Studi Komparasi Algoritma Decision Tree C4.5 dan K-Nearest Neighbor pada Klasifikasi Masa Studi dan Tingkat Stres Mahasiswa
Abstract
This research explores the utilization of Educational Data Mining (EDM) to analyze attributes that affect students' academic performance focusing on study duration and stress levels. In this study, the performance of two classification algorithms Decision Tree C4.5 and K-Nearest Neighbor (KNN) was compared in classifying students' study duration and stress levels based on alumni data from those who graduated between 202-2023. Several variables analyzed in this dataset include gender, GPA, the number of credits taken, admission pathway, participation in organizations, and activity as an assistant. The main findings of this study indicate that gender is a significant factor in predicting students' study duration, while GPA substantially impacts students' stress levels. Regarding algorithm performance, KNN outperformed Decision Tree C4.5, achieving an accuracy rate of 71.44% for study duration classification and 64.17% for stress level classification. This research provides valuable insights for higher education institutions in formulating policies to enhance students' academic performance and well-being.
Keywords: Educational Data Mining; Decision Tree C4.5; K-Nearest Neighbor; Student Study Period; Student Stress Level
Abstrak
Penelitian ini mengeksplorasi pemanfaatan Educational Data Mining (EDM) untuk menganalisis atribut-atribut yang memengaruhi kinerja akademik mahasiswa dengan fokus pada durasi studi dan tingkat stres. Dalam penelitian ini, kinerja dua algoritma klasifikasi yaitu Decision Tree C4.5 dan K-Nearest Neighbor dibandingkan dalam mengklasifikasikan masa studi dan tingkat stres mahasiswa berdasarkan data alumni yang lulus antara tahun 2021-2023. Variabel yang dianalisis dalam dataset ini adalah jenis kelamin, IPK, jumlah SKS yang diambil, jalur masuk, keaktifan organisasi, dan keaktifan asistensi. Temuan utama dari penelitian ini menunjukkan bahwa jenis kelamin merupakan faktor signifikan dalam memprediksi durasi studi mahasiswa, sedangkan IPK memiliki dampak substansial terhadap tingkat stres mahasiswa. Berdasarkan hasil komparasi performa algoritma, KNN lebih unggul dibandingkan Decision Tree C4.5, dengan tingkat akurasi sebesar 71,44% untuk klasifikasi durasi studi dan 64,17% untuk klasifikasi tingkat stres. Penelitian ini memberikan wawasan berharga bagi institusi pendidikan tinggi dalam merumuskan kebijakan untuk meningkatkan kinerja akademik dan kesejahteraan mahasiswa.
Keywords
References
S.A.A. Kharis and A.H.A. Zili., “Learning Analytics dan Educational Data Mining pada Data Pendidikan”, JRPMS (Jurnal Riset Pembelajaran Matematika Sekolah)., vol. 6, no. 1, pp. 12-20, 2022.
M.M. Abu Tair and A. M. Al-Helees., “Mining Educational Data to Improve Students’ Performance: A Case Study”, International Journal of Information and Communication Technology Research, vol 2, no. 2, pp. 21-30, 2012.
C. Jalota and R. Agrawal., "Analysis of Educational Data Mining using Classification", 2019 International Conference on Machine Learning, Big Data, Cloud and Parallel Computing (COMITCon), Faridabad, India, pp. 243-247, 2019, doi: 10.1109/COMITCon.2019.8862214.
N. Renaningtias., J.E., Suseno., and R. Gernowo., “Hybrid Decision Tree and Naïve Bayes Classifier for Predicting Study Period and Predicate of Student’s Graduation”, International Journal of Computer Application, vol.180, pp. 49-58, 2018
D. Safitri., S. S. Hilabi, and F. Nurapriani., “Analisis Penggunaan Algoritma Klasifikasi dalam Prediksi Kelulusan Menggunakan Orange Data Mining”, RABIT: Jurnal Teknologi dan Sistem Informasi Univrab, vol. 8, no. 1, pp. 75-81, 2023.
A. Trifani, A. P. Windarto, and H. Qurniawan, “Penerapan Data Mining Klasifikasi C4.5 dalam Menentukan Tingkat Stres Mahasiswa Akhir”, Jurnal Riset Rumpun Ilmu Teknik, vol. 1, no. 2, pp. 91–105, 2022 https://doi.org/10.55606/jurritek.v1i2.414
A.M. Goff, “Stresor, Academic performance and learned resourcefulness in baccalaureate nursing student”, International Journal of Nursing Education Scholarship, vol. 8, no. 1, pp. 923 – 154, 2011, doi:10.2202/1548-923X.2114
L. Setiyani, M. Wahidin, D. Awaludin, and S. Purwani, “Analisis Prediksi Kelulusan Mahasiswa Tepat Waktu Menggunakan Metode Data Mining Naïve Bayes : Systematic Review”, Faktor Exacta, vol. 13, no. 1, pp. 35-40, 2020, doi: https://doi.org/10.30998/faktorexacta.v13i1.5548
L.O.M. Zulfiqar., N. Renaningtias., and M.Y. Fathoni., “Educational Data Mining in Graduation Rate and Grade Predictions Utilizing Hybrid Decision Tree and Naïve Bayes Classifier”, in Proceedings of the International Conferences on Information System and Technology (CONRIST 2019), pp. 151-157, 2019.
A. Yandi Saputra and Y. Primadasa, “Penerapan Teknik Klasifikasi Untuk Prediksi Kelulusan Mahasiswa Menggunakan Algoritma K-Nearest Neighbour Implementation of Classification Method to Predict Stident”, Techno Com, vol. 17, no. 4, pp. 395-403, doi: 10.33633/tc.v17i4.1864
F. Alshareef, H. Alhakami, T. Alsubait, and A Baz, “Educational Data Mining Applications and Techniques”, International Journal of Advanced Computer Science and Applications, vol. 11, no. 4, pp. 729-734, 2020, http://dx.doi.org/10.14569/IJACSA.2020.0110494
Y. Apridiansyah, N.D.M. Veronika, and E.D., Putra, “Prediksi Kelulusan Mahasiswa Fakultas Teknik Informatika Universitas Muhammadiyah Bengkulu Menggunakan Metode Naive Bayes”, JSAI (Journal Scientific and Applied Informatics), vol. 4, no. 2, pp. 236–247, 2021 DOI: https://doi.org/10.36085/jsai.v4i2.1701
D. Priyambodo, A. Nugroho, and B. Zaman, “Prediksi Ketepatan Waktu Studi Mahasiswa Bidik Misi Menggunakan K-Nearest Neighbour”, Jurnal Pendidikan Teknologi Informasi (JUKANTI), vol. 5, no. 2, pp. 16–22. 2022, doi: https://doi.org/10.37792/jukanti.v5i2.520
E. Siswanto., “Optimasi Metode Naïve Bayes Dalam Memprediksi Tingkat Kelulusan Mahasiswa Stekom Semarang”, Jurikom, vol. 6 no. 1, pp. 1–13, 2019.
N.P. Indah, Widodo, and H. Ajie, “Kinerja Algoritma Classification And Regression Tree (Cart) dalam Mengklasifikasikan Lama Masa Studi Mahasiswa yang Mengikuti Organisasi di Universitas Negeri Jakarta”, PINTER : Jurnal Pendidikan Teknik Informatika Dan Komputer, vol. 3, no. 2, pp. 139–145, 2019.
I.G.I. Suardika, “Prediksi Tingkat Kelulusan Mahasiswa Tepat Waktu Menggunakan Naive Bayes: Studi Kasus Fakultas Ekonomi Dan Bisnis Universitas Pendidikan Nasional”, Jurnal Ilmu Komputer Indonesia, vol. 4, no. 2, pp. 37– 44, 2019.
J. Nasir, “Penerapan Data Mining Clustering Dalam Mengelompokan Buku Dengan Metode K-Means”. Simetris: Jurnal Teknik Mesin, Elektro dan Ilmu Komputer, vol. 11, no.2, pp. 690–703, 2021 DOI: https://doi.org/10.24176/simet.v11i2.5482
E. Mardiani, et al. “Komparasi Metode Knn, Naive Bayes, Decision Tree, Ensemble, Linear Regression Terhadap Analisis Performa Pelajar SMA”. Innovative: Journal Of Social Science Research, vol. 3, no. 2, 13880–13892, 2023.
H. Rajaguru, “Analysis of Decision Tree and K-Nearest Neighbor Algorithm in the Classification of Breast Cancer”, Asian Pacific journal of cancer prevention: APJCP, vol. 20, no. 12, 3777–3781, 2019.
S. Wiyono, and T. Abidin, “Implementation of K-Nearest Neighbour (KNN) Algorithm to Predict Student’s Performance”, Jurnal SIMETRIS, vol. 9, no. 2, pp. 873-878, 2018.
H. Priatmojo, at. All. “Perbandingan Klasifikasi Tingkat Penjualan Buah di Supermarket dengan Pendekatan Algoritma Decision Tree, Naïve Bayes dan K-Nearest Neighbor”, Jurnal INSAN (Journal of Information Systems Management Innovation), vol. 3, no. 1, pp. 21-28, 2023.
A.D.R. Wibisono at all. “Comparison of K-Nearest Neighbor and Decision Tree Methods using Principal Component Analysis Technique in Heart Disease Classification”, ijodas, vol. 4, no. 2, pp. 87-96, Jul. 2023.
A. Mayssara and A. Hassanin, “Klasifikasi Predikat Kelulusan Mahasiswa dengan Metode CRISP-DM dan Naïve Bayes pada Fakultas Komunikasi dan Informatika Universitas Muhammadiyah Surakarta”, Paper Knowledge Toward a Media History of Documents, vol. 16, 2014.
How To Cite This :
Refbacks
- There are currently no refbacks.
