KLASIFIKASI SENTIMEN TWITTER MENGENAI PERSEPSI MASYARAKAT TERHADAP PRESIDENSI G20 MENGGUNAKAN SUPPORT VECTOR MACHINE

Yohanes Billy Putera, . (2023) KLASIFIKASI SENTIMEN TWITTER MENGENAI PERSEPSI MASYARAKAT TERHADAP PRESIDENSI G20 MENGGUNAKAN SUPPORT VECTOR MACHINE. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.

[img] Text
ABSTRAK.pdf
Download (37kB)
[img] Text
AWAL.pdf
Download (492kB)
[img] Text
BAB I.pdf
Download (117kB)
[img] Text
BAB II.pdf
Restricted to Repository UPNVJ Only
Download (263kB)
[img] Text
BAB III.pdf
Restricted to Repository UPNVJ Only
Download (147kB)
[img] Text
BAB IV.pdf
Restricted to Repository UPNVJ Only
Download (487kB)
[img] Text
BAB V.pdf
Download (88kB)
[img] Text
DAFTAR PUSTAKA.pdf
Download (96kB)
[img] Text
RIWAYAT HIDUP.pdf
Restricted to Repository UPNVJ Only
Download (50kB)
[img] Text
LAMPIRAN.pdf
Restricted to Repository UPNVJ Only
Download (330kB)
[img] Text
HASIL PLAGIARISME.pdf
Restricted to Repository staff only
Download (1MB)
[img] Text
ARTIKEL KI.pdf
Restricted to Repository staff only
Download (426kB)

Abstract

This year, according to the stipulation of the 2020 Riyadh Summit, Indonesia was chosen to carry out the functions of the G20 presidency in 2022. The 2022 G20 Summit will be held on 30-31 October 2022 in Bali with President Joko Widodo as chairman of the conference. This is of course a topic that is widely discussed by Indonesian people, especially social media users. Indonesians who use social media are very active in sharing their views on something that is viral, such as the G20 Presidency in 2022. Various opinions can often be seen in the comments column on various social media platforms, one of which is Twitter. The comments that are there are not only positive comments, but there are also neutral and negative ones. Comments on Twitter can be processed into information in a certain way, namely sentiment classification. The classification is performed using the Support Vector Machine algorithm. From the data extracted with the Application Programming Interface (API) and data pre-processing, a total of 268 tweets were obtained which would be divided into three ratios of training data to test data, namely 60:40, 70:30 and 80:20 which were used as data for classification with the Support Vector Machine algorithm. The best accuracy results from the SVM classification are owned by the SVM model with a linear kernel for distribution ratios of 60:40 and 70:30 (77.78% and 81.48% respectively) and sigmoid kernels for distribution ratios of 70:30 and 80: 20 (respectively of 81.48% and 77.78%). The high accuracy of the linear and sigmoid kernels indicates that the SVM classifier can be used to classify sentiments about people's perceptions of the G20 Presidency.

Item Type: Thesis (Skripsi)
Additional Information: [No.Panggil: 1810511105] [Pembimbing 1: Yuni Widiastiwi] [Pembimbing 2: Ika Nurlaili Isnainiyah] [Penguji 1: Widya Cholil] [Penguji 2: Henki Bayu Seta]
Uncontrolled Keywords: Support Vector Machine, tweet, classification.
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
T Technology > T Technology (General)
Divisions: Fakultas Ilmu Komputer > Program Studi Informatika (S1)
Depositing User: Yohanes Billy Putera
Date Deposited: 16 Mar 2023 03:54
Last Modified: 16 Mar 2023 03:54
URI: http://repository.upnvj.ac.id/id/eprint/23909

Actions (login required)

View Item View Item