Implementasi Metode Support Vector Machine (SVM) dan Naïve Bayes Classifier (NBC) pada Analisis Sentimen Pengguna Twitter terhadap Potensi Resesi Ekonomi di Indonesia

Habib, Mohamad Hafidz Al (2023) Implementasi Metode Support Vector Machine (SVM) dan Naïve Bayes Classifier (NBC) pada Analisis Sentimen Pengguna Twitter terhadap Potensi Resesi Ekonomi di Indonesia. Other thesis, Institut Teknologi Sepuluh Nopember.

[thumbnail of 06211940000038-Undergraduate_Thesis.pdf] Text
06211940000038-Undergraduate_Thesis.pdf - Accepted Version
Restricted to Repository staff only until 1 October 2025.

Download (2MB) | Request a copy

Abstract

Resesi ekonomi merupakan suatu keadaan dimana terjadi penurunan signifikan dalam aktivitas ekonomi yang tersebar diseluruh sektor ekonomi di suatu wilayah yang ditandai dengan penurunan Pendapatan Domestik Bruto (PDB) selama dua kuartal atau lebih secara berturut-turut. Resesi ekonomi biasanya terlihat dalam PDB rill, pendapatan rill, lapangan kerja, produksi industri, dan penjualan grosir-eceran. Munculnya virus COVID-19 pada awal Tahun 2020 yang telah menyebar dengan cepat ke berbagai negara dan situasi keamanan dunia yang tidak stabil akibat konflik di Eropa mengakibatkan perlambatan yang cukup besar bahkan kelumpuhan di berbagai sektor, terutama sektor ekonomi. Hal ini berdampak buruk terhadap perekonomian beberapa negara dan terancam masuk ke dalam resesi ekonomi, tak terkecuali dengan Indonesia. Melakukan analisis bagaimana respon masyarakat terhadap ancaman resesi ekonomi ini diperlukan untuk mengetahui bagaimana tanggapan masyarakat untuk menghadapi berbagai kemungkinan kondisi ekonomi kedepannya. Penelitian ini dilakukan untuk mengetahui tanggapan masyarakat di media sosial, khususnya Twitter terhadap isu potensi resesi ekonomi di Indonesia. Metode yang digunakan pada analisis sentimen ini adalah Support Vector Machine dan Naïve Bayes Classifier (NBC). Hasilnya pada metode SVM, fungsi kernel Radial Basis Function (RBF) merupakan model terbaik dengan nilai F-score yang dihasilkan sebesar 92.65% pada data training dan 94.7% pada data testing. Sedangkan pada metode Naïve Bayes, nilai F-score yang dihasilkan sebesar 88.4% pada data training dan 91.4% pada data testing.
=================================================================================================================================
An economic recession is a condition in which there is a significant decline in economic activity spread across all economic sectors in an area which can be identified by a decrease in Gross Domestic Product (GDP) for two or more consecutive quarters. Economic recession can be seen in real GDP, real income, employment, industrial production, and wholesale-retail sales. The emergence of the COVID-19 virus in early 2020 which spread quickly to many countries and the unstable world security situation due to the conflict in Europe resulted in a considerable slowdown and even paralysis in many sectors, especially the economic sector. It has harmed the economies of several countries and threatens to enter an economic recession, including Indonesia. Analyzing how the community responds to the threat of an economic recession is necessary to find out how the community responds to various possible economic conditions in the future. This study aims to determine the public's response on social media, especially Twitter, to the issue of the potential for an economic recession in Indonesia. The methods used in this sentiment analysis are the Support Vector Machine (SVM) and Naïve Bayes Classifier (NBC). The result is that in the SVM method, the Radial Basis Function (RBF) kernel function is the best model, with an F-score value of 92.65% on training data and 94.7% on data testing. Whereas in the Naïve Bayes method, the resulting F-score is 88.4% on the training data and 91.4% on the testing data.

Item Type: Thesis (Other)
Uncontrolled Keywords: Economic Recession, Naïve Bayes Classifier, Sentiment Analysis, Support Vector Machine, Analisis Sentimen, Resesi Ekonomi
Subjects: Q Science > Q Science (General) > Q325.5 Machine learning.
Q Science > QA Mathematics
Divisions: Faculty of Science and Data Analytics (SCIENTICS) > Statistics > 49201-(S1) Undergraduate Thesis
Depositing User: Mohamad Hafidz Al Habib
Date Deposited: 05 Oct 2023 04:28
Last Modified: 05 Oct 2023 04:28
URI: http://repository.its.ac.id/id/eprint/104585

Actions (login required)

View Item View Item