PERBANDINGAN KLASIFIKASI NAIVE BAYES DENGAN ATAU TANPA PARTICLE SWARM OPTIMIZATION UNTUK SELEKSI FITUR PADA ANALISIS SENTIMENT TERHADAP PERPRES NO 10 TAHUN 2021 TENTANG INVESTASI MIRAS PADA MEDIA SOSIAL TWITTER

Gilbert Panangian Doloksaribu, . (2023) PERBANDINGAN KLASIFIKASI NAIVE BAYES DENGAN ATAU TANPA PARTICLE SWARM OPTIMIZATION UNTUK SELEKSI FITUR PADA ANALISIS SENTIMENT TERHADAP PERPRES NO 10 TAHUN 2021 TENTANG INVESTASI MIRAS PADA MEDIA SOSIAL TWITTER. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.

[img] Text
ABSTRAK.pdf
Download (26kB)
[img] Text
Awal (2).pdf
Download (574kB)
[img] Text
BAB I.pdf
Download (92kB)
[img] Text
BAB II.pdf
Restricted to Repository UPNVJ Only
Download (263kB)
[img] Text
BAB III.pdf
Restricted to Repository UPNVJ Only
Download (263kB)
[img] Text
BAB IV.pdf
Restricted to Repository UPNVJ Only
Download (1MB)
[img] Text
BAB V.pdf
Download (77kB)
[img] Text
DAFTAR PUSTAKA.pdf
Download (83kB)
[img] Text
DAFTAR RIWAYAT HIDUP.pdf
Restricted to Repository UPNVJ Only
Download (98kB)
[img] Text
LAMPIRAN.pdf
Restricted to Repository UPNVJ Only
Download (609kB)
[img] Text
Lampiran Similarity Index.pdf
Restricted to Repository staff only
Download (397kB)
[img] Text
KARYA ILMIAH.pdf
Restricted to Repository staff only
Download (581kB)

Abstract

Social media is one of the forms of information and communication technology development. Social networking is a space where you can communicate with each other, and one of the largest social media platforms is Twitter. President Joko Widodo issued Presidential Regulation No. 10 of 2021 regarding investment in the alcoholic beverage industry, which invited both pro and contra opinions. This research was conducted to classify public comments on Presidential Regulation No. 10 of 2021 using the Naive Bayes classification method. The tweet data obtained by crawling on Twitter with related keywords were transformed from unstructured data to structured data, and then the evaluation values between classifications were compared using Naïve Bayes with Naive Bayes classification using Particle Swarm Optimization (PSO) as feature selection to reduce irrelevant attributes in the classification process, thereby improving the accuracy value of the dataset. This study resulted in Naive Bayes classification accuracy values of 65% and Naive Bayes classification with PSO of 69% using iteration parameters 100 times. Evaluation measurements were performed using the Confusion Matrix method and showed an increase in accuracy and F1-Score values using PSO as the feature selection attribute.

Item Type: Thesis (Skripsi)
Additional Information: [No Panggil : 1710511081] [Pembimbing : Iin Ernawati ] [Penguji 1 : Didit Widiyanto] [Penguji 2 : Ria Astriratma]
Uncontrolled Keywords: Twitter, Sentiment Analysis, Presidential Regulation No. 10 of 2021, Naive Bayes Classifier, Particle Swarm Optimization
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions: Fakultas Ilmu Komputer > Program Studi Informatika (S1)
Depositing User: Gilbert Panangian Dolok Saribu
Date Deposited: 04 Sep 2023 02:27
Last Modified: 04 Sep 2023 02:27
URI: http://repository.upnvj.ac.id/id/eprint/24060

Actions (login required)

View Item View Item