Classification of the effectiveness of ICT integration in teaching and learning using data mining based on AHP methods
Information and Communication Technology (ICT) is a medium that people rely on daily to receive information via a specific application. The Ministry of Education in Malaysia has widely integrated ICT into the education system since 1990s. However, ICT is still not fully implemented due to some obsta...
Saved in:
| 主要作者: | |
|---|---|
| 格式: | Thesis |
| 语言: | eng eng eng |
| 出版: |
2023
|
| 主题: | |
| 在线阅读: | https://etd.uum.edu.my/10742/1/permission%20to%20deposit-embargo%206%20months-s826244.pdf https://etd.uum.edu.my/10742/2/s826244_01.pdf https://etd.uum.edu.my/10742/3/s826244_02.pdf |
| 标签: |
添加标签
没有标签, 成为第一个标记此记录!
|
| 总结: | Information and Communication Technology (ICT) is a medium that people rely on daily to receive information via a specific application. The Ministry of Education in Malaysia has widely integrated ICT into the education system since 1990s. However, ICT is still not fully implemented due to some obstacles such as lack of sufficient training, time, ICT resources and infrastructure. Therefore, the purpose of this research is to analyze and rank the factors that impede the integration of ICT in urban and rural secondary schools using the Analytic Hierarchy Process (AHP) approach, as well as to determine the significant difference between factors in urban and rural areas by using t-test analysis. In conjunction with the outputs, several predictive models are then developed to classify the students’ academic performance in urban and rural areas using Data Mining techniques. The respondents for this study are secondary school teachers in the Malaysian state of Kedah. For the first phase, 51 teachers were chosen to complete the questionnaire. A total of 238 teachers were chosen for the second phase. The hypothesis testing showed that there is no significant difference between the factors in both areas. The top three factors are workload (13.46%), lack of accessibility and network connection (13.25%), and lack of support assistance (12.09%). The result gained was used to develop several predictive models and the best model was selected for classifying the students’ academic performance. The Decision Tree (cross-validation) outperformed the other models with a misclassification rate of 32.98% (urban) and 16% (rural). The developed predictive model can be used by Ministry of Education or policymaker to plan national educational policies whilst implement a better strategy for educational development based on government policies and the Education Act. |
|---|