Analisis Sentimen Twitter Bahasa Indonesia Dengan Word2vec

Authors

  • Farhan Wahyu Kurniawan Telkomuniversity
  • Warih Maharani Telkomuniversity

DOI:

https://doi.org/10.34818/eoe.v7i2.12934

Abstract

Abstrak Sentimen merupakan opini seseorang terhadap suatu topik, produk, atau layanan tertentu. Analisis sentimen digunakan untuk menganalisis opini terhadap suatu topik tertentu apakah cenderung positif atau negatif. Media sosial Twitter digunakan oleh masyarakat Indonesia untuk menuliskan opini mereka dalam bentuk cuitan (tweet). Penelitian ini menjelaskan klasifikasi sentimen pada data Twitter berbahasa Indonesia untuk membantu dalam memahami sentimen pengguna Indonesia terhadap suatu topik yang dibahas di Twitter. Penelitian ini menggunakan metode word2vec untuk mengekstraksi fitur dengan mengkonversi data menjadi nilai vektor. Word2Vec memiliki keunggulan dapat melihat hubungan semantik antar kata. Metode klasifikasi pada penelitian ini menggunakan support vector machine (SVM). Proses klasifikasi sentimen dilakukan dengan mengolah data latih berupa data cuitan yang sudah dikumpulkan yang kemudian menjadi model untuk proses pengujian pada data uji. Dari hasil pengujian, penerapan metode word2vec dan SVM menghasilkan tingkat presisi sebesar 64,4%, recall sebesar 58%, dan f-score sebesar 61,1% Kata kunci : analisis sentimen, twitter, word2vec, svm Abstract Sentiment is an opinion of someone on a certain topics, products or services. Sentiment Analysis is used to analyze opinion on a certain topics to decide whether they are positive or negative. Twitter is used by Indonesian to express their opinion in the form of tweets. This study used word2vec method to extract features by converting data into vector score. Word2Vec has the advantage of being able to see semantic relationships between words. This study used support vector machine (SVM) classification method. The sentiment classification process is done by processing training data in the form of collected tweets then turned into model to be tested with testing data. This result of applying word2vec and SVM produce score of precision 64,4%, recall 58%, and f-score 61,1%. Keywords: sentiment analysis, twitter, word2vec, svm

Downloads

Download data is not yet available.

References

[1] M. K. Sohrabi and F. Hemmatian, "An efficient preprocessing method for supervised sentiment analysis by converting sentences to numerical vectors: a twitter case study," Multimedia Tools and Applications, pp. 1-20, 2019.

[2] B. Liu, Sentiment Analysis and Opinion Mining: Synthesis Lectures on Human Language Technologies, Morgan & Claypool Publishers, 2012.

[3] M. Z. Asghar, A. Khan, S. Ahmad and F. M. Kundi, "A review of feature extraction in sentiment analysis," Journal of Basic and Applied Scientific Research, pp. 181-186, 2014.

[4] G. Paltoglou and M. Thelwall, " A study of information retrieval weighting schemes for sentiment analysis," Proceedings of the 48th annual meeting of the association for computational linguistics, pp. 1386-1395, 2010.

[5] J. Ramos, "Using tf-idf to determine word relevance in document queries," Proceedings of the first instructional conference on machine learning, pp. 133-142, 2003.

[6] D. Zhang, H. Xu, Z. Su and Y. Xu, "Chinese comments sentiment classification based on word2vec and svmperf," Expert Systems with Applications, pp. 1857-1863, 2015.

[7] H. Bhavsar and A. Ganatra, " A comparative study of training algorithms for supervised machine learning," International Journal of Soft Computing and Engineering (IJSCE), pp. 2231-2307, 2012.

[8] A. Giachanou and F. Crestani, " Like it or not: A survey of twitter sentiment analysis methods," ACM Computing Surveys (CSUR), 2016.

[9] A. F. Hidayatullah and M. R. Ma’arif, "Pre-processing tasks in Indonesian Twitter messages," Journal of Physics: Conference Series, 2017.

[10] W. Tian, J. Li and H. Li, "A method of feature selection based on word2vec in text categorization," 37th Chinese Control Conference (CCC), pp. 9452-9455, 2018.

[11] T. Mikolov, K. Chen, G. Corrado and J. Dean, " Efficient estimation of word representations in vector space," 2013.

[12] T. Mikolov, I. Sutskever, K. Chen, G. S. Corrado and J. Dean, "Distributed representations of words and phrases and their compositionality," Advances in neural information processing systems , pp. 3111-3119, 2013.

Downloads

Published

2020-08-01

Issue

Pages

7821-7829

Section

Program Studi S1 Informatika

How to Cite

Kurniawan, F. W., & Maharani, W. (2020). Analisis Sentimen Twitter Bahasa Indonesia Dengan Word2vec. EProceedings of Engineering, 7(2), 7821-7829. https://doi.org/10.34818/eoe.v7i2.12934