Skripsi

ANALISIS SENTIMEN KEMACETAN DI KOTA PALEMBANG BERDASARKAN DATA MEDIA SOSIAL FACEBOOK MENGGUNAKAN ALGORITMA SUPPORT VECTOR MACHINE

---

Sentiment analysis on traffic congestion in Palembang City was carried out using Facebook comments that represent public opinions regarding daily traffic conditions. Data were obtained through web scraping, and after undergoing preprocessing stages—such as text cleaning, tokenization, stopwords removal, stemming, and normalization—a total of 2,505 cleaned entries were prepared and transformed using the TF-IDF method. Sentiments were categorized into three classes: smooth, moderately smooth, and congested. The Support Vector Machine (SVM) algorithm with an RBF kernel was employed for classification, achieving accuracies of 92.41% on training data, 90% on validation, and 82.57% on testing. The dominance of negative sentiment indicates that public complaints related to congestion remain significantly high in Palembang. These findings offer a clearer understanding of public perception and may serve as valuable input for developing more effective traffic management strategies and policies in the city.

---

Availability

Detail Information

Series Title

-

Call Number

T1893792025

Publisher

Indralaya : Prodi Sistem Komputer, Fakultas Ilmu Komputer Universitas Sriwijaya., 2025

Collation

xiii, 81 hlm.; ilus.; tab.; 29 cm.

Language

Indonesia

ISBN/ISSN

-

Classification

006.310 7

Content Type

Text

Media Type

-

Carrier Type

-

Edition

-

Subject(s)

Prodi Sistem Komputer
Pembelajaran Mesin

Specific Detail Info

-

Statement of Responsibility

MI

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment