A Comparison of SVM Kernel Functions for Sentiment Analysis of UU TPKS
Keywords:
kernel function, law on the elimination of sexual violence, sentiment analysis, support vector machineAbstract
The law on the elimination of sexual violence or Undang-Undang Tindak Pidana Kekerasan Seksual (UU TPKS) previously known as draft law on criminal sexual violence got approved in April 12th, 2022 in the plenary meeting of the Indonesia’s Parliament. Before the law has been approved, the bills were initiated by the National Commission on Violence Against Women (Komnas Perempuan) in 2012. The passed bills raised many reactions from Indonesian Citizen on social media, specifically Twitter. In this study, we do sentiment analysis on the passes of UU TPKS using 5486 data by keywords UU TPKS and/or #UUTPKS on Twitter. Different kernel functions with different combination of C, gamma, and degree on support vector machine used to find out which kernel is the best for classification on the passed bills such as linear, radial basis function (RBF), sigmoid, and polynomial using cross validation with the value of K equals to 10. The evaluation shows that the model reaches the highest F1-score using radial basis function kernel, C=1 and gamma=1 with 96,36% score.
References
Beigi, G., Hu, X., Maciejewski, R., Liu, H. 2016. An Overview of Sentiment Analysis in Social Media and Its Applications in Disaster Relief. In: Pedrycz, W., Chen, SM. (eds) Sentiment Analysis and Ontology Engineering. Studies in Computational Intelligence, vol 639. Springer, Cham. https://doi.org/10.1007/978-3-319-30319-2_13
Berry, M. W., & Kogan, J. (Eds.). 2010. Text mining: applications and theory. John Wiley & Sons.
Dixon, S. 2022. Countries with most Twitter users 2022. Statista. https://www.statista.com/statistics/242606/number-of-active-twitter-users-in-selected-countries/
Guzman, C. de. 2022. Indonesia Finally Passes Sexual Violence Bill. Time. https://time.com/6166853/indonesia-sexual-violence-law/
Hossin, M., & Sulaiman, M. N. (2015). A review on evaluation metrics for data classification evaluations. International journal of data mining & knowledge management process, 5(2), 1.
Hussain, M., Wajid, S. K., Elzaart, A., & Berbar, M. 2011. A Comparison of SVM Kernel Functions for Breast Cancer Detection. 2011 Eighth International Conference Computer Graphics, Imaging and Visualization. doi:10.1109/CGIV.2011.31
Ihsan, I., Nurjanah, D., & Nurrahmi, H. 2021. Sentiment Analysis RKUHP Pada Twitter Menggunakan Metode Support Vector Machine. eProceedings of Engineering, 8(2).
Komnas Perempuan. (2022). Bayang-Bayang Stagnansi: Daya Pencegahan dan Penanganan Berbanding Peningkatan Jumlah, Ragam dan Kompleksitas Kekerasan Berbasis Gender terhadap Perempuan. Jakarta: Komnas Perempuan.
Liu, B. 2012. Sentiment analysis and opinion mining. Synthesis lectures on human language technologies, 5(1), 1-167.
Pang, B., & Lee, L. 2008. Opinion Mining and Sentiment Analysis. Foundations and Trends in Information Retrieval, 2(1–2), 1–135.
Phienthrakul, T., Kijsirikul, B., Takamura, H., & Okumura, M. 2009. Sentiment Classification with Support Vector Machines and Multiple Kernel Functions. Lecture Notes in Computer Science, 583–592. doi:10.1007/978-3-642-10684-2_65
Prastyo, P. H., Ardiyanto, I., & Hidayat, R. (2020). Indonesian Sentiment Analysis: An Experimental Study of Four Kernel Functions on SVM Algorithm with TF-IDF. 2020 International Conference on Data Analytics for Business and Industry: Way Towards a Sustainable Economy (ICDABI). doi:10.1109/ICDABI51230.2020.9325685
Qaiser, S., & Ali, R. 2018. Text mining: use of TF-IDF to examine the relevance of words to documents. International Journal of Computer Applications, 181(1), 25-29.
Qaiser, S., & Ali, R. 2018. Text mining: use of TF-IDF to examine the relevance of words to documents. International Journal of Computer Applications, 181(1), 25-29.
Rozi, I. F., Pramono, S. H., & Dahlan, E. A. 2013. Implementasi opinion mining (analisis sentimen) untuk ekstraksi data opini publik pada perguruan tinggi. Jurnal EECCIS, 6(1), 37-43.
Sasaki, Y. (2007). The truth of the F-measure. Teach tutor mater, 1(5), 1-5.
Sokolova, M., Japkowicz, N., & Szpakowicz, S. (2006, December). Beyond accuracy, F-score and ROC: a family of discriminant measures for performance evaluation. In Australasian joint conference on artificial intelligence (pp. 1015-1021). Springer, Berlin, Heidelberg.
Wijaya, T. N., Indriati, R., & Muzaki, M. N. 2021. Analisis Sentimen Opini Publik Tentang Undang-Undang Cipta Kerja Pada Twitter. Jambura Journal of Electrical and Electronics Engineering, 3(2), 78-83.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2023 Ni Kadek Mirah Budayani, Isnandar Slamet, Sri Sulistijowati Handajani
This work is licensed under a Creative Commons Attribution 4.0 International License.
