SENTIMEN ANALISIS OPINI MASYARAKAT JAKARTA PADA KINERJA PEMERINTAH JAKARTA TERHADAP ISU TENGGELAMNYA JAKARTA MENGGUNAKAN ALGORITMA SUPPORT VECTOR MACHINE

Adithya Kharisma, . (2023) SENTIMEN ANALISIS OPINI MASYARAKAT JAKARTA PADA KINERJA PEMERINTAH JAKARTA TERHADAP ISU TENGGELAMNYA JAKARTA MENGGUNAKAN ALGORITMA SUPPORT VECTOR MACHINE. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.

[img] Text
ABSTRAK.pdf
Download (10kB)
[img] Text
AWAL.pdf
Download (603kB)
[img] Text
BAB 1.pdf
Download (91kB)
[img] Text
BAB 2.pdf
Restricted to Repository UPNVJ Only
Download (298kB)
[img] Text
BAB 3.pdf
Restricted to Repository UPNVJ Only
Download (203kB)
[img] Text
BAB 4.pdf
Restricted to Repository UPNVJ Only
Download (1MB)
[img] Text
BAB 5.pdf
Download (80kB)
[img] Text
DAFTAR PUSTAKA.pdf
Download (83kB)
[img] Text
RIWAYAT HIDUP.pdf
Restricted to Repository UPNVJ Only
Download (78kB)
[img] Text
LAMPIRAN.pdf
Restricted to Repository UPNVJ Only
Download (184kB)
[img] Text
HASIL PLAGIARISME.pdf
Restricted to Repository staff only
Download (12MB)
[img] Text
ARTIKEL KI.pdf
Restricted to Repository staff only
Download (117kB)

Abstract

The news about the sinking issue of Jakarta is no longer something new. The sinking issue of Jakarta has sparked various opinions among Indonesian society, especially the people of Jakarta. These opinions have generated pros and cons among the public. Such opinions can be used as a measure to gauge the satisfaction of the people regarding the performance of the Jakarta government. Due to the abundance of opinions, it poses a challenge of how to transform these opinions into useful data for the support vector machine model. Therefore, sentiment analysis is conducted to assess the satisfaction of the people towards the government's performance. The sentiment analysis consists of two labels, namely positive and negative. The sentiments are then processed using Natural Language Processing or text mining and transformed into three datasets: the original dataset, undersampling dataset, and oversampling dataset. These three datasets are used to build support vector machine models with different parameter values for cost and kernel. After building the models, evaluation is performed using a confusion matrix. The highest evaluation result among the three dataset models is the oversampling dataset with an average accuracy of 0.9359, precision of 0.9676, recall of 0.9003, specificity of 0.9703, and F1-score of 0.9326.

Item Type: Thesis (Skripsi)
Additional Information: [No.Panggil: 1910511039] [Pembimbing: Iin Ernawati] [Penguji 1: Ermatita] [Penguji 2: Yuni Widiastiwi]
Uncontrolled Keywords: Sentiment Analysis, Jakarta Sinking Issue, Support Vector Machine, Text Mining, confusion matrix.
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions: Fakultas Ilmu Komputer > Program Studi Informatika (S1)
Depositing User: Adithya Kharisma
Date Deposited: 02 Aug 2023 06:56
Last Modified: 02 Aug 2023 06:56
URI: http://repository.upnvj.ac.id/id/eprint/25115

Actions (login required)

View Item View Item