E3S Web Conf.
Volume 202, 2020The 5th International Conference on Energy, Environmental and Information System (ICENIS 2020)
|Number of page(s)||8|
|Section||Smart Information System|
|Published online||10 November 2020|
Improving The Accuracy of Student Problem Identification Using Rule-Based Machine Learning
1 Graduate School of Information System Diponegoro University Semarang, Indonesia
2 Faculty of Science and Mathematics Diponegoro University Semarang, Indonesia
3 Department of Electrical Engineering Diponegoro University Semarang, Indonesia
* Corresponding author: email@example.com
Adolescence are a period of development that is vulnerable to problems and often makes teens unable to control emotions. No exception for adolescents who are studying high school. Problems that do not need to be resolved immediately and bigger problems will arise later on. Many methods of solving students' problems are carried out in a conventional manner which takes time and costly. Therefore, teacher guidance and career guidance at school use the problem checklist method to identify student problems. One thing that promises to improve accuracy with time to identify problems by building information systems using intelligent technology such as machine learning. Machine learning offers sophisticated techniques built by automatic classification that can be utilized by students and teachers to improve accuracy and efficiency in identification. This article discusses issues related to problems faced by senior high school students and proposes a knowledge-based users (rules) machine learning to match the problems and alternative solutions. This system can be used by school counsellors to help students solving their problems and the students to access themselves without having to meet the school counsellor. The results of this research indicate that information system developed based on rule-based machine learning offer a student problem identification which is more accurate, faster, can be done anytime and anywhere, and requires less cost compared to existing conventional methods. Analysis of machine learning with rule-based models using WEKA gives 100% accuracy.
© The Authors, published by EDP Sciences, 2020
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.