Perbandingan Metode Lexicon-based dan SVM untuk Analisis Sentimen Berbasis Ontologi pada Kampanye Pilpres Indonesia Tahun 2019 di Twitter

Authors

  • Ahmad Choirun Najib Institut Teknologi Sepuluh Nopember
  • Akhmad Irsyad Institut Teknologi Sepuluh Nopember
  • Ghiffari Assamar Qandi Institut Teknologi Sepuluh Nopember
  • Nur Aini Rakhmawati Institut Teknologi Sepuluh Nopember

DOI:

https://doi.org/10.21111/fij.v4i2.3573

Keywords:

analisis sentimen, twitter, ontology, svm, lexicon.

Abstract

AbstrakPenggunaan media sosial semakin hari semakin meningkat. Salah satu media sosial yang popular saat ini adalah Twitter. Menjelang pemilihan Presiden Republik Indonesia semakin banyak tweet yang membahas tentang kegiatan tersebut. Hal ini menyebabkan topik kampanye pemilu memiliki peluang yang baik untuk dilakukan proses analisis sentimen. Saat ini, mayoritas analisis sentimen di Indonesia dilakukan hanya menilai sentimen dari kalimat tanpa mengetahui apa entitas yang ada dalam kalimat. Tujuan penelitian ini yaitu melakukan analisis sentimen dengan pendekatan berbasis ontologi. Ontologi digunakan dalam menyaring data yang akan digunakan. Ontologi dalam penelitian ini adalah ekonomi dengan atribut finansial, lapangan kerja, dan kesejahteraan. Proses analisis sentimen dilakukan dengan metode Lexicon-based dan Support Vector Machine (SVM). Proses akuisisi data diperoleh sejumlah 700.000 tweet. Koleksi tersebut diseleksi berdasarkan ontologi ekonomi menghasilkan 16.998 tweet dan dilakukan pelabelan manual sebanyak 1.600. Kemudian dilakukan pengolahan data hingga diperoleh dataset final sejumlah 1.050 tweet. Berdasarkan hasil penelitian yang dilakukan akurasi yang diperoleh berdasarkan metode Lexicon-based adalah 39% dan metode SVM sebesar 83%. Dari penelitian ini diketahui bahwa SVM mempunyai performa yang lebih baik dibandingkan dengan Lexicon-based. Hasil Lexicon-based menunjukkan bahwa sentimen pada mayoritas atribut berupa netral. Sedangkan hasil SVM menunjukkan bahwa sentimen pada mayoritas atribut (finansial dan kesejahteraan) berupa positif, sisanya (lapangan kerja) berupa netral. Selanjutnya, proses ekstraksi dan pembuatan ontologi Bahasa Indonesia secara semi-otomatis pada dataset perlu untuk dikembangkan pada penelitian berikutnya untuk menyempurnakan ontologi.Kata kunci: Analisis Sentimen, Twitter, Ontology, SVM, Lexicon Abstract[Comparison of the Lexicon-based and SVM Method for Ontology-Based Analysis of the 2019 Presidential Election Campaign on Twitter] The use of social media is increasing. One of the most popular social media is Twitter. Towards the election of the President of the Republic of Indonesia, election topic tweets discussed almost every day. Hence, it is suitable for the sentiment analysis process. Nowadays, the sentiment analysis is only evaluating the sentence without knowing what the entity is in the sentence. To overcome this drawback, we propose a sentiment analysis based on ontology. Ontology is used to filter the data to be used. The ontology used in this study is economics with attributes, i.e., financial employment, and welfare. The sentiment analysis process is carried out using the Lexicon and Support Vector Machine (SVM) based methods. The process of acquiring data obtained 700,000 tweets. The collection was selected based on economic ontology to produce 16,998 tweets, and 1,600 manual labels were labelled. Then, the number of the final dataset is 1,050 tweets. The results show that the accuracy of the Lexicon-based method is 39%, and the SVM method is 83%. The SVM has better performance than Lexicon-based. Lexicon-based results show that the sentiment on the majority attributes is neutral. While the SVM results show that the sentiment on the majority attributes (financial and welfare) is positive, the rest (employment) is neutral. A semi-automatic ontology extraction and development for Bahasa Indonesia is necessary for the future works to make a comprehensive ontology and provide better results. Keywords: Sentiment Analysis, Twitter, Ontology, SVM, Lexicon

References

[1] “Kementerian Komunikasi dan Informatika.” [Online]. Available: https://kominfo.go.id/content/detail/2366/indonesia-peringkat-lima-pengguna-twitter/0/sorotan_media. [Accessed: 21-Oct-2019].[2] I. Sunni and D. H. Widyantoro, “Analisis sentimen dan ekstraksi topik penentu sentimen pada opini terhadap tokoh publik,” J. Sarj. ITB Bid. Tek. Elektro dan Inform., vol. 1, no. 2, 2012.[3] F. Nurhuda, S. W. Sihwi, and A. Doewes, “Analisis sentimen masyarakat terhadap calon Presiden Indonesia 2014 berdasarkan opini dari Twitter menggunakan metode Naive Bayes Classifier,” ITSMART J. Teknol. dan Inf., vol. 2, no. 2, pp. 35–42, 2014.[4] A. F. Hidayatullah and A. S. N. Azhari, “Analisis sentimen dan klasifikasi kategori terhadap tokoh publik pada twitter,” in Seminar Nasional Informatika (SEMNASIF), 2015, vol. 1, no. 1.[5] N. Monarizqa, L. E. Nugroho, and B. S. Hantono, “Penerapan Analisis Sentimen Pada Twitter Berbahasa Indonesia Sebagai Pemberi Rating,” J. Penelit. Tek. Elektro dan Teknol. Inf., vol. 1, no. 3, 2014.[6] A. Novantirani, M. K. Sabariah, and V. Effendy, “Analisis Sentimen pada Twitter untuk Mengenai Penggunaan Transportasi Umum Darat Dalam Kota dengan Metode Support Vector Machine,” eProceedings Eng., vol. 2, no. 1, 2015.[7] G. A. Buntoro, “Analisis Sentimen Calon Gubernur DKI Jakarta 2017 Di Twitter,” INTEGER J. Inf. Technol., vol. 2, no. 1, 2017.[8] E. Kontopoulos, C. Berberidis, T. Dergiades, and N. Bassiliades, “Ontology-based sentiment analysis of twitter posts,” Expert Syst. Appl., 2013.[9] I. Kurniawan and A. Susanto, “Implementasi Metode K-Means dan Naïve Bayes Classifier untuk Analisis Sentimen Pemilihan Presiden (Pilpres) 2019,” Eksplora Inform., 2019.[10] A. Lestari and D. Karolita, “ Summarizing Netizens’ Sentiments Towards the 1 st Indonesian Presidential Debate using Lexicon Sentiment Analysis ,” IOP Conf. Ser. Mater. Sci. Eng., 2019.[11] R. Studer, V. R. Benjamins, and D. Fensel, “Knowledge Engineering: Principles and methods,” Data Knowl. Eng., 1998.[12] J. Euzenat and P. Shvaiko, Ontology matching. 2007.[13] Bernhard Ganter and R. Wille, Formal Concept Analysis: Mathematical Foundations. 1999.[14] T. A. Le, D. Moeljadi, Y. Miura, and T. Ohkuma, “Sentiment Analysis for Low Resource Languages: A Study on Informal Indonesian Tweets,” in Proceedings of the 12th Workshop on Asian Language Resources (ALR12), 2016.[15] F. Heimerl, S. Lohmann, S. Lange, and T. Ertl, “Word cloud explorer: Text analytics based on word clouds,” in Proceedings of the Annual Hawaii International Conference on System Sciences, 2014.

Downloads

Submitted

2019-10-23

Accepted

2019-11-24

Published

2019-11-24

Issue

Vol. 4 No. 2 (2019): November

Section

Articles

License

Please find the rights and licenses in the Fountain of Informatics Journal (FIJ). By submitting the article/manuscript of the article, the author(s) agree with this policy. No specific document sign-off is required.

1. License

The non-commercial use of the article will be governed by the Creative Commons Attribution license as currently displayed on Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License. 

2. Author(s)' Warranties

The author warrants that the article is original, written by the stated author(s), has not been published before, contains no unlawful statements, does not infringe the rights of others, is subject to copyright that is vested exclusively in the author, and free of any third party rights, and that any necessary written permissions to quote from other sources have been obtained by the author(s).

3. User/Public Rights

FIJ's spirit is to disseminate articles published are as free as possible. Under the Creative Commons license, FIJ permits users to copy, distribute, display, and perform the work for non-commercial purposes only. Users will also need to attribute authors and FIJ on distributing works in the journal and other media of publications. Unless otherwise stated, the authors are public entities as soon as their articles got published. 

4. Rights of Authors

Authors retain all their rights to the published works, such as (but not limited to) the following rights;

  • Copyright and other proprietary rights relating to the article, such as patent rights,
  • The right to use the substance of the article in own future works, including lectures and books,
  • The right to reproduce the article for own purposes,
  • The right to self-archive the article (please read out deposit policy),
  • The right to enter into separate, additional contractual arrangements for the non-exclusive distribution of the article's published version (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal (Jurnal Optimasi Sistem Industri).

5. Co-Authorship

If the article was jointly prepared by more than one author, any authors submitting the manuscript warrants that he/she has been authorized by all co-authors to be agreed on this copyright and license notice (agreement) on their behalf, and agrees to inform his/her co-authors of the terms of this policy. FIJ will not be held liable for anything that may arise due to the author(s) internal dispute. FIJ will only communicate with the corresponding author.

6. Royalties

Being an open accessed journal and disseminating articles for free under the Creative Commons license term mentioned, author(s) aware that FIJ entitles the author(s) to no royalties or other fees. 

7. Miscellaneous

FIJ will publish the article (or have it published) in the journal if the article’s editorial process is successfully completed. FIJ's editors may modify the article to a style of punctuation, spelling, capitalization, referencing, and usage that deems appropriate. The author acknowledges that the article may be published so that it will be publicly accessible and such access will be free of charge for the readers as mentioned in point 3.