Implementasi Modified Enhanced Confix Stripping Stemmer pada Klasifikasi Fake News Covid-19

Dyas Rahma Putri, Budi Arif Dermawan, Intan Purnamasari

Abstract


Today's advances in technology and information make communication easier, so that the flow of information can quickly spread. The ease also allows anyone to upload anything on online platforms such as blogs, comments to news articles, social media, etc. that could lead to ambiguity of information or even lead to misleading information. Fake news is information that contains things that are uncertain or not a fact that actually happened. One of the popular news topics nowadays is about the covid-19 virus. This research evaluates the performance of Multinomial Naïve Bayes and Bernoulli Naïve Bayes in conducting fake news classifications related to covid-19. Beside that, we used Modified Enhanced Confix Stripping Stemmer in performing indonesian word standardization that has a variety of shapes and structures. The evaluation showed that Bernoulli Naïve Bayes model had the best performance than Multinomial Naïve Bayes, with the accuracy value of 91%, precision 0.93, recall 0.92, and f-1 score 0.92. In addition, the performance of Modified Enhanced Confix Stripping Stemmer (Modified ECS) algorithm is also perform very well in standardizing words (stemming) Indonesian language.

Full Text:

PDF

References


B. D. Wicaksono, “IMR 2019: 5 Fakta Perubahan Pola Konsumsi Media Millennial,” 2019. https://www.idntimes.com/tech/trend/bayu/survei-ims-2019-5-fakta-perubahan-pola-konsumsi-media-millennial/5.

A. Prasetyo, B. D. Septianto, G. F. Shidik, and A. Z. Fanani, “Evaluation of feature extraction TF-IDF in Indonesian hoax news classification,” in Proceedings - 2019 International Seminar on Application for Technology of Information and Communication: Industry 4.0: Retrospect, Prospect, and Challenges, iSemantic 2019, 2019, pp. 1–6, doi: 10.1109/ISEMANTIC.2019.8884291.

F. Rahutomo, I. Yanuar, R. Pratiwi, and D. M. Ramadhani, “Eksperimen Naive Bayes pada Deteksi Berita Hoax Berbahasa Indonesia,” J. Penelit. Komun. dan Opini Publik V, vol. 23, no. 1, pp. 1–15, 2019.

T. Trisna et al., “Analysis and Detection of Hoax Contents in Indonesian News Based on Machine Learning,” JIPN (Journal Informatics Pelita Nusantara), vol. 4, no. 1, 2019.

M. Singh, M. Wasim Bhatt, H. S. Bedi, and U. Mishra, “Performance of bernoulli’s naive bayes classifier in the detection of fake news,” Mater. Today Proc., no. xxxx, 2020, doi: 10.1016/j.matpr.2020.10.896.

E. Yudi and M. Aditya, “Klasifikasi Dokumen Berita Menggunakan Algoritma Enhanced Confix Stripping Stemmer dan Naïve Bayes Classifier,” J. Nas. Teknol. dan Sist. Inf., vol. 02, pp. 90–99, 2020.

K. Kowsari, K. J. Meimandi, M. Heidarysafa, S. Mendu, L. Barnes, and D. Brown, “Text classification algorithms: A survey,” MDPI, vol. 10, no. 4, pp. 1–68, 2019, doi: 10.3390/info10040150.

C. C. Aggarwal, Data Mining text book, vol. 53, no. 9. 2015.

Y. N. Fadziah and E. F. R, “Penerapan Algoritma Enchanced Confix Stripping dalam Pengukuran Keterbacaan Teks Menggunakan Gunning Fog Index,” JATIKOM J. Teor. dan Apl. Ilmu Komput., vol. 1, no. 1, pp. 15–24, 2018.

A. D. Tahitoe and D. Purwitasari, “Implementasi Modifikasi Enhanced Confix Stripping Stemmer Untuk Bahasa Indonesia dengan Metode Corpus Based Stemming,” pp. 1–15, 2010.

C. C. Aggarwal, Mining Text Data. Springer, 2012.

R. Prabhakar, D. C. Manning, and H. Schütze, Introduction to Information Retrieval. 2008.

J. Han and M. Kamber, Data Mining: Concepts and Techniques, vol. 54, no. Second Edition. 2006.

J. Han, M. Kamber, and J. Pei, Data mining: Data mining concepts and techniques. 2014.

G. Miner, J. Elder, R. A. Nisbet, J. Thompson, and R. Foley, Practical Text Mining and Statistical Analysis for Non-structured Text Data Applications, 1st ed. Elsevier Ltd, 2012.




DOI: http://dx.doi.org/10.30645/j-sakti.v5i2.359

Refbacks

  • There are currently no refbacks.


J-SAKTI (Jurnal Sains Komputer & Informatika)
Published Papers Indexed/Abstracted By:

Jumlah Kunjungan :

View My Stats