Perbandingan Ulasan Zoom Cloud Meetings Dan Google Meet Menggunakan Support Vector Machine

Andiva, Friday Angeline (2021) Perbandingan Ulasan Zoom Cloud Meetings Dan Google Meet Menggunakan Support Vector Machine. Undergraduate thesis, Institut Teknologi Sepuluh Nopember.

[thumbnail of 10611710000005-Undergraduate_Thesis.pdf] Text
10611710000005-Undergraduate_Thesis.pdf - Accepted Version
Restricted to Repository staff only until 1 October 2023.

Download (1MB) | Request a copy

Abstract

Aplikasi Zoom Cloud Meetings dan Google Meet sangat sering digunakan pada masa pandemi covid-19 sebagai media untuk tatap muka secara daring (dalam jaringan) yang dapat mendukung hingga ratusan partisipan, namun dua aplikasi tersebut memiliki rating yang cukup kecil yaitu 3,8 dari 5 bintang untuk aplikasi Zoom Cloud Meetings dan 3,5 dari 5 bintang untuk aplikasi Google Meet. Penelitian ini bertujuan untuk menganalisis sentimen menggunakan Support Vector Machine (SVM) pada opini-opini masyarakat tentang kedua aplikasi tersebut yaitu merupakan opini positif atau negatif. Support Vector Machine (SVM) digunakan karena metode ini sangat cepat dan efektif pada klasifikasi data teks. Hasil penelitian menunjukkan bahwa aplikasi Zoom Cloud Meetings memiliki presentase ulasan positif lebih besar dibandingkan ulasan negatif, sedangkan untuk aplikasi Google Meet memiliki presentase ulasan negatif lebih besar dari pada ulasan positif. Ketepatan klasifikasi dilihat dari nilai akurasi yang menunjukkan bahwa proporsi ulasan teridentifikasi dengan tepat, nilai specificity yang menunjukkan bahwa proporsi true positive yang diidentifikasi dengan benar, nilai G-Mean yang menunjukkan proporsi metode svm dapat memisahkan kelas positif dan negatif dengan tepat, dan nilai AUC yang menunjukkan proporsi kinerja pengklasifikasian ulasan pada aplikasi Google Meet memiliki proporsi nilai lebih besar dari pada aplikasi Zoom Cloud Meetings.
===============================================================================================
The Zoom Cloud Meetings and Google Meet applications are very often used during the covid-19 pandemic as a medium for face-to-face online (on the network) that can support up to hundreds of participants. However, the two applications have a fairly small rating, namely 3.8 out of 5 stars for the Zoom Cloud Meetings application and 3.5 out of 5 stars for the Google Meet application. This research wants to analyze sentiment using the Support Vector Machine (SVM) on public opinions about the two applications, which are positive or negative opinions. Support Vector Machine (SVM) is used because this method is very fast and effective in classifying text data. The results show that the Zoom Cloud Meetings application has a higher percentage of positive reviews than negative reviews, while the Google Meet application has a higher percentage of negative reviews than positive reviews. The accuracy value indicating that the proportion of reviews was identified correctly, a specificity value indicating that the proportion of true positive were identified correctly, a G-Mean value indicating the proportion of the svm method to separate positive and negative classes correctly, and an AUC value indicating the proportion of review classification performance in the Google Meet application has a greater value proportion than the Zoom Cloud Meetings application.

Item Type: Thesis (Undergraduate)
Uncontrolled Keywords: Google Meet, Support Vector Machine (SVM), Zoom Cloud Meetings Google Meet, Support Vector Machine (SVM), Zoom Cloud Meetings
Subjects: Q Science > QA Mathematics > QA76.9.D343 Data mining. Querying (Computer science)
R Medicine > RA Public aspects of medicine > RA644.C67 COVID-19 (Disease)
Divisions: Faculty of Science and Data Analytics (SCIENTICS) > Statistics > 49201-(S1) Undergraduate Thesis
Depositing User: Friday Angeline Andiva
Date Deposited: 14 Aug 2021 15:07
Last Modified: 14 Aug 2021 15:07
URI: http://repository.its.ac.id/id/eprint/86243

Actions (login required)

View Item View Item