RIZKY, ZICO CAHYA (2025) ANALISIS SENTIMEN KOMENTAR PENGGUNA DI TWITTER TERHADAP LAYANAN INDIHOME MENGGUNAKAN ALGORITMA NAIVE BAYES. S1 thesis, Universitas Mercu Buana Jakarta.
|
Text (HAL COVER)
01 COVER.pdf Download (532kB) | Preview |
|
![]() |
Text (BAB I)
02 BAB 1.pdf Restricted to Registered users only Download (268kB) |
|
![]() |
Text (BAB II)
03 BAB 2.pdf Restricted to Registered users only Download (435kB) |
|
![]() |
Text (BAB III)
04 BAB 3.pdf Restricted to Registered users only Download (349kB) |
|
![]() |
Text (BAB IV)
05 BAB 4.pdf Restricted to Registered users only Download (788kB) |
|
![]() |
Text (BAB V)
06 BAB 5.pdf Restricted to Registered users only Download (258kB) |
|
![]() |
Text (DAFTAR PUSTAKA)
07 DAFTAR PUSTAKA.pdf Restricted to Registered users only Download (238kB) |
|
![]() |
Text (LAMPIRAN)
08 LAMPIRAN.pdf Restricted to Registered users only Download (572kB) |
Abstract
Sentiment analysis is an essential approach to understanding public opinion toward a service, including digital services such as IndiHome. This study aims to analyze user sentiment on Twitter regarding the IndiHome service using the Naive Bayes algorithm. The data was collected through a crawling process on the Twitter platform, resulting in 700+ user comments to be analyzed. The research method involves several stages, including data preprocessing, manual sentiment labeling, application of the Naive Bayes algorithm for sentiment classification (positive and negative), and model evaluation using a confusion matrix. The results of this study show that the Naive Bayes algorithm achieved an accuracy of 93.69% in classifying user comments. However, the model was only able to recognize negative sentiments optimally with a recall value of 100%, while positive sentiment recognition had a recall of 0%, indicating an imbalanced dataset. Nevertheless, these results still provide valuable insights into public opinion trends regarding the IndiHome service. Keywords: sentiment analysis, Naive Bayes, Twitter, IndiHome, text classification Analisis sentimen merupakan pendekatan penting dalam memahami opini publik terhadap suatu layanan, termasuk layanan digital seperti IndiHome. Penelitian ini bertujuan untuk menganalisis sentimen komentar pengguna di Twitter terhadap layanan IndiHome dengan menggunakan algoritma Naive Bayes. Data diperoleh melalui proses crawling pada platform Twitter, dengan jumlah sebanyak 700+ komentar yang dikumpulkan untuk dianalisis. Metode penelitian ini mencakup tahapan preprocessing data, pelabelan sentimen secara manual, penerapan algoritma Naive Bayes untuk klasifikasi sentimen positif dan negatif, serta evaluasi model menggunakan confusion matrix. Hasil dari penelitian menunjukkan bahwa algoritma Naive Bayes menghasilkan tingkat akurasi sebesar 93,69% dalam mengklasifikasikan komentar pengguna. Namun, model hanya mampu mengenali sentimen negatif secara optimal dengan nilai recall sebesar 100%, sedangkan untuk sentimen positif recall-nya sebesar 0%, yang menunjukkan adanya ketidakseimbangan distribusi data (imbalanced dataset). Meskipun demikian, hasil ini tetap memberikan gambaran yang bermanfaat dalam menganalisis opini publik secara umum terhadap layanan IndiHome. Kata Kunci: analisis sentimen, Naive Bayes, Twitter, IndiHome, klasifikasi teks
Actions (login required)
![]() |
View Item |