Learning style model detection based on prior knowledge in e-learning system

Hasibuan, Muhammad Said; Nugroho, Lukito Edi; Santosa, Insap

doi:10.1109/iac.2017.8280537

Cited by 5 publications

(6 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Priority of prior knowledge generation process uses only three methods. The three methods are Brainstorming, Know-Want To Know-Learned (KWL) Chart and Cognitive Map (Thi Thanh Dieu, 2015;Gouveia, 1974;Hasibuan et al, 2017). The constraints faced in previous prior knowledge generation process are that it is less effective, and very subjective because there is interaction and the process takes a long time.…”

Section: Methodology Researchmentioning

confidence: 99%

“…The learning style detection process can be divided into conventional and automatic forms (Hasibuan et al, 2017 (Kolb, 1984;Honey & Mumford, 1992;Fleming & Mills, 1992;Felder & Silverman, 1988).…”

Section: Learning Style Model Detectionmentioning

confidence: 99%

“…The data-driven approach of learning style detection uses an artificial intelligence method to represent the questionnaire. Both approaches are based on the interaction of learners with the system, such as interaction with teaching materials, following discussion forums, online quizzes and online chats (Rita, Graf & Kinshuk, 2002;Nam, 2013;Hamtini, 2015;Hasibuan, Nugroho & Santosa, 2017). The approach can be classified as an external approach because the process involves learner interaction with the system.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Model detecting learning styles with artificial neural network

Hasibuan¹,

Nugroho²,

Santosa³

2019

J. Technol. Sci. Educ.

View full text Add to dashboard Cite

Currently the detection of learning styles from the external aspect has not produced optimal results. This research tries to solve the problem by using an internal approach. The internal approach is one that derives from the personality of the learner. One of the personality traits that each learner possesses is prior knowledge. This research starts with the prior knowledge generation process using the Latent Semantic Indexing (LSI) method. LSI is a technique using Singular Value Decomposition (SVD) to find meaning in a sentence. LSI works to generate the prior knowledge of each learner. After the prior knowledge is raised, then one can predict learning style using the artificial neural network (ANN) method. The results of this study are more accurate than the results of detection conducted with an external approach.

show abstract

Section: Methodology Researchmentioning

confidence: 99%

Section: Learning Style Model Detectionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Model detecting learning styles with artificial neural network

Hasibuan¹,

Nugroho²,

Santosa³

2019

J. Technol. Sci. Educ.

View full text Add to dashboard Cite

show abstract

“…Another research by [32] succeeded in proposing a model for reviving prior knowledge from test questions using the Latent Semantic method to overcome the previous method (brainstorming, KWL and cognitive map) that were less effective and dynamic. [33] Further developed and evaluated an internal approach, this approach uses learner's personality trait (prior knowledge) to detecting learning style [34]. The research employed LSI techniques that generate prior knowledge of individuals using single value decomposition then predicts VARK learning style using ANN.…”

Section: Related Workmentioning

confidence: 99%

Performance Comparison of Convolutional and Multiclass Neural Network for Learning Style Detection from Facial Images

Gambo¹,

Wajiga²,

Shuib³

et al. 2018

ICST Transactions on Scalable Information Systems

View full text Add to dashboard Cite

Improving the accuracy of learning style detection models is a primary concern in the area of automatic detection of learning style, which can be achieved either through, attribute/feature selection or classification algorithm. However, the role of facial expression in improving accuracy has not been fully explored in the research domain. On the other hand, deep learning solutions have become a new approach for solving complex problems using Deep Neural networks (DNNs); these DNNs have deep architectures that are capable of decomposing problems into multiple processing layers, enabling and devising multiple mapping of complex problems functions. In this paper, we investigate and compare the performance of Convolutional Neural Network (CNN) and MultiClass Neural Network (MCNN) for classification of learners into VARK learning-style dimensions (i.e Visual, Aural, Reading Kinaesthetic, including Neutral class) based on facial images. The performances of the two networks were evaluated and compared using square mean error MSE for training and accuracy metric for testing. The results show that MCNN offers better and robust classification performance of VARK learning style based on facial images. Finally, this paper has demonstrated a potential of a new method for automatic classification of VARK LS based on Facial Expressions (FEs). Based on the experimental results of the models, this approach can benefit both researchers and users of adaptive e-learning systems to uncover the potential of using FEs as identifier learning styles for recommendations and personalization of learning environments.

show abstract

“…Previous researches have been done to improve the learners' motivation, such as using a learning style detection approach [3] [4][5] [6]. The results showed that the learners' motivation learning style was raised.…”

Section: Introductionmentioning

confidence: 99%

Learning Motivation increased due to a Relaxed Assessment in a Competitivee-Learning Environment

Hasibuan

Purbo

2018

EECSI

View full text Add to dashboard Cite

In this work, e-learning is used to increase learners 'motivation and competence in addition to learning complementary environment. This work is based on of the 7years of hybrid e-learning classes on Operating System, Computer Network, Network Security, Network Management subjects at 3 Indonesian universities, namely, Surya University, STKIP Surya, and IBI Darmajaya. Most of STKIP Surya's students are from Papua and need more attention and motivation than others. Relaxed assessment processes are performed on each module in addition to mid term and final exams. On average, there are 12-18 modules in each subject matter. To motivate the learners, they may perform as many exams as ones' wish to attained the highest possible mark within the semester on all exams and quizzes. Relaxed assessment processes to attained maximum grades seems to increase the learners' motivation as some learners' retrying in exceeding 50 times for the 100 questions final shown in the Level of Competency (LoC) measurement. In addition, to anticipate, any cheating, eliminate remedial and cost savings, all exams are done on moodle via web. Such method of a whole semester relaxed assessment equipped with about 2000-6000 questions bank per subject and is for the first time performed in Indonesia. This study is also found an increase in the majority of learner's understanding on the subject is very good without remedial. Thus, e-learning seems not only complement learning processes but also able to motivate and to improve the competence of learners as well creating healthy competitive environment among learners.

show abstract

Learning style model detection based on prior knowledge in e-learning system

Cited by 5 publications

References 8 publications

Model detecting learning styles with artificial neural network

Model detecting learning styles with artificial neural network

Performance Comparison of Convolutional and Multiclass Neural Network for Learning Style Detection from Facial Images

Learning Motivation increased due to a Relaxed Assessment in a Competitivee-Learning Environment

Contact Info

Product

Resources

About