ANALISIS SENTIMEN PERBANDINGAN KEPUASAN PELANGGAN TERHADAP APLIKASI BIMBINGAN BELAJAR PADA MEDIA SOSIAL TWITTER MENGGUNAKAN METODE NAIVE BAYES

Ilham Ellya Khahar, . (2025) ANALISIS SENTIMEN PERBANDINGAN KEPUASAN PELANGGAN TERHADAP APLIKASI BIMBINGAN BELAJAR PADA MEDIA SOSIAL TWITTER MENGGUNAKAN METODE NAIVE BAYES. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.

[img] Text
ABSTRAK.pdf
Download (209kB)
[img] Text
AWAL.pdf
Download (753kB)
[img] Text
BAB 1.pdf
Restricted to Repository UPNVJ Only
Download (222kB)
[img] Text
BAB 2.pdf
Restricted to Repository UPNVJ Only
Download (295kB)
[img] Text
BAB 3.pdf
Restricted to Repository UPNVJ Only
Download (723kB)
[img] Text
BAB 4.pdf
Restricted to Repository UPNVJ Only
Download (2MB)
[img] Text
BAB 5.pdf
Download (172kB)
[img] Text
DAFTAR PUSTAKA.pdf
Download (238kB)
[img] Text
RIWAYAT HIDUP.pdf
Restricted to Repository UPNVJ Only
Download (132kB)
[img] Text
LAMPIRAN.pdf
Restricted to Repository UPNVJ Only
Download (565kB)
[img] Text
HASIL PLAGIARISME.pdf
Restricted to Repository staff only
Download (12MB)
[img] Text
ARTIKEL KI.pdf
Restricted to Repository staff only
Download (198kB)

Abstract

The development of online tutoring applications in Indonesia is growing rapidly, with fierce competition among providers like Ruangguru, Pahamify, Quipper, and Cerebrum to deliver the best quality services. User opinions are often shared on social media, especially Twitter, making it a valuable source of data for analyzing customer sentiment. This study utilizes over 20,000 Indonesian-language tweets posted between July 1, 2021, and July 1, 2024, analyzed using the Naïve Bayes algorithm via Python in Google Colab, and visualized on a static website built with HTML, CSS, and JavaScript. The results show that Quipper has the highest positive sentiment (79.1%), followed by Cerebrum (64.0%), Ruangguru (60.4%), and Pahamify (32.7%). The Naïve Bayes model used performed best on Cerebrum's data with 95% accuracy, followed by Pahamify (93%), Quipper (83%), and Ruangguru (79%), demonstrating the model's ability to consistently classify user sentiments with adequate accuracy. This research provides valuable insights for developers to improve their services and help users choose applications that meet their needs.

Item Type: Thesis (Skripsi)
Additional Information: [No.Panggil: 2110314048] [Pembimbing: Silvia Anggraeni] [Penguji 1: Muhamad Alif Razi] [Penguji 2: Ferdyanto]
Uncontrolled Keywords: sentiment analysis, Naive Bayes, tutoring applications
Subjects: T Technology > T Technology (General)
Z Bibliography. Library Science. Information Resources > ZA Information resources > ZA4450 Databases
Divisions: Fakultas Teknik > Program Studi Teknik Elektro (S1)
Depositing User: ILHAM ELLYA KHAHAR
Date Deposited: 12 Feb 2025 04:59
Last Modified: 12 Feb 2025 04:59
URI: http://repository.upnvj.ac.id/id/eprint/35882

Actions (login required)

View Item View Item