Skripsi

EKSTRAKSI PENGETAHUAN DARI ULASAN APLIKASI CAPCUT MENGGUNAKAN METODE ANALISIS SENTIMEN BERBASIS ASPEK DAN METODE KLASIFIKASI

---

Indonesia is experiencing rapid technological development, especially in the use of the internet and editing platforms such as CapCut. These platforms allow video editing on various devices, but user satisfaction is not always guaranteed due to differences in individual experience. To understand users' opinions and perceptions of CapCut, this study uses Aspect-Based Sentiment Analysis (ABSA) and compares four machine learning algorithms-Naïve Bayes, Support Vector Machine (SVM), Decision Tree, and Random Forest with SMOTE technique applied to improve minority data representation and sentiment analysis accuracy. The results show that the Decision Tree algorithm is the most effective algorithm compared to the other algorithms with an accuracy value of 0.97, Cross-validation accuracy for Decision Tree is 0.97 ± 0.00, which indicates excellent model consistency on different data and Decision Tree algorithm is also not affected much by the use of SMOTE Technique. This research also resulted in the extraction of useful knowledge in the form of XML.

---

Availability

Detail Information

Series Title

-

Call Number

T1620722024

Publisher

Indralaya : Prodi Sistem Informasi, Fakultas Ilmu Komputer Universitas Sriwijaya., 2024

Collation

xv, 51 hlm.; ilus.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

003.107

Content Type

Text

Media Type

unmediated

Carrier Type

other (computer)

Edition

-

Subject(s)

Prodi Sistem Informasi
Identifikasi Sistem

Specific Detail Info

-

Statement of Responsibility

MURZ

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment