The Sriwijaya University Library

  • Home
  • Information
  • News
  • Help
  • Login
  • Librarian
  • Member Area
  • Select Language :
    Arabic Bengali Brazilian Portuguese English Espanol German Indonesian Japanese Malay Persian Russian Thai Turkish Urdu

Search by :

ALL Author Subject ISBN/ISSN Advanced Search

Last search:

{{tmpObj[k].text}}
Image of PERBANDINGAN RANDOM MAJORITY UNDERSAMPLING DAN RANDOM OVERSAMPLING PADA ANALISIS SENTIMEN MENGGUNAKAN BERT UNTUK ULASAN ROBLOX
Bookmark Share

Skripsi

PERBANDINGAN RANDOM MAJORITY UNDERSAMPLING DAN RANDOM OVERSAMPLING PADA ANALISIS SENTIMEN MENGGUNAKAN BERT UNTUK ULASAN ROBLOX

Hidayahni, Putri - Personal Name;

Game application reviews, such as those for Roblox, often exhibit significant class imbalance, where positively labeled reviews vastly outnumber negative ones. This study aims to compare the effectiveness of Random Majority Under-sampling (RMU) and Random Over-sampling (ROS) data balancing techniques on the Bidirectional Encoder Representations from Transformers (BERT) architecture for automatic sentiment classification. The initial dataset was sourced from 435,826 Roblox user reviews, which were subsequently extracted to form a final sample of 11,970 positive and 2,961 negative reviews. The test results from nine experimental scenarios demonstrate that the application of RMU triggers the loss of linguistic information and transforms the model into a single-class predictor (F1-score 0.444981). Conversely, the best configuration was achieved by BERT+ROS (Scenario 9, learning rate 5e-05), which successfully recorded an accuracy of 0.959812, precision of 0.926702, recall of 0.952050, and F1-score of 0.938640. Based on these findings, it is concluded that the BERT architecture optimized with the ROS technique is the most superior approach for imbalanced text-based sentiment analysis.


Availability
#
Central Library (Reference) T1990722026
T199072
Available but not for loan - Not for Loan
Detail Information
Series Title
-
Call Number
T1990722026
Publisher
Indralaya : Prodi Teknik Informatika, Fakultas Ilmu Komputer Universitas Sriwijaya., 2026
Collation
xiv, 90 hlm.; ilus.; tab.; 29 cm.
Language
Indonesia
ISBN/ISSN
-
Classification
006.312 07
Content Type
Text
Media Type
unmediated
Carrier Type
-
Edition
-
Subject(s)
Prodi Teknik Informatika
Klasifikasi Teks
Specific Detail Info
-
Statement of Responsibility
KA
Other version/related
TitleEditionLanguage
KLASIFIKASI TEKS PEMIKIRAN BUNUH DIRI MENGGUNAKAN BIDIRECTIONAL LONG SHORT TERM MEMORY-id
ANALISIS PERBANDINGAN KINERJA CONVOLUTIONAL NEURAL NETWORK DAN LONG SHORT-TERM MEMORY UNTUK KLASIFIKASI TEKS JUDI ONLINEid
File Attachment
  • PERBANDINGAN RANDOM MAJORITY UNDERSAMPLING DAN RANDOM OVERSAMPLING PADA ANALISIS SENTIMEN MENGGUNAKAN BERT UNTUK ULASAN ROBLOX
Comments

You must be logged in to post a comment

The Sriwijaya University Library
  • Information
  • Services
  • Librarian
  • Member Area

About Us

As a complete Library Management System, SLiMS (Senayan Library Management System) has many features that will help libraries and librarians to do their job easily and quickly. Follow this link to show some features provided by SLiMS.

Search

start it by typing one or more keywords for title, author or subject

Keep SLiMS Alive Want to Contribute?

© 2026 — Senayan Developer Community

Powered by SLiMS
Select the topic you are interested in
  • Computer Science, Information & General Works
  • Philosophy & Psychology
  • Religion
  • Social Sciences
  • Language
  • Pure Science
  • Applied Sciences
  • Art & Recreation
  • Literature
  • History & Geography
Icons made by Freepik from www.flaticon.com
Advanced Search
Where do you want to share?