Analisa Kepuasan Mahasiswa Terhadap E-Learning Menggunakan Algoritma Support Vector Machine

Abstract

Learning activities in general that have been carried out are face-to-face learning, but due to the Covid-19 pandemic in Indonesia, learning activities have changed. Learning activities that were initially carried out face-to-face were replaced with e-learning. This of course makes students respond with various responses. Universities must be able to capture student responses well, whether students are satisfied or not with e-learning learning. Data collection used by distributing questionnaires to students. The type of data used in this study is primary data. Meanwhile, to find out how to analyze student satisfaction in this study, the Support Vector Machine (SVM) algorithm will be used. The results of the analysis using SVM accuracy value of 98.23% means that the SVM algorithm method can predict respondents who are satisfied and who are not satisfied correctly 98.23% of the total data. Precision is the ratio of true positive predictions compared to the overall predicted positive results so this SVM algorithm predicts respondents who are correctly satisfied by 95.65% compared to the overall predicted results are satisfied. Recall is the ratio of true positive predictions compared to the total number of true positive data. The SVM algorithm produces a recall value of 95.65%, meaning that the SVM algorithm predicts respondents who are predicted to be satisfied compared to all respondents who are actually satisfied.

Klasifikasi Kanker Payudara Menggunakan Algoritma SVM dengan Kernel RBF, Linier, dan Sigmoid

“…Proses klasifiksi diartikan sebagai proses memperoleh model untuk mengidentifikasi kelas data, apabila model telah diperoleh, model tersebut dapat digunakan untuk klasifikasi kelas data baru [4]. Support Vector Machine (SVM) merupakan salah satu algoritma klasifikasi (supervised learning) yang dapat menangani data berdimensi tinggi, selain itu algoritma ini juga dapat menangani klasifikasi untuk data-data non-linier yang tidak dapat dipisahkan secara linier [5]. Algoritma SVM sangat baik digunakan untuk klasifikasi biner, yakni klasifikasi dengan dua kelas keputusan.…”

Sentiment Analysis for Online Learning using The Lexicon-Based Method and The Support Vector Machine Algorithm

“…This research applies the SVM algorithm. In classification modeling, SVM has a more mature and clearer concept mathematically compared to other classification techniques [15]. This technique can also solve classification and regression problems with linear and nonlinear [16].…”