Skripsi

ANALISIS SENTIMEN ULASAN E-COMMERCE SHOPEE TERKAIT FITUR COD DENGAN MENGGUNAKAN METODE SUPPORT VECTOR MECHINE DAN SELEKSI FITUR MUTUAL INFORMATION

---

Penilaian

---

The rapid development of e-commerce in Indonesia has driven significant changes in people's shopping patterns, with Shopee as one of the most popular platforms. One of the superior features offered is Cash on Delivery (COD), which provides a sense of security for users in making transactions. However, this feature also raises various responses that are reflected in user reviews of the COD feature.This study aims to analyze user review sentiments towards the COD feature on Shopee e-commerce. The method used is Support Vector Machine (SVM) with feature selection using Mutual Information and text representation using Sentence Transformers. The data used are 1887 user reviews taken from Kaggle. The results of the study showed that the SVM model without feature selection produced an accuracy of 63.33% and SVM using Mutual Information feature selection produced an accuracy of 53.33%. Testing was carried out by comparing the performance of the two models using the C regulation parameter, the test results showed that the value of C = 1 gave the best performance for both models. Based on this, it can be concluded that the SVM model without feature selection provides better performance than the model with Mutual Information. Implementation of Mutual Information as a feature selection technique that is considered relevant, but decreases model performance, possibly due to the loss of important features during the selection process. This indicates that feature selection needs to be done carefully, especially on small data. Keywords: Sentence Transformers, SVM, Mutual Information,COD

---

Availability

No copy data

Detail Information

Series Title

-

Call Number

T1797632025

Publisher

Indralaya : Prodi Teknik Informatika, Fakultas Ilmu Komputer Universitas Sriwijaya., 2025

Collation

xvi, 125 hlm.; ilus.; tab.; 29 cm.

Language

Indonesia

ISBN/ISSN

-

Classification

004.07

Content Type

Text

Media Type

-

Carrier Type

-

Edition

-

Subject(s)

Teknik Informatika

Specific Detail Info

-

Statement of Responsibility

MI

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment