Learner classification based on interaction data in E-learning environments: the ELECTRE TRI method

Şahi̇n, Muhittin; Ulucan, Aydın

doi:10.1007/s10639-020-10358-2

Cited by 9 publications

(5 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The findings in this study support the previous research in this area which links LMS records to learner behavior such as LS and CT. The method validates the ideas of Şahin et al. (2020) who classified the learners based on the interaction data gathered from an LMS.…”

Section: Resultssupporting

confidence: 59%

“…Several studies investigating learner behavior in LMS have been carried out. More recently, Şahin et al (2020) utilized the ELECTRE TRI method to classify the learners based on the interaction data gathered from LMS and concluded that there was a correlation between the categories investigated and the real-life classification. In another related study, Ferreira et al (2019) used machine learning algorithms to analyze data from the Moodle LMS and characterized the learning profiles of students according to the Felder-Silverman Learning Style Model (FSLSM).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Identifying learning styles and cognitive traits in a learning management system

Lwande

Muchemi

Oboko

2021

Heliyon

View full text Add to dashboard Cite

Investigating learner behavior is an increasingly important research topic in online learning. Learning styles and cognitive traits have been the subjects of research in this area. Although learning institutions use Learning Management Systems such as Moodle, Claroline, and Blackboard to facilitate teaching, the platforms do not have features for analyzing data and identifying behavior such as learning styles and cognitive traits. Instead, they only produce certain statistical reports from the daily access records. Even though complex models have been proposed in the literature, most studies are based on a single behavior such as learning styles or cognitive traits but not both. Only a few have investigated a combination of cognition-based theories such as working memory capacity and psychology-based ones such as learning styles. Thus, this study sought to answer the research question of whether it was possible to establish a methodology for the estimation of learning styles and cognitive traits from a learning management system. The study combined the Felder-Silverman Learning Style Model and Cognitive Trait Model as theoretical frameworks to identify behavior in a Learning Management System. This study designed a model for extracting records from Learning Management Systems access records to estimate learning style and cognitive traits. From this, a prototype was developed to estimate the learning style and cognitive traits for each student. The model was evaluated by administering manual tools to students in a classroom environment then comparing the results gathered against those estimated by the model. The results analyzed using Kappa statistics demonstrated the interrater reliability results were moderately in agreement. Taken together, these results suggest that it is possible to estimate the learning styles and cognitive traits of a learner in a Learning Management System. The information generated by the model can be used by tutors to provide a conducive online learning environment where learners with similar behavior ask each other for help. This can reduce the teaching load for online tutors because learners themselves act as a teaching resource. Information on learning styles and cognitive styles can also facilitate online group formation by isolating the individual factors that contribute to team success.

show abstract

Section: Resultssupporting

confidence: 59%

Section: Introductionmentioning

confidence: 99%

Identifying learning styles and cognitive traits in a learning management system

Lwande

Muchemi

Oboko

2021

Heliyon

View full text Add to dashboard Cite

show abstract

“…Motivation is seen as a mental impulse that drives and directs the attitudes and behavior of a learner [27] . Therefore, online learners' interaction profiles differ according to their learning motivation [6] . In other words, different levels of motivation affect the patterns of interaction in the online learning environment.…”

Section: Discussionmentioning

confidence: 99%

“…Success in online learning demands adjustments in attitudes towards technology use, time management and student interaction skills [5] . Studies indicate that a learner's motivation and learning strategy significantly affect their online engagement [6,7] . Warner, Christie and Choy (1998) first introduced the concept of online learning readiness, focusing on course modality preference, computer communication competence and self-directed learning ability [8] .…”

Section: Introductionmentioning

confidence: 99%

Learners’ Determinants of Learning Environment Preferences: Online vs. Blended

Shatla,

Hegazy,

Abd Elbary

2024

Journal of Medical Education and Practice

View full text Add to dashboard Cite

BackgroundIn recent years, the education sector has witnessed a significant shift towards online and blended learning, further accelerated by global events like the COVID-19 pandemic. Understanding what influences learners' preferences for these modes is vital for educational institutions adapting to changing pedagogical needs. This study focuses on exploring the characteristics that shape medical students' choices between online-only and blended learning. ObjectivesThis research aims to investigate learner traits impacting their selection of learning environments, specifically emphasizing the preference for online only or blended learning. MethodsWe conducted a cross-sectional survey among medical students at the end of the 2020/2021 academic year's first semester. The survey covered demographics, learning environment preferences, the Scale of University Students' Readiness for E-Learning, and the Motivation and Learning Strategies Scale. We employed statistical analyses, including t-tests, Eta coefficient tests (η) for correlation, and Eta squared tests (η²) for effect size. ResultsOut of 665 respondents, the majority (63.2 %) favored blended learning. Interestingly, students preferring online-only learning scored significantly higher in e-learning readiness, motivation, and cognitive learning strategies. A strong correlation and substantial effect size linked the preferred environment to e-learning readiness, especially motivation for e-learning (η = 0.834, η² = 0.695), and overall motivation for learning. However, the influence of cognitive learning strategies showed weaker correlation and a smaller effect size. DiscussionThis study highlights the pivotal role of e-learning readiness, particularly motivation for e-learning and general motivation for learning, in shaping students' preferences for learning environments. In contrast, cognitive learning strategies exert less impact on these preferences.To prepare students for evolving educational landscapes, prioritizing e-learning skills and motivation enhancement is recommended, especially given the potential for future disruptions to traditional learning methods..

show abstract

“…An app involving 3D simulation and another app that displays animated procedures and only some interactive parts (eg, 3D manipulative or drawing tool) would still be considered dynamic interactive apps. It was beyond the scope of this initial investigation to study the full scope of virtuality and interaction of these tools, as these spectra are still being defined [ 48 , 61 ].…”

Section: Discussionmentioning

confidence: 99%

Digital Learning in Speech-Language Pathology, Phoniatrics, and Otolaryngology: Interdisciplinary and Exploratory Analysis of Content, Organizing Structures, and Formats

Lin

Neuschaefer‐Rube

2021

JMIR Med Educ

View full text Add to dashboard Cite

Background The digital revolution is rapidly transforming health care and clinical teaching and learning. Relative to other medical fields, the interdisciplinary fields of speech-language pathology (SLP), phoniatrics, and otolaryngology have been slower to take up digital tools for therapeutic, teaching, and learning purposes—a process that was recently expedited by the COVID-19 pandemic. Although many current teaching and learning tools have restricted or institution-only access, there are many openly accessible tools that have gone largely unexplored. To find, use, and evaluate such resources, it is important to be familiar with the structures, concepts, and formats of existing digital tools. Objective This descriptive study aims to investigate digital learning tools and resources in SLP, phoniatrics, and otolaryngology. Differences in content, learning goals, and digital formats between academic-level learners and clinical-professional learners are explored. Methods A systematic search of generic and academic search engines (eg, Google and PubMed); the App Store; Google Play Store; and websites of established SLP, phoniatrics, and otolaryngology organizations was conducted. By using specific search terms and detailed inclusion and exclusion criteria, relevant digital resources were identified. These were organized and analyzed according to learner groups, content matter, learning goals and architectures, and digital formats. Results Within- and between-learner group differences among 125 identified tools were investigated. In terms of content, the largest proportion of tools for academic-level learners pertained to anatomy and physiology (60/214, 28%), and that for clinical-professional learners pertained to diagnostic evaluation (47/185, 25.4%). Between groups, the largest differences were observed for anatomy and physiology (academic-level learners: 60/86, 70%; clinical-professional learners: 26/86, 30%) and professional issues (8/28, 29% vs 20/28, 71%). With regard to learning goals, most tools for academic-level learners targeted the performance of procedural skills (50/98, 51%), and those for clinical-professional learners targeted receptive information acquisition (44/62, 71%). Academic-level learners had more tools for supporting higher-level learning goals than clinical-professional learners, specifically tools for performing procedural skills (50/66, 76% vs 16/66, 24%) and strategic skills (8/10, 80% vs 2/10, 20%). Visual formats (eg, pictures or diagrams) were dominant across both learner groups. The greatest between-group differences were observed for interactive formats (45/66, 68% vs 21/66, 32%). Conclusions This investigation provides initial insights into openly accessible tools across SLP, phoniatrics, and otolaryngology and their organizing structures. Digital tools in these fields addressed diverse content, although the tools for academic-level learners were greater in number, targeted higher-level learning goals, and had more interactive formats than those for clinical-professional learners. The crucial next steps include investigating the actual use of such tools in practice and students’ and professionals’ attitudes to better improve upon such tools and incorporate them into current and future learning milieus.

show abstract

Learner classification based on interaction data in E-learning environments: the ELECTRE TRI method

Cited by 9 publications

References 24 publications

Identifying learning styles and cognitive traits in a learning management system

Identifying learning styles and cognitive traits in a learning management system

Learners’ Determinants of Learning Environment Preferences: Online vs. Blended

Digital Learning in Speech-Language Pathology, Phoniatrics, and Otolaryngology: Interdisciplinary and Exploratory Analysis of Content, Organizing Structures, and Formats

Contact Info

Product

Resources

About