Analisis Sentimen Masyarakat Terhadap Kebijakan Kenaikan PPN 12% Dengan Metode Regresi Logistik Biner Dan Naïve Bayes Classifier

Latifah, Tarbiyatul (2025) Analisis Sentimen Masyarakat Terhadap Kebijakan Kenaikan PPN 12% Dengan Metode Regresi Logistik Biner Dan Naïve Bayes Classifier. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 5003211098-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only Download (6MB)

Abstract

The policy to increase the Value Added Tax (VAT) from 11% to 12%, which will take effect starting in 2025, has sparked a variety of reactions among the public. Some members of the public are concerned about the impact of rising prices for goods and services, which could reduce purchasing power, while the government views this policy as a strategic step to maintain fiscal stability. Therefore, this study aims to analyze public sentiment toward the policy by utilizing opinions collected from the social media platform Instagram. The study employs two classification methods—Binary Logistic Regression and Naïve Bayes Classifier—to compare their effectiveness in classifying sentiment. Public opinion data was analyzed through preprocessing stages using Natural Language Processing (NLP) techniques and keyword weighting using the Term Frequency - Inverse Document Frequency (TF-IDF) method. The Gemini API was used to categorize sentiment as positive or negative. The results of the study show that the Naïve Bayes Classifier method has superior performance with a total accuracy of 0.8337, precision of 0.8235, recall of 0.3529, F1-score of 0.4941, and AUC value of 0.8379, compared to Binary Logistic Regression. Content analysis also indicates a predominance of negative sentiment, with public concern centered on the impact of price increases on purchasing power. This study is expected to provide insight into public reactions to the VAT increase policy and serve as a reference for the government in formulating more effective communication strategies, as well as a benchmark for similar studies in the future.
=======================================================================================================================================
Kebijakan kenaikan Pajak Pertambahan Nilai (PPN) dari 11% menjadi 12% yang akan berlaku mulai tahun 2025 telah menimbulkan beragam reaksi di masyarakat. Sebagian masyarakat mengkhawatirkan dampak kenaikan harga barang dan jasa yang dapat menurunkan daya beli, sementara pemerintah melihat kebijakan ini sebagai langkah strategis untuk menjaga stabilitas fiskal. Oleh karena itu, penelitian ini bertujuan untuk menganalisis sentimen masyarakat terhadap kebijakan tersebut dengan memanfaatkan opini yang dikumpulkan dari media sosial Instagram. Penelitian ini menerapkan dua metode klasifikasi, yaitu Regresi Logistik Biner dan Naïve Bayes Classifier, untuk membandingkan efektivitas keduanya dalam mengklasifikasikan sentimen. Data opini publik dianalisis melalui tahapan preprocessing dengan teknik Natural Language Processing (NLP), dan pembobotan kata kunci menggunakan metode Term Frequency - Inverse Document Frequency (TF-IDF). Gemini API digunakan untuk mengkategorikan sentimen menjadi positif atau negatif. Hasil penelitian menunjukkan bahwa metode Naïve Bayes Classifier memiliki performa yang lebih unggul dengan akurasi total sebesar 0,8337, precision 0,8235, recall 0,3529, F1-score 0,4941, dan nilai AUC 0,8379, dibandingkan dengan Regresi Logistik Biner. Analisis konten juga mengindikasikan dominasi sentimen negatif, di mana kekhawatiran utama masyarakat berpusat pada dampak kenaikan harga terhadap daya beli. Penelitian ini diharapkan dapat memberikan wawasan mengenai reaksi publik terhadap kebijakan kenaikan PPN dan menjadi referensi bagi pemerintah dalam merumuskan strategi komunikasi yang lebih efektif, serta sebagai acuan bagi penelitian serupa di masa mendatang.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Sentiment Analysis, Binary Logistic Regression, Naïve Bayes Classifier, Value Added Tax (VAT), Analisis Sentimen, Regresi Logistik Biner, Naïve Bayes Classifier, Pajak Pertambahan Nilai (PPN)
Subjects:	H Social Sciences > HA Statistics H Social Sciences > HA Statistics > HA31.3 Regression. Correlation. Logistic regression analysis. H Social Sciences > HA Statistics > HA31.7 Estimation Q Science > Q Science (General) > Q325.5 Machine learning. Support vector machines.
Divisions:	Faculty of Science and Data Analytics (SCIENTICS) > Statistics > 49201-(S1) Undergraduate Thesis
Depositing User:	Tarbiyatul Latifah
Date Deposited:	06 Aug 2025 06:08
Last Modified:	06 Aug 2025 06:08
URI:	http://repository.its.ac.id/id/eprint/127793

Actions (login required)

View Item