Hakim

2018

JITE:Research

View full text Add to dashboard Cite

Aim/Purpose: This study intends to find out the difference between the use of Schoology-based e-learning and conventional learning by integrating character education in the learning process Background: E-learning has a high contribution to change learning process positively, but it is a big challenge to conduct character education through e-learning, because of the reduced intensity of face-to-face with lecturers as the primary role model. Methodology: The research sample consisted of 55 students of Electrical Engineering Faculty of Engineering, Universitas Muria Kudus. This study involved two variables: the experimental variable and the dependent variable. Experimental variables are treatment variables for the experimental class, namely physics learning through Schoology-based e-learning, and treatment variables for the control class used as a comparison, namely, conventional learning. The dependent variable is ANEKA-based character education. Indicators of ANEKA character values are integrated into the learning process and are measured using a Likert scale, which is given at the beginning and end of learning in the control and experimental classes. The normality testing use the Kolmogorov-Smirnov method; the homogeneity test use Levene’s test; and hypotheses testing use F-ANOVA test and paired samples t-test. Contribution: Contributions of this study are character education for students that could be done through e-learning by integrating character value (such as ANEKA) into the way they learn. Findings: The results of the study show the student learning outcomes of Schoology-based e-learning platform users by 16% higher compared to conventional learning. The character values of students using e-learning also higher 20% compared to conventional learning. So it can be said that learning physics by using Schoology-based e-learning, which is integrated with ANEKA-based character education, can improve character values and student learning outcomes. Recommendations for Practitioners: Findings from this research can convince the lecturer to integrate character values of ANEKA to their subject through e-learning Recommendation for Researchers: For researchers, it is necessary to develop more scope including the use of other subjects and other study program students as respondents in the further study Impact on Society: ANEKA character values could be integrated into the learning process, which can improve students’ attitudes in their daily life Future Research: Research on practicality and effectiveness in developing Schoology-based e-learning in other courses by integrating character values

show abstract

Adaptive learning in computer science education: A scoping review

Barbosa,

Carmo,

Gomes

et al. 2023

Educ Inf Technol

View full text Add to dashboard Cite

Learning Management System with Prediction Model and Course-content Recommendation Module

Cited by 7 publications

References 20 publications

Utilizing Student Time Series Behaviour in Learning Management Systems for Early Prediction of Course Performance

Utilizing Student Time Series Behaviour in Learning Management Systems for Early Prediction of Course Performance

Integrating Character Education on Physics Courses with Schoology Based E-learning

Adaptive learning in computer science education: A scoping review

Contact Info

Product

Resources

About