DIGITALMASSIVE DATA-MINING ANALYSIS OF DISTANCE SCIENCE EDUCATION LEARNING SYSTEMS
1 National Kaohsiung Normal University (TAIWAN)
2 National Center for High-Performance Computing of NARLabs (TAIWAN)
2 National Center for High-Performance Computing of NARLabs (TAIWAN)
About this paper:
Appears in: EDULEARN23 Proceedings
Publication year: 2023
Pages: 4611-4619
ISBN: 978-84-09-52151-7
ISSN: 2340-1117
doi: 10.21125/edulearn.2023.1229
Publication year: 2023
Pages: 4611-4619
ISBN: 978-84-09-52151-7
ISSN: 2340-1117
doi: 10.21125/edulearn.2023.1229
Conference name: 15th International Conference on Education and New Learning Technologies
Dates: 3-5 July, 2023
Location: Palma, Spain
Dates: 3-5 July, 2023
Location: Palma, Spain
Abstract:
To promote the development of science literacy and life-long learning habits of teachers in primary, secondary and kindergarten, so as to give back to students and make knowledge activities a part of social cultural promotion activities, Taiwan's primary and secondary school teachers’ in-service education system under the breakthrough time and space limit, use distance learning method, the biggest in-service education learning web site for the National Center for High-performance Computing Co-Life team build "Knowledge Lecture Hall" web site, https://knowledge.colife.org.tw/. The purpose of this study was to establish a data storage based on the number of over 98,950 in-service training data out of 5,290 teachers participating in distance science education in the past five years (2018-2022) collected by the Knowledge Lecture website. The data contained 17 field variables, including basic information of teachers and the schools they serve, online viewing time, and in-service training course information of teachers. In the process of knowledge discovery in the database, the Apriori algorithm was used to explore the association rules between the nature of teachers' in-service training courses, and the support and correlation index (lift) were used to judge and mine the association rules. The support and trust were used to try to find out the meaningful and positively related rules, and the best model was analyzed. To carry out the following explorations:1. To explore the preferences and trends of in-service teachers' participation in learning courses during the past five years (2018-2022).
2. Explore the association rules of in-service teachers' participation in learning courses in the Knowledge Forum during the past five years (2018-2022).
Based on the results of the study, suggestions for improvement are provided as a reference for the future management of in-service distance learning courses in the Knowledge Lecture website and for future research by future researchers.