Skripsi

ANALISIS SENTIMEN PENGGUNA APLIKASI SOCIOLLA MENGGUNAKAN ALGORITMA SUPPORT VECTOR MACHINE DENGAN OPTIMASI GRID SEARCH

---

The rapid growth of digital technology has driven innovations in the beauty industry, one of which is the Soco by Sociolla platform that provides online product reviews. The large number of user reviews on the Soco platform provides an opportunity to analyze sentiment in order to understand perceptions of services and products. This study aims to analyze user sentiments on Soco by Sociolla reviews into positive and negative categories utilizing the Support Vector Machine (SVM) algorithm. Two kernels, Linear and Radial Basis Function (RBF), were employed, with parameter optimization conducted through the Grid search method to achieve optimal performance. The study stages include data collection, text preprocessing, labeling, data splitting, model training, and evaluation. The results show that the RBF kernel provides the best performance with an accuracy of 88.5% and is supported by the results of grid search optimization, which produces a combination of RBF parameters with a precision value of 0.93, recall of 0.82, and f1-score of 0.87, indicating its superiority over the linear kernel in capturing non-linear patterns within user review data.

---

Availability

Detail Information

Series Title

-

Call Number

T1963772026

Publisher

Indralaya : Prodi Sistem Informasi, Fakultas Ilmu Komputer Universitas Sriwijaya., 2026

Collation

xvi, 44 hlm.; ilus.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

006.312 07

Content Type

Text

Media Type

unmediated

Carrier Type

-

Edition

-

Subject(s)

Support Vector Machine
Prodi Sistem Informasi

Specific Detail Info

-

Statement of Responsibility

KA

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment