ANALISIS SENTIMEN BERBASIS ASPEK PADA ULASAN APLIKASI VIDIO DI GOOGLE PLAY STORE MENGGUNAKAN INDOBERT DAN LDA

Raafi, Alhadi (2024) ANALISIS SENTIMEN BERBASIS ASPEK PADA ULASAN APLIKASI VIDIO DI GOOGLE PLAY STORE MENGGUNAKAN INDOBERT DAN LDA. Undergraduate Thesis thesis, Institut Teknologi Telkom Purwokerto.

[img] Text
Cover.pdf
Download (836kB)
[img] Text
Abstrak.pdf
Download (38kB)
[img] Text
Abstract.pdf
Download (99kB)
[img] Text
BAB I.pdf
Download (122kB)
[img] Text
BAB II.pdf
Download (547kB)
[img] Text
BAB III.pdf
Download (350kB)
[img] Text
BAB IV.pdf
Restricted to Registered users only
Download (461kB)
[img] Text
BAB V.pdf
Download (108kB)
[img] Text
Lampiran.pdf
Restricted to Registered users only
Download (299kB)

Abstract

Vidio is one of the most popular online video streaming applications in Indonesia, with a monthly viewership reaching 60 million and around 3.5 million subscribers in the second quarter of 2022. However, not all customers are satisfied with Vidio’s services. This is evident from the critical or complaint-laden reviews written by users on the Google Play Store platform. This study aims to analyze aspect-based sentiment from these reviews using the pre-trained IndoBERT model for sentiment analysis and the Latent Dirichlet Allocation (LDA) model to identify sentimentrelated aspects in user reviews. The data used consists of 55,811 Indonesian-language reviews from the Google Play Store, covering the years 2016 to 2022. The study results show that the overall sentiment polarity is generally positive (62.6%). However, in 2022, there was a noted decrease in the number of positive reviews and an increase in negative reviews. The aspects influencing user opinions from 2016 to 2022 are divided into positive (content quality and variety, satisfaction with features, and streaming quality), negative (technical issues, ad interruptions, subscription services, and app performance), and neutral (transactions, access to paid content, and content availability and features) Keywords : Aspect-based sentiment analysis, reviews, IndoBERT, LDA, Vidio

Item Type: Thesis (Undergraduate Thesis)
Subjects: T Technology > T Technology (General)
Divisions: Faculty of Informatics > Data Science
Depositing User: repository staff
Date Deposited: 02 Oct 2024 09:00
Last Modified: 02 Oct 2024 09:00
URI: http://repository.ittelkom-pwt.ac.id/id/eprint/11396

Actions (login required)

View Item View Item
Repository IT Telkom Purwokerto is powered by EPrints 3 which is developed by the School of Electronics and Computer Science at the University of Southampton. More information and software credits.