Klasifikasi Topik Ayat Al-qur’an Terjemahan Berbahasa Inggris Menggunakan Metode Support Vector Machine Berbasis Vector Space Model Dan Word2vec

Authors

DOI:

https://doi.org/10.34818/eoe.v6i2.9931

Abstract

Abstrak Tujuan diturunkannya Al-Qur’an adalah sebagai petunjuk hidup bagi umat manusia. Al-Qu’an memiliki kandungan makna dan hikmah disetiap ayatnya. Didalam Al-Qur’an terdapat ayat-ayat yang memiliki makna yang tersirat. Al-Qur’an mengandung beberapa topik yang antar surat Al-Qur’an dapat memiliki kemiripan topik dengan surat Al-Qur’an yang lainnya. Pada penelitian ini, dilakukan implementasi metode Support Vector Machine dan Word2vec pada terjemahan ayat Al-Qur’an berbahasa Inggris yang digunakan untuk pengklasifikasian berdasarkan topik. Kategori topik Al-Qur’an yang digunakan pada penelitian ini dibagi menjadi tiga yaitu perintah, larangan, dan lainnya. Dokumen tersebut diubah kedalam bentuk vektor dengan tf-idf weighting dan Word2vec. Vektor-vektor kata tersebut dipemetakan berdasarkan nilai kedekatan vektor antar kata pada dokumen. Selanjutnya metode Support Vector Machine digunakan untuk mengklasifikasikan topik Al-Qur’an dengan memberikan hyperplane pada tiap kategori. Hasil pengujian dari penelitian ini menunjukkan bahwa penerapan Word2vec dan Support Vector Machine mendapatkan nilai akurasi tertinggi sebesar 0.64 dengan jumlah data training sebesar 70% dari keseluruhan dataset.

Kata kunci : Topik Al-Qur’an, Klasifikasi, Support Vector Machine, Word2vec

Abstract The purpose of the Qur'an is as a guide for human’s life. Al-Qu’an has meaning and wisdom in every verse. In the Qur'an there are verses that have implied meaning. Al-Qur’an contains several topics which among the Surahs of the Qur'an can have a similarity to the topic of other Al-Qur’an's surah. In this research, the implementation of the Support Vector Machine and Word2vec method is used to classify based on topics in the English translation of Al-Qur’an verses. The used topic categories in this study are divided into three namely commands, prohibitions, and others. The document is converted into vector with tf-idf weighting and Word2vec. Then the word vectors are mapped based on the value of the proximity of the vectors between words in the document. Then Support Vector Machine method is used to classify the topic of the Qur'an by giving hyperplane in each category. The test results of this study showed that the implementation of Word2vec and Support Vector Machine has the highest accuracy results of 0.64 with the amount of training data is 70% of the entire dataset.

Keywords: Topics of Al-Qur’an, Classification, Support Vector Machine, Word2vec

Downloads

Download data is not yet available.

References

[1] Syaamil Qur’an, “Cordova Al-Qur’an and Translation” ,2004.

[2] Prayogo, A. H., and Adiwijaya. (2017). On the Feature Extraction for the English Holy Quran Tafseer Text Classification. 10.

[3] Yoshua Bengio, Ducharme Rejean, Vincent Pascal & Janvin Christian. “A Neural Probabilistic Language Model”, 2003. http://www.jmlr.org/papers/volume3/bengio03a/bengio03a.pdf

[4] Collobert Ronan, & Weston Jason. “A Unified Architecture for Natural Language Processing: Deep Neural Networks with Multitask Learning”. 2008. https://ronan.collobert.com/pub/matos/2008_nlp_icml.pdf

[5] Tomas Mikolov, Greg Corrado, Kai Chen & Jeffrey Dean. “Efficient Estimation of Word Representations in Vector Space”, 2013. https://arxiv.org/pdf/1301.3781.pdf

[6] M. Faruqui and C. Dyer, "Improving Vector Space Word Representations Using Multilingual Correlation", Carnegie Mellon University, 2014 hal.236-244

[7] Tomas Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean. Efficient Estimation of Word Representations in Vector Space, In Proceedings of Workshop at ICLR, 2013.

[8] Khandelwal, Renu. 2018. “Support Vector Machine”. Medium Corporation. https://medium.com/datadriveninvestor/support-vector-machines [diakses 9 Agustus 2019]

[9] Robertson, Stephen., 2005, Understanding Inverse Document Frequency: On Theoretical Arguments for IDF, England Journal of Documentation, Vol. 60, pp. 502 – 520.

[10] Tian, Wenfeng., and Li Hongguang., 2018, A Method of Feature Selection Based on Word2vec in Text Categorization: {roceeding of the 37th Chinese Control Conference.

[11] Tomas Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean. Efficient Estimation of Word Representations in Vector Space, In Proceedings of Workshop at ICLR, 2013.

[12] https://code.google.com/archive/p/Word2vec.

[13] Le, Q. Mikolov, T. Distributed Representations of Sentences and Documents. Google Inc, 1600 Amphitheatre Parkway, Mountain View, CA 94043

[14] Yulietha, I. M., Faraby, S. A., & Adiwijaya. (2017). Klasifikasi Sentiment Review Film Menggunakan Support Vector Machine. 10. [15] ] E. Prasetyo, Data Mining: Konsep dan Aplikasi menggunakan Matlab, 1 ed. Yogyakarta: Andi Offset, 2012. 17

[16] M. Sokolova dan G. Lapalme, “A sistematic analysis of performance measures for classification tasks,” Inf. Process. Manag., vol. 45, no. 4, hal. 427–437, 2009

[17] V. Labatut and H. Cherifi, “Evaluation of Performance Measures for Classifiers Comparison,” Ubiquitous Comput. Commun. Journal, pp. 621-34, 2011.

[18] F. Guillet and H. J. Hamilton, Quality Measures in Data Mining, Berlin: Springer, 2007.

Downloads

Published

2019-08-01

Issue

Pages

9133-9142

Section

Program Studi S1 Informatika

How to Cite

Salama, A., Adiwijaya, A., & Al Faraby, S. (2019). Klasifikasi Topik Ayat Al-qur’an Terjemahan Berbahasa Inggris Menggunakan Metode Support Vector Machine Berbasis Vector Space Model Dan Word2vec. EProceedings of Engineering, 6(2), 9133-9142. https://doi.org/10.34818/eoe.v6i2.9931