Pendekatan TF-IDF, SMOTE, dan SVM dalam Klasifikasi Sentimen Masyarakat terhadap Pemblokiran Judi Online

Authors

  • Robert Antonius Universitas Multi Data Palembang
  • Achmad Rizky Zulkarnain
  • Hafiz Irsyad

DOI:

https://doi.org/10.58369/biit.v2i3.65

Keywords:

SMOTE, Support Vector Machine, TF-IDF

Abstract

Judi online adalah topik hangat di kalangan masyarakat. Salah satu pembicaraan terkait judi online yang muncul adalah apakah seharusnya pemerintah melakukan pemblokiran situs judi online. Ada beberapa sisi dari pembahasan ini, seperti apakah pemblokiran itu benar akan membantu mencegah adiksi judi online dan apakah justru seharusnya pemerintah melegalkan judi online. Untuk membantu dalam menavigasi wacana hangat ini, dibangunlah sebuah sistem yang dapat mendeteksi dua sisi sentimen terhadap pemblokiran judi online. Model dilatih dengan dataset yang diseimbangkan dengan SMOTE karena tidak meratanya kelas klasifikasi, lalu diboboti dengan TF-IDF untuk dapat fokus pada kata-kata berbobot tinggi. Model klasifikasi yang dibangun dengan Support Vector Machine mencapai tingkat akurasi 61.54% dengan tolak ukur evaluasi confusion matrix.

Online gambling is currently a hot topic among internet netizens. One of the talking points in the discourse was how should the government handle blocking online gambling sites. There is multiple sides to the discourse, such as does blocking the sites actually help in preventing gambling addiction or would legalizing it be the right policy instead. To help navigate this controversial topic, a system was built to differentiate the two sides of the argument towards blocking online gambling sites. The model is trained on a dataset that is first balanced with SMOTE, then weighted with TF-IDF to give focus to vocal tokens of the discourse. The classification model was built with Support Vector Machine and reached an accuracy level of 61.54% when evaluated with a confusion matrix.

References

S. M. Gainsbury, “Online Gambling Addiction: the Relationship Between Internet Gambling and Disordered Gambling,” Curr Addict Rep, vol. 2, no. 2, pp. 185–193, 2015, doi: 10.1007/s40429-015-0057-8.

M. Chóliz, “The Challenge of Online Gambling: The Effect of Legalization on the Increase in Online Gambling Addiction,” J Gambl Stud, vol. 32, no. 2, pp. 749–756, 2016, doi: 10.1007/s10899-015-9558-6.

D. Fitriya et al., “MENELAAH FENOMENA JUDI ONLINE (SLOT) DI KALANGAN MAHASISWA DALAM PERSPEKTIF HUKUM ISLAM DI INDONESIA,” Jurnal Kajian Agama dan Dakwah, vol. 2, 2024, doi: 10.333/Tashdiq.v1i1.571.

J. Homepage et al., “MALCOM: Indonesian Journal of Machine Learning and Computer Science Sentiment Analysis of Online Lectures in Indonesia from Twitter Dataset Using InSet Lexicon Analisis Sentimen terhadap Perkuliahan Daring di Indonesia dari Twitter Dataset Menggunakan InSet Lexicon,” vol. 1, pp. 24–33, 2021.

S. Qaiser, U. Utara, M. Sintok, M. Kedah, A. Ramsha, and T. Analytics, “Text Mining: Use of TF-IDF to Examine the Relevance of Words to Documents Text Mining,” 2018.

M. Liang and T. Niu, “Research on Text Classification Techniques Based on Improved TF-IDF Algorithm and LSTM Inputs,” Procedia Comput Sci, vol. 208, pp. 460–470, 2022, doi: https://doi.org/10.1016/j.procs.2022.10.064.

S.-W. Kim and J.-M. Gil, “Research paper classification systems based on TF-IDF and LDA schemes,” Human-centric Computing and Information Sciences, vol. 9, no. 1, p. 30, 2019, doi: 10.1186/s13673-019-0192-7.

R. Kristianto Hondro, “Jurnal Pendidikan Teknologi Informasi Dan Komputer Analisis Penerapan Text Mining dan TF-IDF dalam Mengetahui Sentimen Masyarakat Terhadap Kinerja POLRI,” 2023, [Online]. Available: https://journal.grahamitra.id/index.php/petik

A. J. Mohammed, “Improving Classification Performance for a Novel Imbalanced Medical Dataset using SMOTE Method,” International Journal of Advanced Trends in Computer Science and Engineering, vol. 9, no. 3, pp. 3161–3172, Jun. 2020, doi: 10.30534/ijatcse/2020/104932020.

A. Fernández, S. García, F. Herrera, and N. V Chawla, “SMOTE for Learning from Imbalanced Data: Progress and Challenges, Marking the 15-year Anniversary,” 2018.

Hermanto, A. Y. Kuntoro, T. Asra, E. B. Pratama, L. Effendi, and R. Ocanitra, “Gojek and Grab User Sentiment Analysis on Google Play Using Naive Bayes Algorithm and Support Vector Machine Based Smote Technique,” in Journal of Physics: Conference Series, IOP Publishing Ltd, Nov. 2020. doi: 10.1088/1742-6596/1641/1/012102.

C. Cortes, “Support-Vector Networks,” 1995.

A. Baita and N. Cahyono, “ANALISIS SENTIMEN MENGENAI VAKSIN SINOVAC MENGGUNAKAN ALGORITMA SUPPORT VECTOR MACHINE (SVM) DAN K-NEAREST NEIGHBOR (KNN).”

D. S. Utami and A. Erfina, “ANALISIS SENTIMEN PINJAMAN ONLINE DI TWITTER MENGGUNAKAN ALGORITMA SUPPORT VECTOR MACHINE (SVM),” 2021.

D. Iskandar Mulyana, N. Lutfianti, S. Tinggi Ilmu Komputer Cipta Karya Informatika, J. Radin Inten No, and J. Timur, “Analisis Sentimen Dengan Algoritma SVM Dalam Tanggapan Netizen Terhadap Berita Resesi 2023 Analysis Sentiment Using the SVM Algorithm in Netizen Responses to News of the 2023 Recession,” vol. 13, no. 1, 2023, doi: 10.30700/jst.v13i1.1339.

A. Nursalim and R. Novita, “SENTIMENT ANALYSIS OF COMMENTS ON GOOGLE PLAY STORE, TWITTER AND YOUTUBE TO THE MYPERTAMINA APPLICATION WITH SUPPORT VECTOR MACHINE,” Jurnal Teknik Informatika (JUTIF), vol. 4, no. 6, pp. 1305–1312, 2023, doi: 10.52436/1.jutif.2023.4.6.1059.

Downloads

Published

2024-06-06

Issue

Section

Articles