Nadhifa Zhafira, . (2022) ANALISIS SENTIMEN TERHADAP LAYANAN INDIHOME PADA TWITTER DENGAN METODE KLASIFIKASI NAIVE BAYES DAN SELEKSI FITUR PARTICLE SWARM OPTIMIZATION. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.
![[img]](http://repository.upnvj.ac.id/style/images/fileicons/text.png) |
Text
ABSTRAK.pdf Download (494kB) |
|
Text
AWAL.pdf Download (993kB) |
|
Text
BAB 1.pdf Download (725kB) |
|
Text
BAB 2.pdf Restricted to Repository UPNVJ Only Download (946kB) |
|
Text
BAB 3.pdf Restricted to Repository UPNVJ Only Download (1MB) |
|
Text
BAB 4.pdf Restricted to Repository UPNVJ Only Download (1MB) |
|
Text
BAB 5.pdf Download (687kB) |
|
Text
DAFTAR PUSTAKA.pdf Download (573kB) |
|
Text
RIWAYAT HIDUP.pdf Restricted to Repository UPNVJ Only Download (380kB) |
|
Text
LAMPIRAN.pdf Restricted to Repository UPNVJ Only Download (534kB) |
|
Text
HASIL PLAGIARISME.pdf Restricted to Repository staff only Download (3MB) |
|
Text
ARTIKEL KI.pdf Restricted to Repository staff only Download (481kB) |
Abstract
In this digital era, the use of the internet in daily life has become an important part for most of the world's population, including in Indonesia. Internet users in Indonesia are always increasing every year and based on data for June 2021, Indonesia ranks third as the largest internet user in Asia. One of the Internet Service Providers (ISP) in Indonesia with the most users is IndiHome. Sentiment analysis is a method for processing information in the form of text data to be classified into positive or negative sentiments. The data used is 500 tweet data taken from 04 April 2022 to 11 May 2022. The classification process will use the Naïve Bayes algorithm and utilize feature selection with the Particle Swarm Optimization algorithm for optimization and improve the performance of the classification process, then comparisons will be made. In the first test, namely the classification process with a single Naïve Bayes algorithm, the accuracy value is 86%, the recall value is 84.78%, the precision value is 84.78%, and the f-1 score is 84.77%. The second test by adding the Particle Swarm Optimization feature selection obtained an accuracy value of 91.33%, a recall value of 91.67%, a precision value of 90.41%, and an f-1 score of 91.02%. Based on these results, the addition of the Particle Swarm Optimization feature selection for the classification process with Nave Bayes in this study had an effect and succeeded in improving the performance of the Naïve Bayes algorithm.
| Item Type: | Thesis (Skripsi) |
|---|---|
| Additional Information: | [No.Panggil: 1810511111] [Pembimbing 1: Catur Nugrahaeni] [Pembimbing 2: Ika Nurlaili Isnainiyah] [Penguji 1: Ermatita] [Penguji 2: Mayanda Mega Santoni] |
| Uncontrolled Keywords: | Naïve Bayes, PSO, Sentiment Analysis, Twitter |
| Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science Q Science > QA Mathematics > QA76 Computer software |
| Divisions: | Fakultas Ilmu Komputer > Program Studi Informatika (S1) |
| Depositing User: | Nadhifa Zhafira |
| Date Deposited: | 21 Sep 2022 03:44 |
| Last Modified: | 21 Sep 2022 03:44 |
| URI: | http://repository.upnvj.ac.id/id/eprint/19949 |
Actions (login required)
 |
View Item |