Klasifikasi Siswa Slow Learner untuk Mendukung Sekolah dalam Meningkatkan Pemahaman Siswa Menggunakan Algoritma Naïve Bayes

Penulis

Abdul Harris Wicaksono, Ahmad Afif Supianto, Satrio Hadi Wijoyo, Didik Krisnandi, Ana Heryana

Abstrak

Tidak semua siswa sekolah bisa menangkap materi dengan kemampuan yang sama dikarenakan tingkat kecerdasan dan kemampuan belajar setiap anak berbeda - beda. Ada siswa yang kemampuan belajarnya rendah sehingga lambat dalam memahami materi yang biasa disebut sebagai slow learner. Siswa slow learner ini perlu perlakuan yg khusus supaya dapat memahami materi seperti siswa lainnya. Siswa slow learner yang tidak terdeteksi dapat memperlambat kegiatan belajar mengajar karena guru harus mengulang kembali menjelaskan materi untuk membuat siswa memahami materi tersebut. Penelitian ini bertujuan untuk mengklasifikasikan siswa slow learner dan non slow learner dan menghasilkan visualisasi dashboard yang dapat digunakan untuk membantu sekolah. Penelitian ini mengangkat studi kasus siswa kelas XI dan XII SMA Tunas Luhur yang berjumlah 89 siswa.  Penelitian ini menggunakan algoritma naive bayes untuk klasifikasi dan cross validation 10 folds sebagai metode pengujian. Hasil pengujian didapatkan nilai akurasi 0.92857, precison  0.94736, recall 0.97297 , dan F-measure 0.96 serta hasil pengujian visualisasi dashboard menggunakan kuesioner System Usability Scale yang menghasilkan skor 71.75 atau acceptable. Algoritma naïve bayes  berhasil mengklasifikasikan siswa slow learner dan non slow learner dengan baik, dan visualisasi dashboard bisa diterima dengan baik oleh pihak sekolah.

 

Abstract

Not all school students can capture material with the same abilities because each child's level of intelligence and learning ability are different. There are students whose learning ability is low so that it is slow in understanding the material commonly referred to as slow learner. These slow learner students need special treatment in order to understand the material like other students. Undetectable slow learner students can slow down teaching and learning activities because teachers have to redo explain the material to make students understand the material. This study aims to classify slow learner and non slow learner students and produce dashboard visualizations that can be used to help schools. This study raised the case study of grade XI and XII students of Tunas Luhur High School which amounted to 89 students.  The study used naive bayes algorithms for classification and cross validation of 10 folds as a testing method. The test result obtained an accuracy score of 0.92857, precison of 0.94736, recall of 0.97297 , and F-measure of 0.96 and dashboard visualization test results using the System Usability Scale questionnaire which resulted in a score of 71.75 or acceptable. Bayes' naïve algorithm successfully classifies slow learner and non-slow learner students well, and dashboard visualization is well received by the school.


Teks Lengkap:

PDF

Referensi


ALUJA, ANTON dan ANGEL BLANCH. Socialized Personality, Scholastic Aptitudes, Study Habits, and Academic Achievement: Exploring the Link. European Journal of Psychological Assessment, 2004. [Online] Available at : http://web.udl.es/usuaris/e7806312/grup/aaluja-archi/arti_aluja/pu_47.pdf [Diakses 12 Oktober 2020].Gen, M. & Cheng, R. 2000. Genetic Algorithms and Engineering Optimization. John Wiley & Sons, Inc., New York.

ADEBAYO, A. O. C. M. S., 2019. Classification Techniques on the Analysis of Student's Performance. Global Scientific, 7(4), pp. 79-95.

BROOKE, J., 2013. SUS: A Retrospective. Journal of Usability Studies, VIII(2), pp. 22-40.

BUSTAMI, 2014. Penerapan Algoritma Naïve Bayes Untuk Mengklasifikasi Data Nasabah Asuransi. Jurnal Informatika. 8(1), pp. 884-898.

CAHYA, R. A, ADIMANGGALA, D and SUPIANTO, A. A. 2019. Deep Feature Weighting Based on Genetic Algorithm and Naïve Bayes for Twitter Sentiment Analysis. International Conference on Sustainable Information Engineering and Technology (SIET), pp. 326-331, doi: 10.1109/SIET48054.2019.8986107

DARNISA, A. et al., 2019. Perbandingan Normalisasi Data Untuk Klasifikasi Wine Menggunakan Algoritma K-Nn. CESS (Journal of Computer Engineering System and Science), 4(1), pp. 78.82.

DESTUARDI & SURYA, S. 2009. Klasifikasi Emosi Untuk Teks Bahasa Indonesia Menggunakan Metode Naive bayes. Teknik Elektron, Institut Teknologi Sepuluh Nopember, Surabaya.

FHYLAYLI, S. U., 2019. Prediksi Tingkat Pemahaman Siswa Dalam Materi Pelajaran Bahasa Indonesia Menggunakan Naive bayes Dengan Seleksi Fitur Information Gain. Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer, 3(3), pp. 2154-2159.

JAIN, Y., BHANDERE, S., 2014. Min Max Normalization Based Data Perturbation Method for Privacy Protection. International Journal of Computer & Communication Technology (IJCCT). 3(4), pp. 45-50.

KAUR, P., SINGH, M. & JOSAN, G. S., 2015. Classification and prediction based data mining algorithms to predict slow learners in education sector. Procedia Computer Science, Volume 57, pp. 500-508.

MENDEZABAL, MARIE JEAN N. Study Habits and Attitudes: The Road to Academic Success. International Journal of Applied Research and Studies, 2013. [Online] Available at : http://ijars.in/iJARS% 20309.pdf [Diakses 12 Oktober 2020].

RANA & KAUSAR, 2011. Comparison of Study Habits and Academic Performance of Pakistani British and White British Students. Pakistan Journal of Social and Clinical Psychology, Volume 9, pp. 21-26.

SCHUH, G. et al., 2019. Data Mining Definitions and Applications for the Management of Production Complexity. Procedia CIRP, Volume 81, pp. 874-879.

SHAW, S. R., 2005. Slow learners and mental health issues (up date) [Online] Available at: http://www.theguidancechannelzine.com [Diakes 20 Januari 2020].

TULLIS, T. & ALBERT, B., 2013. System Usability Scale. [Online] Available at: https://www.sciencedirect.com/topics/computer-science/system-usability-scale [Diakses 30 Januari 2020].

URSO, A. et al., 2019. Data Mining: Classification and Prediction. Encyclopedia of Bioinformatics and Computational Biology, Volume 1, pp. 384-402.

VASUDEVAN , A., 2017. Slow learners – Causes, problems and educational programmes. International Journal for Applied Research, 3(12), pp. 308-313.

VORA, P., 2009. Web Application Design Patterns. Burlington: Morgan Kaufmann.

WU, X., KUMAR, V. et al., 2008. Top 10 algorithms in data mining. Knowledge and Information Systems, 14(1), pp. 1-37.

YUSUF, M., 2018. Pengantar Ilmu Pendidikan. Cetakan 1 . Palopo : Lembaga Penerbit Kampus IAIN Palopo.¬¬¬




DOI: http://dx.doi.org/10.25126/jtiik.2022935609