Melola Discovery

← Melola Discovery

Open access Jurnal SINTA 3

Perbandingan SVM dan Random Forest pada Analisis Sentimen Kebijakan Tabungan Perumahan Rakyat Berdasarkan Data Media Sosial X

SemanTIK: Teknik Informasi · Vol. 11 No. 1 (2025)

DOI
10.55679/semantik.v11i1.93
ISSN
2502-8928, 2460-1446
Published
2025-06-19
Publisher
Informatics Engineering Department of Halu Oleo University
Language
eng
License
creativecommons.org/licenses/by-sa/4.0

Abstract

Tabungan Perumahan Rakyat atau biasa disingkat Tapera, menjadi salah satu isu kebijakan yang hingga kini banyak diperbincangkan. Tapera merupakan bentuk kebijakan pemerintah yang mewajibkan potongan gaji/upah karyawan dari seluruh lapisan pekerjaan sebesar 3%. Potongan tersebut dilakukan secara berkala dalam kurun waktu tertentu untuk nantinya dijadikan tabungan perumahan rakyat. Berdasarkan data media sosial X, didapatkan sebanyak 6.218 data opini masyarakat terkait program Tapera. Penelitian ini bertujuan untuk melakukan analisis sentimen opini masyarakat terkait program Tapera pada media sosial X dengan perbandingan algoritma Random Forest dan Support Vector Machine. Hasil analisis sentimen yang dilakukan, terdapat sebanyak sebanyak 1.502 data sebagai sentimen positif, 4.085 data tweet sebagai sentimen negatif, dan 631 data tweet sebagai sentimen netral. Hasil pemodelan menunjukan akurasi SVM lebih tinggi dibandingkan Random Fores. SVM menghasilkan nilai akurasi 94,12%, Recall 94.12 %, Precision 94.34 %, F1-Score 94.16 % sementara Random Forest memiliki nilai akurasi 91.76 %, Recall 91.76 %, Precision 92.11 %, F1-Score 91.83 %. This Public Housing Savings or commonly abbreviated as Tapera, is one of the policy issues that has been widely discussed until now. Tapera is a form of government policy that requires deductions from the salaries / wages of employees from all levels of work of 3%. These deductions are made periodically over a period of time to later be used as public housing savings. Based on X social media data, 6,218 public opinion data related to the Tapera program were obtained. This study aims to conduct sentiment analysis of public opinion related to the Tapera program on social media X with a comparison of the Random Forest and Support Vector Machine algorithms. The results of sentiment analysis conducted, there are as many as 1,502 data as positive sentiment, 4,085 tweet data as negative sentiment, and 631 tweet data as neutral sentiment. Modeling results show SVM accuracy is higher than Random Fores. SVM produces an accuracy value of 94.12%, Recall 94.12%, Precision 94.34%, F1-Score 94.16% while Random Forest has an accuracy value of 91.76%, Recall 91.76%, Precision 92.11%, F1-Score 91.83%

Keywords

Collaboration network of the authors

2 authors · 1 co-authorship link

Hover or tap a name to highlight its co-authors. Double-click to open the author's page.

  • Universitas Teknokrat Indonesia
  • Affiliation unknown
  • Different organisations
  • Same organisation
  • Affiliation unknown
  • Thicker line = more joint articles · bigger circle = more articles
Show as table
Co-authorOrganisationJoint articles

Affiliations come from OpenAlex; journal OAI-PMH metadata carries none. Authors without an OpenAlex ID are matched by name, which can merge or split people.

Metadata source: OAI-PMH (metadata jurnal) https://semantik.uho.ac.id/index.php/journal/oai, first harvested 26 Okt 2026, last seen 26 Okt 2026.
Original metadata (oai_dc) 
<oai_dc:dc xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/  http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
	<dc:title xml:lang="en-US">Perbandingan SVM dan Random Forest pada Analisis Sentimen Kebijakan Tabungan Perumahan Rakyat Berdasarkan Data Media Sosial X</dc:title>
	<dc:creator>afandy, yayat</dc:creator>
	<dc:creator>Parjito</dc:creator>
	<dc:subject xml:lang="en-US">Tabungan Perumahan Rakyat</dc:subject>
	<dc:subject xml:lang="en-US">Analisis Sentimen</dc:subject>
	<dc:subject xml:lang="en-US">Random Forest</dc:subject>
	<dc:subject xml:lang="en-US">Algoritma Support Vector Machine</dc:subject>
	<dc:description xml:lang="en-US">Tabungan Perumahan Rakyat atau biasa disingkat Tapera, menjadi salah satu isu kebijakan yang hingga kini banyak diperbincangkan. Tapera merupakan bentuk kebijakan pemerintah yang mewajibkan potongan gaji/upah karyawan dari seluruh lapisan pekerjaan sebesar 3%. Potongan tersebut dilakukan secara berkala dalam kurun waktu tertentu untuk nantinya dijadikan tabungan perumahan rakyat. Berdasarkan data media sosial X, didapatkan sebanyak 6.218 data opini masyarakat terkait program Tapera. Penelitian ini bertujuan untuk melakukan analisis sentimen opini masyarakat terkait program Tapera pada media sosial X dengan perbandingan algoritma Random Forest dan Support Vector Machine. Hasil analisis sentimen yang dilakukan, terdapat sebanyak sebanyak 1.502 data sebagai sentimen positif, 4.085 data tweet sebagai sentimen negatif, dan 631 data tweet sebagai sentimen netral. Hasil pemodelan menunjukan akurasi SVM lebih tinggi dibandingkan Random Fores. SVM menghasilkan nilai akurasi 94,12%, Recall 94.12 %, Precision 94.34 %, F1-Score 94.16 % sementara Random Forest memiliki nilai akurasi 91.76 %, Recall 91.76 %, Precision 92.11 %, F1-Score 91.83 %.
This Public Housing Savings or commonly abbreviated as Tapera, is one of the policy issues that has been widely discussed until now. Tapera is a form of government policy that requires deductions from the salaries / wages of employees from all levels of work of 3%. These deductions are made periodically over a period of time to later be used as public housing savings. Based on X social media data, 6,218 public opinion data related to the Tapera program were obtained. This study aims to conduct sentiment analysis of public opinion related to the Tapera program on social media X with a comparison of the Random Forest and Support Vector Machine algorithms. The results of sentiment analysis conducted, there are as many as 1,502 data as positive sentiment, 4,085 tweet data as negative sentiment, and 631 tweet data as neutral sentiment. Modeling results show SVM accuracy is higher than Random Fores. SVM produces an accuracy value of 94.12%, Recall 94.12%, Precision 94.34%, F1-Score 94.16% while Random Forest has an accuracy value of 91.76%, Recall 91.76%, Precision 92.11%, F1-Score 91.83%</dc:description>
	<dc:publisher xml:lang="en-US">Informatics Engineering Department of Halu Oleo University</dc:publisher>
	<dc:date>2025-06-19</dc:date>
	<dc:type>info:eu-repo/semantics/article</dc:type>
	<dc:type>info:eu-repo/semantics/publishedVersion</dc:type>
	<dc:type xml:lang="en-US">Peer-reviewed Article</dc:type>
	<dc:format>application/pdf</dc:format>
	<dc:identifier>https://semantik.uho.ac.id/index.php/journal/article/view/93</dc:identifier>
	<dc:identifier>10.55679/semantik.v11i1.93</dc:identifier>
	<dc:source xml:lang="en-US">SemanTIK : Teknik Informasi; Vol. 11 No. 1 (2025): Vol. 11 No. 1 (2025): SemanTIK Teknik Informasi</dc:source>
	<dc:source>2502-8928</dc:source>
	<dc:source>2460-1446</dc:source>
	<dc:language>eng</dc:language>
	<dc:relation>https://semantik.uho.ac.id/index.php/journal/article/view/93/19</dc:relation>
	<dc:rights xml:lang="en-US">Copyright (c) 2025 YAYAT AFANDY, Parjito</dc:rights>
	<dc:rights xml:lang="en-US">https://creativecommons.org/licenses/by-sa/4.0</dc:rights>
</oai_dc:dc>