This study developed an adaptive web-based learning system focusing on students' cognitive styles. The system is composed of a student model and an adaptation model. It collected students' browsing behaviors to update the student model for unobtrusively identifying student cognitive styles through a multi-layer feed-forward neural network (MLFF). The MLFF was adopted because of its ability on imprecise or incompletely understood data, ability to generalize and learn from specific examples, ability to be quickly updated with extra parameters, and speed in execution making them ideal for real time applications. The system then adaptively recommended learning content presented with a variety of content and interactive components through the adaptation model based on the student cognitive style identified in the student model. The adaptive web interfaces were designed by investigating the relationships between students' cognitive styles and browsing patterns of content and interactive components. Training of the MLFF and an experiment were conducted to examine the accuracy of identifying students' cognitive styles during browsing with the proposed MLFF and the impact of the proposed adaptive web-based system on students' engagement in learning. The training results of the MLFF showed that the proposed system could identify students' cognitive styles with high accuracy and the temporal effects should be considered while identifying students' cognitive styles during browsing. Two factors, the acknowledgment of students' cognitive styles while browsing and the existence of adaptive web interfaces, were used to assign three classes of college freshmen into three groups. The experimental results revealed that the proposed system could have significant impacts on temporal effects on students' engagement in learning, not only for students with cognitive styles known before browsing, but also for students with cognitive styles identified during browsing. The results provide evidence of the effectiveness of the adaptive web-based learning system with students' cognitive styles dynamically identified during browsing, thus validating the research purposes of this study.
(private-note)Cognitive style Myers-Briggs recognition using NN and adaptation based on that - looks simple, matching type of content to style.
Nowadays, there are more and more web-based learning systems on network which can provide lots of learning materials for users. However, plenty of these systems fail to let users grasp the important information they need due to their arbitrary structure. How to design a web-based learning system that can make users learn materials efficiently becomes a major problem for designers. In the meanwhile, people have different cognitive styles which influence how people organize and process information, and it thus has influence on their learning performance. As a result, since cognitive style of users can influence the effectiveness and efficiency of learning, letting web-based learning system includes information about students' cognitive style may be a good idea.
But, to realize it, there may be two obstacles. One is the difficulty of identifying student cognitive styles online. Another is the adaptive learning materials in web-based environment. Based on these concerns, the purpose of this study is presenting an adaptive web-based learning system focusing on users' cognitive styles.
Since asking users to provide personal information explicitly to identify their cognitive styles may make them uncomfortable, the system in this study chooses to record users' browsing history and put these history data into a multi-layer feed-forward neural network to get the certain users' cognitive style using Myers-Briggs Type Indicator which is based on Jung's theory of cognitive styles and divides the cognitive style into four types, Mastery, Understanding, Self-expressive and Interpersonal. In this process, the system will use four kinds of users' browsing history data as the neural network's input, such as the selection frequency of certain component, selection ration of certain component, average staying time of certain component and selection ratio of certain content link type. In the beginning, the system uses some participants' data to build the neutral network and then lets some other participants to test the accuracy of the neutral network. And the result is the identification of all four cognitive styles' accuracy ratio reaches to 80\% which proves that the neutral network is quite reliable.
The second task is to study the relationship between users' cognitive styles and their browsing behavior. In the study, more than one hundred participants were asked to use the system about one learning topic for 30 minutes and the system collected all their browsing behavior which is mainly the selection ratio and the average staying time of the system screen's content and interactive components. These time can reflect users' preference for these components with respect to different cognitive styles. And the result shows that if one component's selection ration is high, its staying time must be high. Therefore, the web interfaces for students with different cognitive style would be designed based on these data. To evaluate the adaptive web-based learning system's impacts on users' browsing behavior. The study conducted a controlled experiment. The result showed that when user used the non-adaptive system, the Interpersonal and Master cognitive styles user would lose patience in the last several minutes of the 30 minutes experiment time. But when they used the adaptive system, all types of cognitive styles of users would pay attention to the interface they faced all the time.
Thus, the study in this research proves that the adaptive web-based learning system based on users' cognitive styles can satisfy users' more interests and let them learn information more efficiently.
%0 Journal Article
%1 citeulike:9831143
%A Lo, Jia-Jiunn
%A Chan, Ya-Chen
%A Yeh, Shiou-Wen
%D 2012
%J Computers & Education
%K adaptive-hypermedia en neural-network personal-traits
%N 1
%P 209--222
%R 10.1016/j.compedu.2011.08.018
%T Designing an adaptive web-based learning system based on students' cognitive styles identified online
%U http://dx.doi.org/10.1016/j.compedu.2011.08.018
%V 58
%X This study developed an adaptive web-based learning system focusing on students' cognitive styles. The system is composed of a student model and an adaptation model. It collected students' browsing behaviors to update the student model for unobtrusively identifying student cognitive styles through a multi-layer feed-forward neural network (MLFF). The MLFF was adopted because of its ability on imprecise or incompletely understood data, ability to generalize and learn from specific examples, ability to be quickly updated with extra parameters, and speed in execution making them ideal for real time applications. The system then adaptively recommended learning content presented with a variety of content and interactive components through the adaptation model based on the student cognitive style identified in the student model. The adaptive web interfaces were designed by investigating the relationships between students' cognitive styles and browsing patterns of content and interactive components. Training of the MLFF and an experiment were conducted to examine the accuracy of identifying students' cognitive styles during browsing with the proposed MLFF and the impact of the proposed adaptive web-based system on students' engagement in learning. The training results of the MLFF showed that the proposed system could identify students' cognitive styles with high accuracy and the temporal effects should be considered while identifying students' cognitive styles during browsing. Two factors, the acknowledgment of students' cognitive styles while browsing and the existence of adaptive web interfaces, were used to assign three classes of college freshmen into three groups. The experimental results revealed that the proposed system could have significant impacts on temporal effects on students' engagement in learning, not only for students with cognitive styles known before browsing, but also for students with cognitive styles identified during browsing. The results provide evidence of the effectiveness of the adaptive web-based learning system with students' cognitive styles dynamically identified during browsing, thus validating the research purposes of this study.
@article{citeulike:9831143,
abstract = {{This study developed an adaptive web-based learning system focusing on students' cognitive styles. The system is composed of a student model and an adaptation model. It collected students' browsing behaviors to update the student model for unobtrusively identifying student cognitive styles through a multi-layer feed-forward neural network (MLFF). The MLFF was adopted because of its ability on imprecise or incompletely understood data, ability to generalize and learn from specific examples, ability to be quickly updated with extra parameters, and speed in execution making them ideal for real time applications. The system then adaptively recommended learning content presented with a variety of content and interactive components through the adaptation model based on the student cognitive style identified in the student model. The adaptive web interfaces were designed by investigating the relationships between students' cognitive styles and browsing patterns of content and interactive components. Training of the MLFF and an experiment were conducted to examine the accuracy of identifying students' cognitive styles during browsing with the proposed MLFF and the impact of the proposed adaptive web-based system on students' engagement in learning. The training results of the MLFF showed that the proposed system could identify students' cognitive styles with high accuracy and the temporal effects should be considered while identifying students' cognitive styles during browsing. Two factors, the acknowledgment of students' cognitive styles while browsing and the existence of adaptive web interfaces, were used to assign three classes of college freshmen into three groups. The experimental results revealed that the proposed system could have significant impacts on temporal effects on students' engagement in learning, not only for students with cognitive styles known before browsing, but also for students with cognitive styles identified during browsing. The results provide evidence of the effectiveness of the adaptive web-based learning system with students' cognitive styles dynamically identified during browsing, thus validating the research purposes of this study.}},
added-at = {2018-03-19T12:24:51.000+0100},
author = {Lo, Jia-Jiunn and Chan, Ya-Chen and Yeh, Shiou-Wen},
biburl = {https://www.bibsonomy.org/bibtex/2e904f2e56591d47a11b157dad8cbca32/aho},
citeulike-article-id = {9831143},
citeulike-linkout-0 = {http://dx.doi.org/10.1016/j.compedu.2011.08.018},
comment = {(private-note)Cognitive style Myers-Briggs recognition using NN and adaptation based on that - looks simple, matching type of content to style.
Nowadays, there are more and more web-based learning systems on network which can provide lots of learning materials for users. However, plenty of these systems fail to let users grasp the important information they need due to their arbitrary structure. How to design a web-based learning system that can make users learn materials efficiently becomes a major problem for designers. In the meanwhile, people have different cognitive styles which influence how people organize and process information, and it thus has influence on their learning performance. As a result, since cognitive style of users can influence the effectiveness and efficiency of learning, letting web-based learning system includes information about students' cognitive style may be a good idea.
But, to realize it, there may be two obstacles. One is the difficulty of identifying student cognitive styles online. Another is the adaptive learning materials in web-based environment. Based on these concerns, the purpose of this study is presenting an adaptive web-based learning system focusing on users' cognitive styles.
Since asking users to provide personal information explicitly to identify their cognitive styles may make them uncomfortable, the system in this study chooses to record users' browsing history and put these history data into a multi-layer feed-forward neural network to get the certain users' cognitive style using Myers-Briggs Type Indicator which is based on Jung's theory of cognitive styles and divides the cognitive style into four types, Mastery, Understanding, Self-expressive and Interpersonal. In this process, the system will use four kinds of users' browsing history data as the neural network's input, such as the selection frequency of certain component, selection ration of certain component, average staying time of certain component and selection ratio of certain content link type. In the beginning, the system uses some participants' data to build the neutral network and then lets some other participants to test the accuracy of the neutral network. And the result is the identification of all four cognitive styles' accuracy ratio reaches to 80\% which proves that the neutral network is quite reliable.
The second task is to study the relationship between users' cognitive styles and their browsing behavior. In the study, more than one hundred participants were asked to use the system about one learning topic for 30 minutes and the system collected all their browsing behavior which is mainly the selection ratio and the average staying time of the system screen's content and interactive components. These time can reflect users' preference for these components with respect to different cognitive styles. And the result shows that if one component's selection ration is high, its staying time must be high. Therefore, the web interfaces for students with different cognitive style would be designed based on these data. To evaluate the adaptive web-based learning system's impacts on users' browsing behavior. The study conducted a controlled experiment. The result showed that when user used the non-adaptive system, the Interpersonal and Master cognitive styles user would lose patience in the last several minutes of the 30 minutes experiment time. But when they used the adaptive system, all types of cognitive styles of users would pay attention to the interface they faced all the time.
Thus, the study in this research proves that the adaptive web-based learning system based on users' cognitive styles can satisfy users' more interests and let them learn information more efficiently.},
doi = {10.1016/j.compedu.2011.08.018},
interhash = {65385ade8cc69311228a7ac36b1be972},
intrahash = {e904f2e56591d47a11b157dad8cbca32},
issn = {03601315},
journal = {Computers \& Education},
keywords = {adaptive-hypermedia en neural-network personal-traits},
month = jan,
number = 1,
pages = {209--222},
posted-at = {2014-04-26 20:57:26},
priority = {2},
timestamp = {2018-03-19T12:24:51.000+0100},
title = {{Designing an adaptive web-based learning system based on students' cognitive styles identified online}},
url = {http://dx.doi.org/10.1016/j.compedu.2011.08.018},
volume = 58,
year = 2012
}