ANALISIS SENTIMEN PADA ULASAN APLIKASI VIDEO CONFERENCE MENGGUNAKAN NAIVE BAYES

SUHENDRA, MICHAEL (2021) ANALISIS SENTIMEN PADA ULASAN APLIKASI VIDEO CONFERENCE MENGGUNAKAN NAIVE BAYES. Masters thesis, UNIVERSITAS MA CHUNG.

	Text 05 311610012_ABSTRAK.pdf Download (37kB)
	Text 09 311610012_BAB 1.pdf Download (150kB)
	Text 10 311610012_BAB 2.pdf Download (733kB)
	Text 11 311610012_BAB 3.pdf Restricted to Registered users only Download (155kB)
	Text 12 311610012_BAB 4.pdf Restricted to Registered users only Download (790kB)
	Text 13 311610012_BAB 5.pdf Download (67kB)
	Text 14 311610012_DAFTAR PUSTAKA.pdf Download (77kB)

Abstract

Video conferencing is an application that allows users to communicate, conduct meetings, learn and share information. Until now, many video conferencing applications have been used, such as Zoom, Google Meet, and Microsoft Teams. Of course, in every application there is a review of the application used. With reviews, other users can consider and find out more about the applications used. However, because the number of reviews on the internet is very
large, a sentiment analysis is needed to be able to classify sentiment into positive, neutral, or negative sentiments. In this study, 400 data reviews for each application
were taken from the Play Store. The review data uses Indonesian and is taken based on the latest application version. Before being used, the data needs to be labeled
and preprocessed in order to be able to classify sentiments. The process uses TF�IDF word weighting, Naïve Bayes classification, and confusion matrix as evaluation materials. Later, the review data from the three applications will be processed separately. From the results of the sentiment analysis test using 100 test data, a comparison of the number of positive sentiments was obtained between the actual class (55 reviews for Zoom, 52 reviews for Google Meet, and 47 reviews for Microsoft Teams) and the prediction class (90 reviews, 76 reviews, and 71 reviews).
In addition, the average accuracy value of the three applications is 69%.Keywords: video conference, sentiment analysis, TF-IDF, naïve bayes, confusion matrix

Item Type:	Thesis (Masters)
Additional Information:	TUGAS AKHIR
Subjects:	T Technology > T Technology (General)
Divisions:	Fakultas Teknologi dan Desain > S1 Teknik Informatika
Depositing User:	Surya
Date Deposited:	19 Nov 2024 03:26
Last Modified:	19 Nov 2024 03:26
URI:	http://repository.machung.ac.id/id/eprint/478

Actions (login required)

View Item