Framework for Personalised Online Education based on Learning Analytics through the use of Domain-Specific Modelling and Data Analytics
Authors: Meacham, S., Nauck, D. and Zhao, H.
Journal: 2nd International Conference on Next Generation Computing Applications 2019, NextComp 2019 - Proceedings
ISBN: 9781728114606
DOI: 10.1109/NEXTCOMP.2019.8883640
Abstract:This paper contains a framework for the design and development of adaptive Virtual Learning Environments (VLEs) to assist educators of all disciplines with configuring and creating adaptive VLEs tailored to their needs. The proposed work is performed in three stages: In the first stage, development of an adaptive VLE that collects learning analytics and enables the educator to parametrize (turn on/off) their collection. The output of these analytics gets stored for further processing. In the second stage, data analysis and processing has been performed for the collected information. In the third stage, the results have been used as an input to adaptive VLE to enable informed personalisation of the student learning path and other adaptations. In this paper, we have proposed the combined use of two different environments for the different stages to achieve the most from their specialisation. For the first and the third stage, the MPS Jetbrains environment for the development of a domain-specific language (DSL) for adaptive VLEs was utilised. This development environment assists the creation of a new DSL that will enable educators to focus on the domain aspects and configure their adaptive VLE implementation to their needs. For the second stage of data analysis, the weka library was used to process the data, apply a range of classification algorithms and produce/store results that can then be used as an input to the adaptive VLE DSL. Overall, the proposed frameworksystem is anticipated to isolate the domain problem from the corresponding implementation details of web development and data analysis and give the adaptive VLE developer a seamless environment to experiment with a very quick turn-around time with ideas in their domain. More automation and integration between the VLE and the data science algorithms utilised for learning analytics data are part of our future plans towards the greater vision of more autonomic and personalised VLEs.
https://eprints.bournemouth.ac.uk/32790/
Source: Scopus
Framework for Personalised Online Education based on Learning Analytics through the use of Domain-Specific Modelling and Data Analytics
Authors: Meacham, S., Nauck, D. and Zhao, H.
Journal: 2019 SECOND INTERNATIONAL CONFERENCE ON NEXT GENERATION COMPUTING APPLICATIONS 2019 (NEXTCOMP 2019)
DOI: 10.1109/nextcomp.2019.8883640
https://eprints.bournemouth.ac.uk/32790/
Source: Web of Science (Lite)
Framework for personalised online education based on learning analytics through the use of domain-specific modelling and data analytics
Authors: Meacham, S., Nauck, D. and Zhao, H.
Conference: Next Generation Computing Applications 2019, IEEE Mauritus Section
Dates: 19-21 September 2019
Journal: Next Generation Computing Applications 2019
Pages: 197-203
Publisher: IEEE Mauritius Section
Abstract:This paper contains a framework for the design and development of adaptive Virtual Learning Environments (VLEs) in order to assist educators of all disciplines with configuring and creating adaptive VLEs tailored to their needs. The proposed work is performed in three stages: In the first stage, development of an adaptive VLE that collects learning analytics and enables the educator to parametrize (turn on/off) their collection. The output of these analytics gets stored for further processing. In the second stage, data analysis and processing has been performed for the collected information. In the third stage, the results have been used as an input to adaptive VLE to enable informed personalisation of the student learning path and other adaptations. In this paper, we have proposed the combined use of two different environments for the different stages to achieve the most from their specialisation. For the first and the third stage, the MPS Jetbrains environment for the development of a domain-specific language (DSL) for adaptive VLEs was utilised. This development environment assists the creation of a new DSL that will enable educators to focus on the domain aspects and configure their adaptive VLE implementation to their needs. For the second stage of data analysis, the weka library was used to process the data, apply a range of classification algorithms and produce/store results that can then be used as an input to the adaptive VLE DSL. Overall, the proposed framework-system is anticipated to isolate the domain problem from the corresponding implementation details of web development and data analysis and give the adaptive VLE developer a seamless environment to experiment with a very quick turn-around time with ideas in their domain. More automation and integration between the VLE and the data science algorithms utilised for learning analytics data are part of our future plans towards the greater vision of more autonomic and personalised VLEs.
https://eprints.bournemouth.ac.uk/32790/
Source: Manual
Framework for personalised online education based on learning analytics through the use of domain-specific modelling and data analytics
Authors: Meacham, S., Nauck, D. and Zhao, H.
Conference: Next Generation Computing Applications 2019, IEEE Mauritus Section
Pages: 197-203
Publisher: IEEE Mauritius Section
Abstract:This paper contains a framework for the design and development of adaptive Virtual Learning Environments (VLEs) in order to assist educators of all disciplines with configuring and creating adaptive VLEs tailored to their needs. The proposed work is performed in three stages: In the first stage, development of an adaptive VLE that collects learning analytics and enables the educator to parametrize (turn on/off) their collection. The output of these analytics gets stored for further processing. In the second stage, data analysis and processing has been performed for the collected information. In the third stage, the results have been used as an input to adaptive VLE to enable informed personalisation of the student learning path and other adaptations. In this paper, we have proposed the combined use of two different environments for the different stages to achieve the most from their specialisation. For the first and the third stage, the MPS Jetbrains environment for the development of a domain-specific language (DSL) for adaptive VLEs was utilised. This development environment assists the creation of a new DSL that will enable educators to focus on the domain aspects and configure their adaptive VLE implementation to their needs. For the second stage of data analysis, the weka library was used to process the data, apply a range of classification algorithms and produce/store results that can then be used as an input to the adaptive VLE DSL. Overall, the proposed framework-system is anticipated to isolate the domain problem from the corresponding implementation details of web development and data analysis and give the adaptive VLE developer a seamless environment to experiment with a very quick turn-around time with ideas in their domain. More automation and integration between the VLE and the data science algorithms utilised for learning analytics data are part of our future plans towards the greater vision of more autonomic and personalised VLEs.
https://eprints.bournemouth.ac.uk/32790/
Source: BURO EPrints