Learning Analytics Using Social Network Analysis and Bayesian Network Analysis in Sustainable Computer-Based Formative Assessment System

Choi, Younyoung; Cho, Young Il

doi:10.3390/su12197950

Cited by 10 publications

(4 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Yet, there are many learning elements that differ between online and offline learning environments [37]. For example, learning processing relies on instructional design in a multimedia environment more than in a face-to-face classroom learning environment [37][38][39]. Moreover, self-regulated learning ability is more required to improve the academic performance in online learning than offline learning environments [40].…”

Section: Measuring Cognitive Loadmentioning

confidence: 99%

Psychometric Properties for Multidimensional Cognitive Load Scale in an E-Learning Environment

Choi

Lee

2022

IJERPH

Self Cite

View full text Add to dashboard Cite

(1) Background: A learner’s cognitive load in a learning system should be effectively addressed to provide optimal learning processing because the cognitive load explains individual learning differences. However, little empirical research has been conducted into the validation of a cognitive load measurement tool (cognitive load scale, i.e., CLS) suited to online learning systems within higher education. The purpose of this study was to evaluate the psychometric properties of the CLS in an online learning system within higher education through the framework suggested by the Standards for Educational and Psychological Testing. (2) Methods: Data from 800 learners were collected from a cyber-university in South Korea. The age of students ranged from 20 to 64. The CLS was developed, including three components: extraneous cognitive load, intrinsic cognitive load, and germane cognitive load. Then, psychometric properties of the CLS were evaluated including reliability and validity. Evidence relating to content validity, construct validity, and criterion validity were collected. The response pattern of each item was evaluated on the basis of item response theory (IRT). Cronbach’s α was computed for reliability. (3) Results: The CLS presented high internal consistency. A three-factor model with extraneous cognitive load, intrinsic cognitive load, and germane cognitive load was suggested by exploratory and confirmatory factor analysis. This three-factor model is consistent with the previous research into the cognitive load in an offline learning environment. Higher levels of the extraneous cognitive load and intrinsic cognitive load were related to lower levels of academic achievement in an online learning environment, but the germane cognitive load was not significantly positively associated with midterm exam scores, though it was significantly related to the final exam scores. IRT analysis showed that the item-fit statistics for all items were acceptable. Lastly, the measurement invariance was examined through differential item functioning analysis (DIF), with the results suggesting that the items did not contain measurement variance in terms of gender. (4) Conclusions: This validation study of the CLS in an online learning environment within higher education assesses psychometric properties and suggests that the CLS is valid and reliable with a three-factor model. There is a need for an evaluation tool to take into account the cognitive load among learners in online learning system because the characteristics of learners within higher education were varied. This CLS will help instructional/curriculum designers and educational instructors to provide more effective instructions and identify individual learning differences in an online learning environment within higher education.

show abstract

Section: Measuring Cognitive Loadmentioning

confidence: 99%

Psychometric Properties for Multidimensional Cognitive Load Scale in an E-Learning Environment

Choi

Lee

2022

IJERPH

Self Cite

View full text Add to dashboard Cite

show abstract

“…The BN has been proposed for modeling student performance in educational settings, to estimate and diagnose proficiency [41][42][43].…”

Section: Bayesian Network Analysis For Diagnostic Information About the Cognitive Loadmentioning

confidence: 99%

Learning Analytics for Diagnosing Cognitive Load in E-Learning Using Bayesian Network Analysis

Choi¹,

Kim²

2021

Sustainability

Self Cite

View full text Add to dashboard Cite

A learner’s cognitive load is highly associated with their academic achievement within learning systems. Diagnostic information about a learner’s cognitive load is useful for achieving optimal learning, by enabling the learner to manage and control their cognitive load in the e-learning environment. However, little empirical research has been conducted to obtain diagnostic information about the cognitive load in e-learning systems. The purpose of this study was to analyze a personalized diagnostic evaluation for a learner’s cognitive load in an e-learning system, using the Bayesian Network (BN) as a learning analytic method. Data from 700 learners were collected from Cyber University. A learner’s cognitive load level was measured in terms of three components: extraneous cognitive load, intrinsic cognitive load, and germane cognitive load. The BN was built by representing the relationship among the extraneous cognitive load, intrinsic cognitive load, germane cognitive load, and academic achievement. The conditional and marginal probabilities in the BN were estimated. This study found that the BN provided diagnostic information about a learner’s level of cognitive load in the e-learning system. In addition, the BN predicted the learner’s academic achievement in terms of their different cognitive load patterns. This study’s results imply that diagnostic information related to cognitive load helps learners to improve academic achievement by managing and controlling their cognitive loads in the e-learning environment. In addition, instructional designers are able to offer more appropriately customized instructional methods by considering learners’ cognitive loads in online learning.

show abstract

“…The framework provides a unifying semantic foundation in the form of a set of controlled vocabularies for describing competencies and their related details within the contexts of technology-enhanced competencybased learning and training. Choi and Cho (2020) introduced a framework of a learning analytic method including assessment design, data mining method using social network analysis, and analytic method using a Bayesian network to analyse the learners' performances based on a computational psychometric framework. The scalable competence assessment through a learning analytics approach (SCALA) project, is an analytics system that tracks how the user interacts with resources and how students and teachers interact among themselves to support competency assessment (Rayón et al, 2014).…”

Section: Semantic Learning Analytics For Modelling and Discovering Competenciesmentioning

confidence: 99%

Students’ competencies discovery and assessment using learning analytics and semantic web

Halimi

Seridi-Bouchelaghem²

2021

AJET

View full text Add to dashboard Cite

Traditional content-based assessment systems, which depend on the score as a key criterion for students’ evaluation, have proven to have many drawbacks, especially with the development of learning methods in recent years. Based on these developments, there is a need to adopt new assessment methods to assess the actual skills of students in the digital age. Therefore, the competency-based assessment approach is adopted in this paper to address the subject of students’ competency modelling and discovery in technology-enhanced learning systems. This method of assessment is perfectly suited to modern teaching trends. The authors proposed an approach of assessment semantic analytics to be used for discovering and assessing students’ competencies. This study notes that, all knowledge about students and their competencies has been modelled by semantic representations. Student’s models have been subjected to a set of learning analytics approaches to analyse data generated by students’ activities in order to discover their explicit and latent competencies hidden behind their activities. This experimental study indicates that the competency-based assessment approach is efficient and expected to show significant advantages in evaluating students’ competencies. Implications for practice or policy: Students become able to organise their gains, then integrate and employ them in solving life's problems. Educators get to know more about the extent to which the objectives of their educational process are achieved by evaluating the intellectual, cultural, knowledge, and skilful assets that the learners obtain. Educational policymakers can have a pedagogical and technical vision to move from the culture of content-based evaluations to a competency-based assessment.

show abstract

Learning Analytics Using Social Network Analysis and Bayesian Network Analysis in Sustainable Computer-Based Formative Assessment System

Cited by 10 publications

References 31 publications

Psychometric Properties for Multidimensional Cognitive Load Scale in an E-Learning Environment

Psychometric Properties for Multidimensional Cognitive Load Scale in an E-Learning Environment

Learning Analytics for Diagnosing Cognitive Load in E-Learning Using Bayesian Network Analysis

Students’ competencies discovery and assessment using learning analytics and semantic web

Contact Info

Product

Resources

About