Threshold Value in Automatic Learning Style Detection

Ahmad, Norazlina; Tasir, Zaidatun

doi:10.1016/j.sbspro.2013.10.244

Cited by 14 publications

(7 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Learning style is further broken down into learning style models and learning style modalities (Ahmad and Tasir, 2013). A theoretical coherence and a common framework for all learning style models are lacking (Klašnja-Milićević et al, 2016).…”

Section: Introductionmentioning

confidence: 99%

Classification of Visual and Non-visual Learners Using Electroencephalographic Alpha and Gamma Activities

Jawed

Amin

Malik³

et al. 2019

Front. Behav. Neurosci.

View full text Add to dashboard Cite

This study analyzes the learning styles of subjects based on their electroencephalo-graphy (EEG) signals. The goal is to identify how the EEG features of a visual learner differ from those of a non-visual learner. The idea is to measure the students’ EEGs during the resting states (eyes open and eyes closed conditions) and when performing learning tasks. For this purpose, 34 healthy subjects are recruited. The subjects have no background knowledge of the animated learning content. The subjects are shown the animated learning content in a video format. The experiment consists of two sessions and each session comprises two parts: (1) Learning task: the subjects are shown the animated learning content for an 8–10 min duration. (2) Memory retrieval task The EEG signals are measured during the leaning task and memory retrieval task in two sessions. The retention time for the first session was 30 min, and 2 months for the second session. The analysis is performed for the EEG measured during the memory retrieval tasks. The study characterizes and differentiates the visual learners from the non-visual learners considering the extracted EEG features, such as the power spectral density (PSD), power spectral entropy (PSE), and discrete wavelet transform (DWT). The PSD and DWT features are analyzed. The EEG PSD and DWT features are computed for the recorded EEG in the alpha and gamma frequency bands over 128 scalp sites. The alpha and gamma frequency band for frontal, occipital, and parietal regions are analyzed as these regions are activated during learning. The extracted PSD and DWT features are then reduced to 8 and 15 optimum features using principal component analysis (PCA). The optimum features are then used as an input to the k -nearest neighbor ( k -NN) classifier using the Mahalanobis distance metric, with 10-fold cross validation and support vector machine (SVM) classifier using linear kernel, with 10-fold cross validation. The classification results showed 97% and 94% accuracies rate for the first session and 96% and 93% accuracies for the second session in the alpha and gamma bands for the visual learners and non-visual learners, respectively, for k -NN classifier for PSD features and 68% and 100% accuracies rate for first session and 100% accuracies rate for second session for DWT features using k -NN classifier for the second session in the alpha and gamma band. For PSD features 97% and 96% accuracies rate for the first session, 100% and 95% accuracies rate for second session using SVM classifier and 79% and 82% accuracy for first session and 56% and 74% accuracy for second session for DWT features using SVM classifier. The results showed that the PSDs in the alpha and gamma bands represent distinct and stable EEG signatures for visual learners and non-visual learners during the retrieval of the learned contents.

show abstract

Section: Introductionmentioning

confidence: 99%

Classification of Visual and Non-visual Learners Using Electroencephalographic Alpha and Gamma Activities

Jawed

Amin

Malik³

et al. 2019

Front. Behav. Neurosci.

View full text Add to dashboard Cite

show abstract

“…Automatic detection of learning styles is considered a better way than the traditional pencil-and-paper approach in terms of data accuracy (Ahmad and Tasir, 2013): the data collected is from students' interaction with the learning system, so there is no extra time input from participants, which minimised errors caused by participants' fatigue, biased expectations, impatience or misconceptions (Adkins and Guerreiro, 2018;Ahmad and Tasir, 2013;Bernard et al, 2017;Feldman et al, 2015;Graf and Kinshuk, 2010). Moreover, the automatic approach enables students to focus on study instead of paying attention to their preferences (Graf and Liu, 2008).…”

Section: Literature Reviewmentioning

confidence: 99%

“…Numerous studies have attempted to identify visualisers and verbalisers using diverse approaches and achieved different levels of accuracy, as shown in Table 1. According to Ahmad and Tasir (2013), the two main approaches are literature-based and data-driven.…”

Section: Identification Of Visualisers/verbalisersmentioning

confidence: 99%

The use of eye-tracking technology to identify visualisers and verbalisers: accuracy and contributing factors

Luo

O’Steen

Brown

2020

ITSE

View full text Add to dashboard Cite

Purpose To build adaptive learning systems for a better learning experience, designers need to identify users’ behaviour patterns and provide adaptive learning materials accordingly. This study involved a quasi-experiment and also this paper aims to investigate the accuracy of eye-tracking technology in identifying visualisers and verbalisers and the contributing factors to diverse levels of accuracy, which lays the foundation for the establishment of adaptive learning systems. Design/methodology/approach The authors prepared eight documents with different image-text combinations with the intention of triggering participants’ natural reading habits. By analysing the eye-movement data, this author categorised the 22 participants as visualisers or verbalisers. The results were compared for accuracy measure with participants’ self-reports in response to the index of learning style questionnaire. Findings The results showed that visualisers and verbalisers presented significantly different eye-movement patterns, which was confirmed by the fixation data from the Tobii eye-tracker with the detection accuracy ranged from 38% to 77%. Various factors contributed to a range of levels of accuracy, including highlighted elements, learning context, complex background, low relevance of images and texts, learner differences, awareness of experimental settings, self-conception and prior knowledge. Originality/value To the authors’ knowledge, this is the first paper investigating the feasibility of eye-tracking technology to identify visualisers and verbalisers for the development of adaptive learning systems.

show abstract

“…Among them, in particular, the learning style model developed by Felder and Silverman (1988) are highly suitable for studies about learning styles in online courses, in which the information is presented by multimedia applications [4]. This model, which is highly referenced in the literature as an important conceptualiser of learning styles [40], can analyse the sizes of learning styles clearly according to a scale ranging between +11 and -11 [2]. For this study, this learning style model was used because learning objects were presented to students in an online environment.…”

Section: Learning Stylesmentioning

confidence: 99%

The Analysis of the Relationship between Primary Learning Styles and Learning Objects in an Online Environment

Özdemir

2016

European Journal of Contemporary Education

View full text Add to dashboard Cite

This study investigates the relationships between the primary learning styles of students and different learning objects presented simultaneously in an online learning environment in the context of the usage levels of these objects. A total of 103 sophomores from a Turkish State University participated in the study. Felder-Solomon Index of Learning-Styles (F-SILS) was used to determine the learning styles of the participants. Four different types of learning objects (i.e. video lecturing, audio lecturing, PDF lecturing and subject comprehension tests) were prepared for the course ‗Basic database operations with MySQL'. Koper's (2003) classification model was used in selecting these learning objects. Descriptive analysis methods were used to determine the distribution of the participants according to their learning styles. Independent-Samples T-Test and the Mann-Whitney Wilcoxon test were used to test the differences between learning styles and learning objects. The usage levels of the learning objects were analysed in the context of interdimensional primary learning styles in the scale of the F-SILS. Those with sensory and visual learning styles were in the majority among the primary learning styles of participants. The study did not include the findings of students with other primary learning styles due to their small sample size. The findings of the study on the usage frequencies of subject comprehension tests and the duration of video lectures by primarily visual and sensory students demonstrated a significant difference on behalf of the primary sensory students. On the other hand, there was no statistically significant difference between students with primarily sensory styles and students with primarily visual styles in terms of the reading frequency of PDF lectures and the listening frequency of audio lectures.

show abstract

Threshold Value in Automatic Learning Style Detection

Cited by 14 publications

References 21 publications

Classification of Visual and Non-visual Learners Using Electroencephalographic Alpha and Gamma Activities

Classification of Visual and Non-visual Learners Using Electroencephalographic Alpha and Gamma Activities

The use of eye-tracking technology to identify visualisers and verbalisers: accuracy and contributing factors

The Analysis of the Relationship between Primary Learning Styles and Learning Objects in an Online Environment

Contact Info

Product

Resources

About