Perbandingan Algoritma SVM dan RF pada Analisis Sentimen menggunakan Pendekatan Machine Learning

Tristanto Ariaji; Sri Ngudi Wahyuni; Muhammad Ikhsan

doi:10.47134/jacis.v5i1.107

Authors

Tristanto Ariaji Universitas Amikom Yogyakarta
Sri Ngudi Wahyuni Universitas Amikom Yogyakarta
Muhammad Ikhsan Universitas Amikom Yogyakarta

DOI:

https://doi.org/10.47134/jacis.v5i1.107

Keywords:

SVM, Random Forest, Analisis Sentimen, machine learning, twitter

Abstract

Analisis sentimen tentang kelangkaan Bahan Bakar Minyak (BBM) di Indonesia merupakan salah satu cara untuk mengetahui opini masyarakat tentang kelangkaan BBM. Analisis sentimen digunakan sebagai dasar pengambilan keputusan oleh pihak berwenang sebagai upaya penyelesaian masalah, sehingga prediksi sentimen perlu dilakukan. Tujuan penelitian ini adalah melakukan perbandingan akurasi algoritma Support Vector Machine (SVM), dan Random Forest (RF) untuk analisis sentimen. Kontribusi pada penelitian ini adalah penentuan algoritma yang efektif dalam analisis sentimen Bahan Bakar Minyak di Indonesia. Adapun Tools olah data menggunakan Google Colab, dengan bahasa pemrograman Python dan pendekatan Machine Learning. Data eksperimen menggunakan data Twitter, diambil pada tanggal 1 -30 Juli 2022 dan terkumpul 6602 data dalam bahasa inggris. Hasil eksperimen menunjukkan bahwa hasil uji SVM untuk nilai Pressision, F1-Score dan support sebesar 0.98 lalu 0,97, kemudian 0.98 dan 67, sehingga nilai akurasi secara keseluruhan SVM adalah 0.98. Sedangkan RF memiliki hasil uji nilai Pressision, Recall. F1-Score dan support sebesar 0,86 kemudian 0,99 lalu 0,92 dan 67. Sedangkan nilai akurasi secara keseluruhan RF adalah 0.90. sehingga secara keseluruhan model SVM lebih direkomendasikan untuk pemodelan prediksi khususnya analisis sentimen pada kasus kelangkaan BBM melalui data Twitter.

References

[1] Fransiscus and A. S. Girsang, “Sentiment Analysis of COVID-19 Public Activity Restriction (PPKM) Impact using BERT Method,” Int. J. Eng. Trends Technol., vol. 70, no. 12, pp. 281–288, Dec. 2022, doi: 10.14445/22315381/IJETT-V70I12P226.

[2] A. S. Neogi, K. A. Garg, R. K. Mishra, and Y. K. Dwivedi, “Sentiment analysis and classification of Indian farmers’ protest using twitter data,” Int. J. Inf. Manag. Data Insights, vol. 1, no. 2, Nov. 2021, doi: 10.1016/j.jjimei.2021.100019.

[3] M. Demircan, A. Seller, F. Abut, and M. F. Akay, “Developing Turkish sentiment analysis models using machine learning and e-commerce data,” Int. J. Cogn. Comput. Eng., vol. 2, no. October, pp. 202–207, 2021, doi: 10.1016/j.ijcce.2021.11.003.

[4] S. R. Shah, A. Kaushik, S. Sharma, and J. Shah, “Opinion-mining on marglish and devanagari comments of youtube cookery channels using parametric and non-parametric learning models,” Big Data Cogn. Comput., vol. 4, no. 1, pp. 1–19, Mar. 2020, doi: 10.3390/bdcc4010003.

[5] S. S. Aljameel et al., “A sentiment analysis approach to predict an individual’s awareness of the precautionary procedures to prevent covid-19 outbreaks in Saudi Arabia,” Int. J. Environ. Res. Public Health, vol. 18, no. 1, pp. 1–12, Jan. 2021, doi: 10.3390/ijerph18010218.

[6] E. Elgeldawi, A. Sayed, A. R. Galal, and A. M. Zaki, “Hyperparameter tuning for machine learning algorithms used for arabic sentiment analysis,” Informatics, vol. 8, no. 4, Dec. 2021, doi: 10.3390/informatics8040079.

[7] P. T. Krishnan, A. N. Joseph Raj, and V. Rajangam, “Emotion classification from speech signal based on empirical mode decomposition and non-linear features: Speech emotion recognition,” Complex Intell. Syst., vol. 7, no. 4, pp. 1919–1934, Aug. 2021, doi: 10.1007/s40747-021-00295-z.

[8] J. Artikel, “Form Hasil Review (Faizah)”.

[9] G. Kanugrahan, V. Hafizh, C. Putra, and Y. Ramdhani, “Analisis Sentimen Aplikasi Gojek Menggunakan SVM , Random Forest dan Decision Tree,” vol. 6, no. 2, 2024.

[10] T. Ahmed Khan, R. Sadiq, Z. Shahid, M. M. Alam, and M. Mohd Su’ud, “Sentiment Analysis using Support Vector Machine and Random Forest,” J. Informatics Web Eng., vol. 3, no. 1, pp. 67–75, 2024, doi: 10.33093/jiwe.2024.3.1.5.

[11] B. A. Maulana, M. J. Fahmi, A. M. Imran, and N. Hidayati, “Analisis Sentimen Terhadap Aplikasi Pluang Menggunakan Algoritma Naive Bayes dan Support Vector Machine (SVM),” MALCOM Indones. J. Mach. Learn. Comput. Sci., vol. 4, no. 2, pp. 375–384, 2024, doi: 10.57152/malcom.v4i2.1206.

[12] F. M. Carina, Admi Salma, Dony Permana, and Zamahsary Martha, “Sentiment Analysis of X Application Users on the Conflict Between Israel and Palestine Using Support Vector Machine Algorithm,” UNP J. Stat. Data Sci., vol. 2, no. 2, pp. 204–212, 2024, doi: 10.24036/ujsds/vol2-iss2/170.

[13] P. Sankar, N. Palanichamy, and K. Ng, “Sentiment Analysis on Twitter Data for Depression Detection,” J. Logist. Informatics Serv. Sci., vol. 11, no. 3, pp. 21–36, 2024, doi: 10.33168/jliss.2024.0302.

[14] F. Rustam, M. Khalid, W. Aslam, V. Rupapara, A. Mehmood, and G. S. Choi, “A performance comparison of supervised machine learning models for Covid-19 tweets sentiment analysis,” PLoS One, vol. 16, no. 2, Feb. 2021, doi: 10.1371/journal.pone.0245909.

[15] Ferdi and Vina Ayumi, “Analisa Sentimen Mengenai Kenaikan Harga Bbm Menggunakan Metode Naïve Bayes Dan Support Vector Machine,” JSAI (Journal Sci. Appl. Informatics), vol. 6, no. 1, pp. 1–10, 2023, doi: 10.36085/jsai.v6i1.4628.

[16] R. Alfred and J. H. Obit, “The roles of machine learning methods in limiting the spread of deadly diseases: A systematic review,” Heliyon, vol. 7, no. 6. Elsevier Ltd, Jun. 01, 2021. doi: 10.1016/j.heliyon.2021.e07371.

[17] A. Al-Hashedi et al., “Ensemble Classifiers for Arabic Sentiment Analysis of Social Network (Twitter Data) towards COVID-19-Related Conspiracy Theories,” Appl. Comput. Intell. Soft Comput., vol. 2022, 2022, doi: 10.1155/2022/6614730.

[18] M. Maemunah, M. Istighosah, S. N. Wahyuni, and Suyatmi, “The implementation of sentiment analysis on Indonesian sexual violation bill using Naïve Bayes algorithm,” AIP Conf. Proc., vol. 2508, 2023, doi: 10.1063/5.0117726.