Implementation of Text-Mining For Sentiment Analysis Twitter With Support Vector Machine Algorithm

  • Indrico Jowensen Jasumin
  • Aditiya Hermawan
Keywords: Support Vector Machine

Abstract

Text Mining can make it possible to analyze sentiments quickly. In this implementation, the process of capturing text is done with the help of the API. Twitter is used as an object of research because Twitter provides a medium for the process of retrieving data quickly by using keywords in the form of a word or hashtag. The form of implementation made in this study is the website. This website is made with the Django framework with the Python programming language. To produce sentiments, a data mining process is needed. This data mining process uses a support vector machine algorithm and this process takes place in the backend of a website. The level of accuracy generated by this data mining process is 73%. The purpose of this sentiment analysis is used so that the data that has been collected can be used as useful information.

References

Bing, L., Minqing, H. & Cheng, J., 2005. Opinion Observer: Analyzing and Comparing Opinions on the Web." Proceedings of the 14th International World Wide Web Conference (WWW-2005). WWW '05 Proceedings of the 14th international conference on World Wide Web, pp. 342-351.
Kamus Bahasa Indonesia, (2008). Kamus Bahasa Indonesia. 5th red. Jakarta: Pusat Bahasa.
Kemp, S., (2019). Digital 2019: Global Digital Overview, Vancouver: Hootsuite.
Purbo, O. W., 2019. Text Mining Analisis MedSos, Kekuatan Brand & Intelijen di Internet. Yogyakarta: Penerbit ANDI.
Vapnik, V., (1995). The Nature of Statistical Learning Theory. Berlin: Springer.
Visual Capitalist, 2019. How Much Data is Generated Each Day?. [Online]
Available at: https://www.visualcapitalist.com/wp-content/uploads/2019/04/data-generated-each-day-full.html
[Använd 22 10 2019].
Wahid, D. H. & Azhari, S. N., 2016. Peringkasan Sentimen Esktraktif di Twitter Menggunakan Hybrid TF-IDF dan Cosine Similarity. Indonesian Journal of Computing and Cybernetics Systems, 10(2), pp. 207-218.
Zulfa, I. & Winarko, E., (2017). Sentimen Analisis Tweet Berbahasa Indonesia dengan Deep Belief Network. IJCCS (Indonesian Journal of Computing and Cybernetics Systems), Volym 11, pp. 187-198.
Published
2022-01-01
How to Cite
Jasumin, I. J., & Hermawan, A. (2022). Implementation of Text-Mining For Sentiment Analysis Twitter With Support Vector Machine Algorithm. Selangor Science & Technology Review (SeSTeR), 5(4). Retrieved from https://sester.journals.unisel.edu.my/ojs/index.php/sester/article/view/239
Issue
Vol 5 No 4 (2021): Diversity and Inclusion in Digital Communities
Section
Articles in English

All materials contained within this journal are protected by Intellectual Property Corporation of Malaysia, Copyright Act 1987 and may not be reproduced, distributed, transmitted, displayed, published, or
broadcast without the prior, express written permission of Centre for Graduate Studies, Universiti Selangor, Malaysia. You may not alter or remove any copyright or other notice from copies of this content.