Computational Intelligence Methods for Data Analysis and Mining of eLearning Activities

Dráždilová, Pavla; Obadi, Gamila; Slaninová, Kateřina; Al-Dubaee, Shawki A.; Martinovič, Jan; Snåšel, Václav

doi:10.1007/978-3-642-11224-9_9

Cited by 17 publications

(8 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…SPA may be used to analyse learners' navigation paths across a system (Campagni et al, 2012;Dráždilová et al, 2010). Some studies have focused on the potential uses of SPA (Munk & Drlik, 2011;Zhou, 2010), whereas some have looked into the design of the system or were based on repetitive sequential patterns (Wang et al, 2012;Wong et al, 2019), and others have analysed sequential interactions by labelling learners as successful or unsuccessful (Lin et al, 2017;Shih, 2018).…”

Section: Navigational Paths and Spamentioning

confidence: 99%

“…After the learners were clustered, the average factor loading for each cluster was calculated and presented as graphics. The primary purpose of this method was to identify the frequently used sequential item sets in a data set (Dráždilová et al, 2010). The sequential patterns that appear more often than others are determined based on support value or support ratio (Campagni et al, 2012;Dráždilová et al, 2010).…”

Section: Hierarchical Clustering and Spamentioning

confidence: 99%

See 1 more Smart Citation

Interrelated analysis of interaction, sequential patterns and academic achievement in online learning

Yıldırım

Usluel

2022

AJET

View full text Add to dashboard Cite

This study aimed to examine the behaviour of learners across a whole system and in various courses to reveal the interrelation between learners' system interaction, age, programme features and course design. We obtained data from the system logs of 1,634 learners enrolled in distance learning programmes. We performed hierarchical clustering analysis to describe system interactions; then, we carried out a sequential pattern analysis to examine navigational behaviours by clusters. The results showed that the system interactions (e.g., content, live lesson, assignment, exam, discussion) across the whole system differ by age and programme. The behaviour profiles of the learners changed when different course designs were presented. Learners who interacted more with any component (e.g., live lesson or content) according to their needs were more successful than those with limited interaction and assessment-oriented (those with limited interactions outside of the assignment). In an information and communication technology course, learners whose system interactions were sufficient to receive rewards were more likely to succeed. The sequential pattern analysis showed that the assessment-oriented cluster interacted with the assignment in the midterm weeks; the award-oriented cluster interacted with the content or completed their assignment and received an award. Consequently, it is difficult to determine or generalise the intervention unless the system, programme and course design features are standard. Implications for practice or policy: Course designers can use the assessment activities or motivation factors such as awards to increase students' system interactions. Course designers should not determine or generalise interventions unless the system, programme and course design are standard. Researchers should not only focus on data but also consider the contextual characteristics of data.

show abstract

Section: Navigational Paths and Spamentioning

confidence: 99%

Section: Hierarchical Clustering and Spamentioning

confidence: 99%

Interrelated analysis of interaction, sequential patterns and academic achievement in online learning

Yıldırım

Usluel

2022

AJET

View full text Add to dashboard Cite

show abstract

“…The cognitive state and learning content of learners can be changed with time and context. Various recommendation techniques were proposed to explore learners' preferences, knowledge and browsing histories for recommendation (Dráždilová et al, 2010;Lytras & Ordóñez de Pablos, 2011;Núñez-Valdéz et al, 2012). Convolutional Neural Network (CBCNN) was used to design content-based learning resource recommendation model (Shu et al, 2018), while it was indicated that using conventional recommendation methods had an important problem in e-learning recommendation systems (Kovanović, Joksimović, Gašević, Siemens & Hatala, 2015).…”

Section: Related Work E-learning Communitiesmentioning

confidence: 99%

Leveraging personality information to improve community recommendation in e‐learning platforms

Sun¹,

Geng²,

Cheng³

et al. 2020

Brit J Educational Tech

View full text Add to dashboard Cite

E‐learning platforms are becoming more and more important and they are gradually changing people’s learning ways. In the e‐learning platforms, users actively create and join their favorite communities to share their questions and ideas. With the increase of users of e‐learning platforms, the number of communities is increasing dramatically. In this context, it has become difficult for users to find learning communities that match their interests and preferences. Therefore, how to effectively recommend the learning community for users has become an urgent need. However, compared to learning item recommendation, there is relatively limited work on learning community recommendation, and the existing research on community recommendation often ignores the personality information. Personality is considered one of the primary factors that influence human behavior and social relationships, as it affects how people react and interact with others. Several studies have demonstrated that people with similar personality tend to have similar interests. Furthermore, homophily theory also states that social interactions between similar individuals occur at a higher rate than among dissimilar ones. Since interests and interactions are important driving forces for users to join the learning communities, personality has an important impact on users’ choices of communities. Therefore, this paper aims at shedding some light on the impact of personality information on the accuracy of community recommendations. Particularly, we propose three enhanced matrix factorization models based on the Big Five personality framework. To evaluate the effectiveness of our proposed models, we conducted extensive experiments on myPersonality datasets. The results prove that the personality information can improve the performance of the learning community recommendation model and alleviate the data sparsity problem.

show abstract

“…It is naturally related to distance learning, but nowadays it is commonly used to support face-to-face learning as well. Learning Management Systems (LMS) provides effective maintenance of particular courses and facilitate communication within the student community and between educators and students (Drazdilova et al, 2010).…”

Section: Introductionmentioning

confidence: 99%

Using High Performance Computing and Open Source Technologies for Solving Behaviour Analytics Problems in E-Learning

Zacs

Jansone

2015

SIE

View full text Add to dashboard Cite

In this paper the authors describe solution for solving various analytical problems in E-learning, Course Management Systems like Moodle by using HPC (High Performance Computing) and Apache Hadoop open source technologies in Liepaja University. The problem is that nowadays there are collecting huge amounts of analytics data from several gigabytes to petabytes, which is hard to store, process, analyse and visualize. This article reflects one of the solutions concerning distributed parallel processing of huge amounts of data across inexpensive, industry-standard servers that can store and process the data, can scale without limits and provides technological opportunities of reliable, scalable and distributed computing.

show abstract

Computational Intelligence Methods for Data Analysis and Mining of eLearning Activities

Cited by 17 publications

References 54 publications

Interrelated analysis of interaction, sequential patterns and academic achievement in online learning

Interrelated analysis of interaction, sequential patterns and academic achievement in online learning

Leveraging personality information to improve community recommendation in e‐learning platforms

Using High Performance Computing and Open Source Technologies for Solving Behaviour Analytics Problems in E-Learning

Contact Info

Product

Resources

About