KLASIFIKASI SENTIMEN REVIEW PENGGUNA PADA APLIKASI GOOGLE MEET MENGGUNAKAN PARTICLE SWARM OPTIMIZATION TERHADAP OPTIMASI METODE SUPPORT VECTOR MACHINE (SVM)

Hilda Harisa, . (2022) KLASIFIKASI SENTIMEN REVIEW PENGGUNA PADA APLIKASI GOOGLE MEET MENGGUNAKAN PARTICLE SWARM OPTIMIZATION TERHADAP OPTIMASI METODE SUPPORT VECTOR MACHINE (SVM). Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.

[img] Text
ABSTRAK.pdf
Download (11kB)
[img] Text
AWAL.pdf
Download (674kB)
[img] Text
BAB 1.pdf
Download (145kB)
[img] Text
BAB 2.pdf
Restricted to Repository UPNVJ Only
Download (434kB)
[img] Text
BAB 3.pdf
Restricted to Repository UPNVJ Only
Download (175kB)
[img] Text
BAB 4.pdf
Restricted to Repository UPNVJ Only
Download (689kB)
[img] Text
BAB 5.pdf
Download (234kB)
[img] Text
DAFTAR PUSTAKA.pdf
Download (384kB)
[img] Text
DAFTAR RIWAYAT HIDUP.pdf
Restricted to Repository UPNVJ Only
Download (139kB)
[img] Text
LAMPIRAN.pdf
Restricted to Repository UPNVJ Only
Download (521kB)
[img] Text
HASIL PLAGIARISME.pdf
Restricted to Repository staff only
Download (704kB)
[img] Text
ARTIKEL KI.pdf
Restricted to Repository staff only
Download (776kB)

Abstract

Since the coronavirus, a new policy has been implemented in Indonesia. This policy encourages students and workers to work from home virtually. Video conferencing applications can help in overcoming these problems, one of which is Google Meet. In the services provided, the application is certainly not perfect, it has advantages and disadvantages from the user's point of view. Therefore, this study will conduct sentiment analysis on the Google Meet application to provide information or evaluation of user responses through comment reviews, by classifying opinions into positive and negative opinions using the Support Vector Machine (SVM) and Particle Swarm Optimization (PSO) methods as feature selection method. The review data that has been obtained will be carried out data labeling and data cleaning before the text processing process, then the data is given a weight for each word with TF-IDF which will be used as a feature after which feature selection is carried out with PSO, then data is divided using 10-fold cross-validation and classified by the SVM method. The average results of the confusion matrix evaluation where the accuracy is 80%; precision is 84%; recall of 82% using the SVM method and 82% accuracy; 92% precision; 80% recall using the PSO.

Item Type: Thesis (Skripsi)
Additional Information: [No.Panggil: 1810511093] [Pembimbing 1; Iin Ernawati] [Pembimbing 2: Mayanda Mega Santoni] [Penguji 1: Ermatita] [Penguji 2: Nurul Chamidah]
Uncontrolled Keywords: Sentiment Analysis, Classification, Google Meet, Support Vector Machine (SVM), Particle Swarm Optimization (PSO)
Subjects: T Technology > T Technology (General)
Divisions: Fakultas Ilmu Komputer > Program Studi Informatika (S1)
Depositing User: Hilda Harisa
Date Deposited: 18 Aug 2022 06:59
Last Modified: 18 Aug 2022 06:59
URI: http://repository.upnvj.ac.id/id/eprint/19666

Actions (login required)

View Item View Item