A DATA-DRIVEN APPROACH TO ASSESSING ICT COMPETENCIES IN VOCATIONAL HIGH SCHOOLS
Abstract
The development of information technology has had a profound impact on all aspects of life, including education, making Information and Communication Technology (ICT) competencies an essential component for learners in solving problems using technology. Educational units that adopt a learning approach based on ICT can foster independent learning innovations compared to conventional methods, leading to a more consistent standard of learning quality. Blended Learning, in particular, has shown promising results in improving learning outcomes when integrated with ICT in educational institutions.
In the context of the COVID-19 pandemic, full online or blended learning has become a critical solution, necessitating effective and efficient changes in the learning process. To ensure smooth learning experiences and support pedagogical planning, it is crucial to map and visualize the ICT competencies of students. Such mapping serves as a valuable reference for formulating lesson plans, ICT policies, and placements for Industrial Work Practices (Prakerin) for students.
Data clustering, a Data Mining technique, is employed to automate the analysis and extraction of knowledge from ICT competency data. The K-Means Clustering Algorithm is one such method that partitions data into distinct clusters based on similarities, facilitating the identification of highly competent, competent, and less competent students in the field of ICT.
This study focuses on SMKN 3 Lhokseumawe, an educational unit implementing blended learning, to determine the ICT competency levels of its students. By calculating the shortest distance between data points and centroid in each cluster, the K-Means algorithm generates distinct groups of students based on their ICT competencies. Previous research using the K-Means algorithm has demonstrated its effectiveness in clustering participants in the National Science Olympiad and determining superior class students. Additionally, the algorithm has been applied to measure the correlation between student profiles and grades and cluster student interest in school selection.
Through this study, we aim to provide valuable insights into the ICT competency levels of SMKN 3 Lhokseumawe students and contribute to the enhancement of educational practices through data-driven decision-making.
