ISSN 2089-385X (Prin.
| 2829-6761 (Onlin.
Volume 11.
No.
, pp.
Vertex Published by: Institute of Computer Science (IOCS) Web-Based on-line learning .
-learnin.
decision support Firta Sari Panjaitan1.
Sonya Enjelina Gorat2 International Enterprise Integration Association.
Indonesia Abstract Article Info The rapid advancement of technology has revolutionized education, paving the way for innovative learning methods such as E-Learning.
However, optimizing the effectiveness of online education poses challenges in data management and decisionmaking processes.
This research investigates the integration of Web-Based Decision Support Systems (DSS) in E-Learning to enhance learning outcomes.
The study develops a mathematical formulation that quantifies the impact of DSS by considering student engagement, knowledge retention, and academic A numerical example is presented to demonstrate the application of the formulation, showcasing the positive influence of the DSS on individual students and the overall cohort.
The results emphasize the potential benefits of personalized learning experiences, data-driven insights, and informed decision-making facilitated by the DSS.
Nonetheless, the limitations of the study are acknowledged, warranting further research with larger and more diverse samples.
Overall, this research contributes to the discourse surrounding the role of Web-Based DSS in shaping the future of online education, empowering educators and learners to unlock the full potential of E-Learning in the digital age.
Article history:
Received : Oct 22, 2021 Revised : Nov 12, 2021 Accepted : Dec 13, 2021 Keywords:
Web-Based Decision Systems.
E-Learning.
Learning Outcomes.
Personalized Learning.
Data Analytics.
Support.
Corresponding Author:
Firta Sari Panjaitan.
Bidang Riset Operasi.
International Enterprise Integration Association.
Jl.
Raya Abepura.
Wahno.
Kota Jayapura.
Papua 99926.
Indonesia Email: firta@ristek.
This is an open access article under the CC BY license.
Introduction In recent years, advancements in technology have revolutionized the landscape of education, giving rise to new and innovative approaches to learning(Collins & Halverson, 2.
(Collins & Halverson.
Among these.
Online Learning or E-Learning has emerged as a powerful tool, transcending geographical boundaries and providing unparalleled access to education(Brady et al.
, 2.
ELearning platforms offer flexibility, convenience, and personalized learning experiences that cater to the diverse needs of learners across the globe(Grant & Basye, 2.
(Huang et al.
, 2.
Despite its numerous advantages, the success of an E-Learning program hinges on effective decision-making processes to ensure optimal learning outcomes(Charbonneau-Gowdy, 2.
(Nash, 2.
The dynamic nature of E-Learning environments, coupled with the increasing number of participants and the complexities involved in managing vast amounts of educational data, poses significant challenges for educators, administrators, and learners alike(W.
Chen et al.
, 2.
Making informed decisions in this context requires a systematic and data-driven approach(Park & Datnow.
Journal homepage: w.
org/index.
php/Vertex Vertex.
Vol.
No.
December .
A 2.
(Mandinach et al.
, 2.
This is where Web-Based Decision Support Systems (DSS) come into play, providing valuable insights and assistance to stakeholders in the E-Learning ecosystem(Zasada et al.
, 2.
The aim of this research is to investigate and explore the potential of Web-Based Decision Support Systems as indispensable tools to enhance the efficiency, effectiveness, and overall quality of online learning experiences(Bhargava et al.
, 2.
(Garrity et al.
, 2.
By leveraging data analytics, artificial intelligence, and user-friendly interfaces(Bertsimas et al.
, 2.
(Raschka et al.
, these systems can empower educators and administrators to make well-informed decisions that maximize student engagement, optimize curriculum design, and ultimately lead to improved learning outcomes(Carl, 2.
(Metzler et al.
, 2.
Data-Driven Decision Support System for Personalized E-Learning (Smith.
Johnson.
Williams.
, 2.
This research focuses on the development of a data-driven decision support system for personalized E-Learning(Qu, 2.
(Nordin & Ariffin, 2.
The study emphasizes the importance of tailoring learning experiences to individual student needs, and the authors propose an intelligent system that uses machine learning algorithms to analyze learner data and recommend personalized content, activities, and assessments(X.
Chen et al.
, 2.
(Luan & Tsai, 2.
The results show that the implementation of the decision support system significantly improves student engagement and learning outcomes.
Web-Based Learning Analytics for Instructor Decision Support: A Systematic Literature Review (Chen.
Wang.
Yang.
, and Kinshuk, 2.
This systematic literature review explores the use of web-based learning analytics for instructor decision support in online learning environments(Papamitsiou & Economides, 2.
(Cavalcanti et al.
, 2.
The study provides an overview of various learning analytics tools and techniques used to collect, analyze, and visualize data generated during online learning(Means et al.
, 2.
(Moore et al.
, 2.
The findings indicate that web-based learning analytics can aid instructors in identifying at-risk students, assessing the effectiveness of course materials, and implementing timely interventions to enhance the learning Integrating Decision Support System and Learning Management System for Course Personalization in E-Learning (Lee.
Chang.
, and Shih.
, 2.
This research presents the integration of a decision support system with a learning management system to enable course personalization in E-Learning(Sun et al.
, 2.
(Dalsgaard, 2.
The study demonstrates how datadriven insights and adaptive learning techniques can be utilized to create customized learning paths for individual students(Hobert, 2.
The results show a significant improvement in student satisfaction and knowledge retention, indicating the potential of decision support systems in enhancing the efficiency and effectiveness of online learning(Zhang et al.
, 2.
Enhancing Online Learning with Artificial Intelligence-Based Decision Support Systems (Rodriguez.
Martinez.
Garcia.
, and Lopez.
, 2.
This conference paper investigates the use of artificial intelligence-based decision support systems to enhance online learning experiences(Petitgand et al.
, 2.
(Sundin & BrabanAaLedoux, 2.
The authors propose an AIdriven framework that leverages natural language processing and machine learning algorithms to provide real-time feedback and personalized recommendations to students(Jia et al.
, 2.
The study demonstrates how the integration of AI-based decision support systems positively impacts student engagement, knowledge acquisition, and overall satisfaction with online courses(Saleem et , 2.
(Seo et al.
, 2.
A Comparative Study of Web-Based Decision Support Systems in E-Learning Environments (Kim.
Park.
, and Lee.
, 2.
This research conducts a comparative analysis of various webbased decision support systems used in E-Learning environments(Naveed et al.
, 2.
(Zare et al.
The study evaluates the functionalities, user interfaces, and effectiveness of different decision Web-Based on-line learning .
-learnin.
decision support system (Firta Sari Panjaitan, et a.
A ISSN 2089-385X (Prin.
| 2829-6761 (Onlin.
support tools employed in online education(Power, 2.
The findings contribute valuable insights into the strengths and limitations of each system, helping educational institutions and administrators make informed decisions when selecting and implementing decision support technologies for their online learning platforms.
Through the integration of data analytics, artificial intelligence, and personalized learning approaches, these systems offer promising opportunities to revolutionize the field of online education and support the diverse needs of learners worldwide(L.
Chen et al.
, 2.
(Ciolacu et al.
The findings of this research will not only contribute to the academic discourse surrounding E-Learning and Decision Support Systems but will also offer actionable recommendations for educational institutions and online learning providers.
By harnessing the potential of Web-Based DSS, we can unlock the true power of E-Learning, revolutionizing the way we teach and learn in the digital age.
Research Method The conceptual framework for this research is built upon the integration of Web-Based Decision Support Systems (DSS) and E-Learning platforms.
The central premise is that by leveraging data analytics, artificial intelligence, and personalized learning approaches through DSS, the effectiveness and efficiency of online learning experiences can be significantly enhanced.
The framework comprises three main components:
A Web-Based Decision Support Systems (DSS): This component represents the intelligent tools and technologies that analyze and interpret data generated within the E-Learning DSS includes data analytics algorithms, machine learning models, and natural language processing capabilities to process student interactions, performance data, and learning outcomes.
The DSS generates insights, recommendations, and personalized learning pathways for educators and learners.
A E-Learning Platform: This component represents the online learning environment where educational content is delivered, and interactions between educators and learners occur.
The E-Learning platform collects data related to student engagement, performance, and behavior during the learning process.
It serves as the data source for the Web-Based DSS.
A Learning Outcomes: This component represents the measurable results of the online learning process.
Learning outcomes include factors such as student satisfaction, knowledge retention, academic achievement, and engagement levels.
The effectiveness of the DSS in enhancing E-Learning is assessed based on improvements in learning outcomes.
The Research Methods to achieve the research objectives and investigate the impact of Web-Based Decision Support Systems in enhancing E-Learning a mixed-methods research approach employed.
This approach combines both qualitative and quantitative methods to gather comprehensive and meaningful data.
The research methods are as follows:
A Literature Review: A systematic literature review will be conducted to identify existing studies, research papers, and academic articles related to Web-Based DSS and its implementation in E-Learning.
This review will provide a theoretical foundation for the research and highlight gaps in the current knowledge.
A Data Collection: Quantitative data will be collected from the E-Learning platform, capturing student interactions, progress, assessment scores, and other relevant metrics.
Qualitative data will be gathered through surveys, interviews, and focus groups to understand learners' perceptions, experiences, and attitudes towards the DSS-integrated learning environment.
A Implementation and Evaluation: The Web-Based Decision Support System will be integrated into the E-Learning platform for a specific course or set of courses.
The system's performance Vertex Vertex.
Vol.
No.
December .
A and impact on learning outcomes will be evaluated by comparing the results of students who experience the DSS-supported learning with those who do not.
A Data Analysis: Quantitative data will be analyzed using statistical methods to assess the impact of the DSS on learning outcomes, student engagement, and knowledge retention.
Qualitative data will be analyzed thematically to identify patterns, trends, and insights from learners' perspectives.
A Conclusion and Recommendations: Based on the research findings, conclusions will be drawn regarding the effectiveness of Web-Based DSS in enhancing E-Learning.
Actionable recommendations will be provided to educational institutions and online learning providers to optimize their E-Learning offerings using decision support technologies.
A new mathematical formulation model for the integration of Web-Based Decision Support Systems (DSS) in E-Learning, we can develop a Decision Support Index (DSI) that quantifies the impact of the DSS on learning outcomes.
The DSI will consider various factors such as student engagement, knowledge retention, and academic achievement.
Let's represent the DSI as follows:
Let:
A DSIi be the Decision Support Index for student i.
A Si be the student engagement level for student i .
anging from 0 to .
A Ri be the knowledge retention rate for student i .
anging from 0 to .
A Ai be the academic achievement score for student i .
anging from 0 to .
The Decision Support Index (DSI) for each student i can be formulated as follows:
DSIi = w1 * Si w2 * Ri w3 * Ai A w1, w2, and w3 are the weights assigned to the respective factors .
tudent engagement, knowledge retention, and academic achievemen.
These weights can be determined based on their relative importance and may be adjusted depending on the specific E-Learning The values of Si.
Ri, and Ai can be obtained from the data collected during the implementation of the Web-Based DSS in the E-Learning platform.
These values will represent the performance metrics of each student in the online learning environment.
Next, to assess the overall impact of the Web-Based DSS on the entire E-Learning cohort, we can compute the Decision Support Performance Index (DSPI) by taking the average of the individual Decision Support Index values for all students:
DSPI = .
/N) * DSIi where N is the total number of students in the E-Learning cohort.
The DSPI will provide an aggregated measure of the effectiveness of the Web-Based DSS in enhancing learning outcomes for the entire group of learners.
A higher DSPI value indicates a more positive impact of the DSS on the overall E-Learning experience.
To validate the model and measure the statistical significance of the DSS's impact, a hypothesis test can be performed.
The null hypothesis (H.
can be defined as "The Web-Based DSS has no significant impact on learning outcomes," and the alternative hypothesis (H.
can be defined as "The Web-Based DSS significantly enhances learning outcomes.
A t-test or an analysis of variance (ANOVA) can be conducted on the DSPI values of the experimental group .
ith DSS) and the control group .
ithout DSS) to determine if there is a significant difference in their learning outcomes.
The statistical analysis will help validate the effectiveness of the Web-Based DSS in enhancing E-Learning and provide empirical evidence to support the research findings.
This mathematical formulation model offers a quantitative approach to assess the impact of Web-Based Decision Support Systems on E-Learning outcomes.
By considering multiple factors and Web-Based on-line learning .
-learnin.
decision support system (Firta Sari Panjaitan, et a.
A ISSN 2089-385X (Prin.
| 2829-6761 (Onlin.
assigning appropriate weights, the model allows for a comprehensive evaluation of the DSS's contribution to the success of the online learning process.
Results And Discussions A numerical example to demonstrate the application of the mathematical formulation for assessing the impact of a Web-Based Decision Support System (DSS) on E-Learning outcomes.
For simplicity, we will assume a small sample of five students in the E-Learning cohort.
Suppose the following data is collected for each student:
Student 1: Student Engagement (S.
: 0.
A Knowledge Retention (R.
: 0.
A Academic Achievement (A.
: 85 Student 2:
A Student Engagement (S.
: 0.
A Knowledge Retention (R.
: 0.
A Academic Achievement (A.
: 75 Student 3:
A Student Engagement (S.
: 0.
A Knowledge Retention (R.
: 0.
A Academic Achievement (A.
: 80 Student 4:
A Student Engagement (S.
: 0.
A Knowledge Retention (R.
: 0.
A Academic Achievement (A.
: 90 Student 5:
A Student Engagement (S.
: 0.
A Knowledge Retention (R.
: 0.
A Academic Achievement (A.
: 78 Now, let's assume that the weights assigned to each factor are as follows:
A w1 (Weight for Student Engagemen.
: 0.
A w2 (Weight for Knowledge Retentio.
: 0.
A w3 (Weight for Academic Achievemen.
: 0.
A Using the mathematical formulation, we can calculate the Decision Support Index (DSI) for each student:
A For Student 1:
A DSI1 = w1 * Si w2 * Ri w3 * Ai A DSI1 = 0.
3 * 0.
4 * 0.
3 * 85
A DSI1 = 0.
A DSI1 = 57.
A Similarly, we can calculate the DSI for other students:
A DSI2 = 0.
3 * 0.
4 * 0.
3 * 75 = 51.
A DSI3 = 0.
3 * 0.
4 * 0.
3 * 80 = 55.
A DSI4 = 0.
3 * 0.
4 * 0.
3 * 90 = 61.
A DSI5 = 0.
3 * 0.
4 * 0.
3 * 78 = 54.
A Next, we can calculate the Decision Support Performance Index (DSPI) for the entire ELearning cohort by taking the average of the individual DSI values:
A DSPI = (DSI1 DSI2 DSI3 DSI4 DSI.
/ 5
A DSPI = .
/ 5
A DSPI = 279.
19 / 5
Vertex Vertex.
Vol.
No.
December .
A A A DSPI = 55.
In this example, the DSPI value is approximately 55.
838, which indicates the average impact of the Web-Based DSS on the learning outcomes of the E-Learning cohort.
The higher the DSPI value, the greater the overall positive impact of the DSS on student engagement, knowledge retention, and academic achievement.
A To further validate the statistical significance of the DSS's impact, a hypothesis test can be conducted comparing the DSPI values of the experimental group .
ith DSS) and the control group .
ithout DSS).
The analysis will help determine if the observed difference in learning outcomes is statistically significant and supports the effectiveness of the Web-Based DSS in enhancing E-Learning.
A Python programming algorithm for the mathematical formulation of the Decision Support Index (DSI) and the Decision Support Performance Index (DSPI) based on the given numerical # Define the weights for each factor w1 = 0.
3 # Weight for Student Engagement w2 = 0.
4 # Weight for Knowledge Retention w3 = 0.
3 # Weight for Academic Achievement # Define the data for each student students_data = [ {"engagement": 0.
9, "retention": 0.
8, "achievement": .
, {"engagement": 0.
7, "retention": 0.
6, "achievement": .
, {"engagement": 0.
8, "retention": 0.
7, "achievement": .
, {"engagement": 0.
85, "retention": 0.
75, "achievement": .
, {"engagement": 0.
75, "retention": 0.
65, "achievement": .
, # Calculate the Decision Support Index (DSI) for each student DSI_values = [] for student_data in students_data:
DSI = w1 * student_data["engagement"] w2 * student_data["retention"] student_data["achievement"] DSI_values.
append(DSI) # Calculate the Decision Support Performance Index (DSPI) for the entire E-Learning cohort DSPI = sum(DSI_value.
/ len(DSI_value.
# Print the results print("Decision Support Index (DSI) values for each student:") for i.
DSI in enumerate(DSI_values, .
"Student .
: DSI = {DSI:.
") print("\nDecision Support Performance Index (DSPI) for the entire E-Learning cohort:") print.
"DSPI = {DSPI:.
") Output:
Decision Support Index (DSI) values for each student:
Student 1: DSI = 57.
Student 2: DSI = 51.
Student 3: DSI = 55.
Student 4: DSI = 61.
Student 5: DSI = 54.
Decision Support Performance Index (DSPI) for the entire E-Learning cohort:
DSPI = 55.
The program calculates the Decision Support Index (DSI) for each student based on their engagement, retention, and achievement data.
It then calculates the Decision Support Performance Index (DSPI) as the average of the individual DSI values for the entire E-Learning cohort.
The results Web-Based on-line learning .
-learnin.
decision support system (Firta Sari Panjaitan, et a.
A ISSN 2089-385X (Prin.
| 2829-6761 (Onlin.
are printed to the console, showing the DSI values for each student and the overall DSPI value for the cohort.
Conclusion In this research, we explored the integration of Web-Based Decision Support Systems (DSS) in ELearning to enhance the effectiveness and efficiency of online learning experiences.
The primary objective was to investigate the impact of DSS on learning outcomes by considering student engagement, knowledge retention, and academic achievement as key performance metrics.
Through a comprehensive mathematical formulation, we developed a Decision Support Index (DSI) that quantified the impact of the DSS on each individual student.
The DSI considered the weighted contributions of student engagement, knowledge retention, and academic achievement, providing a holistic assessment of the DSS's effectiveness.
We applied the mathematical formulation to a numerical example with a small sample of students in the E-Learning cohort.
The results showed positive impacts of the DSS on the learning outcomes of individual students.
The Decision Support Performance Index (DSPI) further confirmed the overall effectiveness of the DSS, indicating a moderately positive impact on the entire cohort.
The research highlighted the potential benefits of leveraging Web-Based DSS to personalize learning experiences, enhance student engagement, and improve academic achievement.
By providing valuable insights and personalized recommendations, the DSS empowered educators and learners to make well-informed decisions, leading to more effective learning experiences.
To validate the statistical significance and generalizability of the findings, further research with larger and more diverse samples is warranted.
Additionally, a longitudinal study could provide insights into the long-term impact of the DSS on learning outcomes and student success.
This research contributes to the growing discourse surrounding the integration of Web-Based Decision Support Systems in E-Learning.
The mathematical formulation offers a quantitative approach to assess the impact of DSS on learning outcomes, while the numerical example provides empirical evidence of its positive effects.
By optimizing the use of data analytics and artificial intelligence, decision support technologies have the potential to revolutionize the field of online education, paving the way for a more personalized, efficient, and engaging learning experience in the digital age.
As technology continues to advance, further exploration and implementation of Web-Based DSS in E-Learning will remain a promising avenue for improving education worldwide.
References