Skripsi

KLASIFIKASI SHORT MESSAGE SERVICE (SMS) SPAM MENGGUNAKAN SUPPORT VECTOR MACHINE (SVM) DAN ARTIFICIAL NEURAL NETWORK (ANN)

---

Penilaian

---

Short Message Service (SMS) is still used as a communication medium for promotions, notifications, and official information. However, SMS is also prone to misuse in the form of spam that can be disruptive and potentially deceive users. To address this issue, an accurate SMS spam and ham classification system is needed. This study developed an SMS spam classification system using SVM and ANN with a MLP architecture. The dataset used is a secondary dataset from the Kaggle platform, consisting of 1,143 SMS messages with a balanced class distribution of 574 spam and 569 ham messages. Feature extraction was carried out using TF-IDF and n-gram, while feature selection used Pearson Correlation. Model parameters were determined using Grid Search. The study was conducted through six testing scenarios. The results showed that the SVM model with a combination of TF-IDF and n-gram without feature selection achieved the best performance, with an accuracy of 98.25%, precision of 97.50%, recall of 99.15%, and F1-score of 98.32%. The best model used a linear kernel with a C value of 1. The findings indicate that SVM outperformed MLP-based ANN in SMS spam classification.

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2507004301	T179421	T1794212025	Central Library (Reference)	Available but not for loan - Not for Loan

Detail Information

Series Title

-

Call Number

T1794212025

Publisher

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

Collation

xxii, 549 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