ANALISIS SENTIMEN DI MEDIA SOSIAL TWITTER/X MENGENAI TAPERA DENGAN PERBANDINGAN METODE K-NEAREST NEIGHBOR (KNN) DAN SUPPORT VECTOR MACHINE (SVM)

TANTRI, AMANDA MUTIARA and Karim, Arman Suryadi (2025) ANALISIS SENTIMEN DI MEDIA SOSIAL TWITTER/X MENGENAI TAPERA DENGAN PERBANDINGAN METODE K-NEAREST NEIGHBOR (KNN) DAN SUPPORT VECTOR MACHINE (SVM). Skripsi thesis, INSTITUT INFORMATIKA DAN BISNIS DARMAJAYA.

[img] Text
cover.pdf
Download (143kB)
[img] Text
LEMBAR PERNYATAAN.pdf
Download (54kB)
[img] Text
HALAMAN PERSETUJUAN.pdf
Download (87kB)
[img] Text
HALAMAN PENGESAHAN.pdf
Download (91kB)
[img] Text
HALAMAN PERSEMBAHAN.pdf
Download (285kB)
[img] Text
HALAMAN MOTO.pdf
Download (139kB)
[img] Text
RIWAYAT HIDUP.pdf
Download (49kB)
[img] Text
ABSTRAK.pdf
Download (201kB)
[img] Text
PRAKATA.pdf
Download (72kB)
[img] Text
DAFTAR ISI.pdf
Download (193kB)
[img] Text
DAFTAR TABEL.pdf
Download (146kB)
[img] Text
DAFTAR GAMBAR.pdf
Download (79kB)
[img] Text
BAB I.pdf
Download (132kB)
[img] Text
BAB II.pdf
Download (229kB)
[img] Text
BAB III BARU.pdf
Download (131kB)
[img] Text
BAB IV.pdf
Download (1MB)
[img] Text
BAB V.pdf
Download (83kB)
[img] Text
DAFTAR PUSTAKA.pdf
Download (234kB)

Abstract

The Indonesian government has made changes to PP number 21 of 2024 concerning the implementation of Public Housing Savings (Tapera), this has caused debate among the public, especially users of the X/twitter platform. On this platform, people share their opinions and views on the Tapera policy. This study aims to analyze public sentiment on Twitter social media regarding the public housing savings policy (Tapera) by comparing two classification methods, namely K Nearest Neighbor (KNN) and Support Vector Machine (SVM). Data was collected through crawling using the Twitter API for 2366 tweets. Then Preprocessing was carried out including Cleaning and labeling sentiment (positive, negative, neutral). The results of the analysis showed that the majority of sentiment was neutral (91%), while positive sentiment (6%) and negative sentiment (2.9%). In terms of classification method performance, SVM showed higher accuracy (94%) than KNN (92.8%). The results show that SVM is more effective in analyzing public sentiment related to TAPERA on Twitter social media. Keywords— sentiment analysis,TAPERA,Twitter, K-Nearest Neighbor, Support Vector Machine

Item Type: Thesis (Skripsi)
Subjects: Ilmu Komputer
eSkripsi
Divisions: Skripsi/TA & PKPM/KP - Fakultas Ilmu Komputer > Sistem Informasi
Depositing User: amanda mutiara tantri
Date Deposited: 11 Sep 2025 03:54
Last Modified: 11 Sep 2025 03:54
URI: http://repo.darmajaya.ac.id/id/eprint/22671

Actions (login required)

View Item View Item