Analisis Sentimen Pada Pembelajaran Daring Menggunakan Metode K-Nearest Neightbour
Studi Kasus : Sma Negeri 3 Cikampek
Abstract
Corona Virus Disease-2019 has been rampant throughout the world, including in Indonesia. Covid-19 has greatly affected several sectors, one of which is the education sector. The Indonesian government itself implements a policy of courageous learning or distance learning which is carried out from their respective homes. SMA Negeri 3 Cikampek is one of the schools that implements bold learning, this bold learning affects the achievement of learning outcomes. Various students from this bold learning, there are those who agree that this bold learning has an effect on the achievement of learning outcomes and some even give a response that does not agree because it has no effect. For this reason, data mining is applied, especially text mining with the K-Nearest Neighbor algorithm to analyze various student responses to bold learning. The data used is a questionnaire data as much as 592 data. Before the data mining stage, the data is divided into 80% of the training data and 20% of the testing data. The classification with K-Nearest Neighbor quality is 85.35% accuracy, 81.19% precision, 92.42% recall and Auc is 0.902. Based on the quantity of negative classes which are more than positive classes, it is known that students will not agree to bold learning because it affects the achievement of learning outcomes.
Keyword: Text mining, Online Learning , Covid-19, K-Nearest Neightbour.
References
Andika, L. A. (2019). Analisis Sentimen Masyarakat terhadap Hasil Quick Count Pemilihan Presiden Indonesia 2019 pada Media Sosial Twitter Menggunakan Metode Naive Bayes Classifier. Indonesian Journal of Applied Statistics, 34.
Andreas, D., Arieshanti, I., & Zainal Arifin, A. (2020). IMPLEMENTASI ALGORITMA K-NEAREST NEIGHBOUR. 1-7.
Arviana, G. N. (2022, Februari Senin). Tableu. Retrieved from Glints: https://glints.com/id/lowongan/tableau- adalah
Azwar, M. K., & Setiati, S. (2020). COVID-19 and Indonesia. 22-25.
B, L. (2015). Sentiment Analysis: Mining Opinions, Sentiments, and Emotions , University of Illinois at Chicago. Cambridge University Press.
Bersiap tameng ekonomi untuk dampak wabah corona. (2022, Februari Senin). Retrieved from Kompas.com: https://jeo.kompas.com/bersiap-tameng-ekonomi-untuk-dampak-wabah-corona
Bramer, M. (2007). Principles of Data Mining. Springer Science.
dkk, P. (2020). Studi Eksploratif Dampak Pandemi COVID-19 Terhadap . Journal of Education, , Volume 2 No. 1.
Fahrizqi, E. B. (2021). The Learning Motivation and Physical Fitness of University Student During the Implementations of Covid-19 Pandemic . JUARA: Jurnal Olahraga, 88-100.
Fajrin, A. A. (2018). Penerapan Data Mining untuk Analisis Pola Pembelian Konsumen dengan Algoritma Fp- Growth pada Data . Kumpulan JurnaL Ilmu Komputer (KLIK), 27-36.
Fatyanosa, T. N. (2017). Classification method comparison on Indonesian social media sentiment analysis. International Conference on Sustainable Information Engineering and Technology (SIET), 24-25.
hafira, N. H. (2020). Persepsi Mahasiswa Terhadap Perkuliahan Daring Sebagai Sarana Pembelajaran. Jurnal Bisnis Dan Kajian Strategi Manajemen.
Hidayat. (2017). ANALISIS HAMBATAN BELAJAR MAHASISWA PADA MATA KULIAH STATISTIKA. Jurnal JPPM.
Indonesia, K. K. (2022, Februari Senin). Profil Kesehatan . Retrieved from Kementerian Kesehatan Republik Indonesia.
J. Iawe. Han, M. K.-H.-F. (2012). Data Mining in Healthcare and Biomedicine. A Survey of The Literature, 2431–2448.
Kristina, E. (2011). Penerapan Metode Statistik Dan Average Energy Untuk Menguji Tingkat Kemiripan Pada Identifikasi Suara. Jurnal Informatika, Vol 7, No 1.
Kusrini. (2009). Algoritma Data Mining. Yogyakarta: Penerbit Andi.
Larose, D. T. (2005). Discovering Knowledge in Data Mining An Introduction to Data Mining. Wiley Interscience.
Monika, N. &. (2013). Analisis Chi-Square dan Transformasi Data Ordinal ke Data Interval Menggunakan Methods Of Succesive Interval . Eksponensial,, 85-90.
Negara, A. B. (2020). Analisis Sentimen Maskapai Penerbangan Menggunakan Metode Naive Bayes dan Seleksi Fitur Information Gain. Jurnal Teknologi Informasi Dan Ilmu Komputer, 599.
Nuramilus, S. R. (2017). Sistem Pakar Diagnosis Penyakit Demam: DBD, Malaria dan Tifoid Menggunakan Metode K-Nearest . Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer, 426-435.
Paramita, A. (2016). Perancangan Data Warehouse pada Perpustakaan Yayasan Lentera Insan. STRING (Satuan Tulisan Riset Dan Inovasi Teknologi), 83-88.
Putra, R. R. (2018). Implementasi Data Mining Pemilihan Pelanggan Potensial Menggunakan Algoritma K-Means. Journal of Information Technology and Computer Science (INTECOMS), 72-77.
Putrianti, R. P., Kurniati, A., & Agustin, D. (2019, August). Implementasi Algoritma K- Nearest Neighbor Terhadap Analisis Sentimen Review Restoran Dengan Teks Bahasa Indonesia. In Seminar Nasional Aplikasi Teknologi Informasi (SNATi).
R. Akbar, R. O. (2017). Implementasi Business Intelligence Un-tuk Menentukan Tingkat. Jurnal Ilmiah Informati-ka, 135-138.
Sani, R. R. (2016). Pengembangan Aplikasi Penentuan Tema Tugas Akhir Berdasarkan Data Abstrak Menggunakan . Prosiding seminar Nasional Multi Disiplin Ilmu & Call For Papers, 103-111.
Santoso, B. (2007). Data Mining Teknik Pemanfaatan Data untuk Keperluan Bisnis (1 ed). Yogyakarta: Graha Ilmu.
Syakuro, A. (2017). Analisis Sentimen Masyarakat Terhadap E-Commerce Pada Media Sosial Menggunakan Metode Naïve Bayes Classifier ( NBC ) Dengan Seleksi Fitur Information Gain ( IG ). Skripsi, 1-89.
Waryanto, N. (2006). Online learning sebagai salah satu inovasi pembelajaran. Jurnal Matematika, 10-23.
Yunianto, T. K. (2022, Februari Senin). Survei SMRC: 92% Siswa Memiliki Banyak Masalah dalam Belajar Daring. Retrieved from katadata.co.id: https://katadata.co.id/ekarina/berita/5f3bc04617957/survei-smrc-92-siswa-memiliki-banyak-masalah-dalam-belajar-daring
Yustanti, W. (2012). Algoritma K-Nearest Neighbour untuk Memprediksi Harga Jual Tanah. Jurnal Matematika Statistika & Computing, 57-68.
Zulkifli, A. (2016). Metode C45 Untuk Mengklarifikasi Pelanggan Perusahaan Telekomunikasi Seluler. Journal Of Computer Science, 65-76.
