Skripsi

PENERAPAN ALGORITMA RANDOM FOREST DENGAN RANDOM OVERSAMPLING UNTUK SENTIMEN ANALISIS PENGGUNA X TERHADAP PROGRAM SEKOLAH RAKYAT

---

The "Sekolah Rakyat" Program is a government initiative aimed at expanding educational services for underprivileged communities to break the cycle of poverty. However, the vast amount of dynamic and unstructured public opinion on platform X poses a challenge in systematically mapping community responses. This study aims to analyze the sentiment of platform X users toward the Sekolah Rakyat Program by implementing the Random Forest algorithm. A dataset of 8,623 tweets was collected using crawling techniques. The research stages include preprocessing (cleaning, normalization, case folding, tokenizing, stopword removal, and stemming) , lexicon-based data labeling , and feature extraction using Term Frequency-Inverse Document Frequency (TF-IDF). To address class imbalance (69.4% positive and 30.6% negative), the Random Oversampling (ROS) technique was applied to the training data. Testing results with an 80:20 data splitting ratio showed that the model achieved an accuracy rate of 80.99%. Furthermore, the weighted precision, weighted recall, and weighted F1-score consistently reached 0.81. These findings indicate that the Random Forest algorithm is effective in classifying public sentiment, with the majority of the public providing positive support toward the program's success in providing inclusive educational access

---

Availability

Detail Information

Series Title

-

Call Number

T1958742026

Publisher

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

Collation

xv, 210 hlm.; ilus.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

006.310 7

Content Type

Text

Media Type

-

Carrier Type

-

Edition

-

Subject(s)

Analisis sentimen
Prodi Sistem Informasi

Specific Detail Info

-

Statement of Responsibility

TUTI

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment