TEXT MINING DAN SENTIMEN ANALISIS TWITTER PADA GERAKAN LGBT

Hartanto Hartanto(1),

DOI: https://doi.org/10.15294/intuisi.v9i1.9561


(1) Fakultas Psikologi, Universitas Widya Dharma, Klaten

Abstract

Abstrak. Tujuan penelitian ini untuk mendeskripsikan frekuensi opini kicauan di Twitter terkait pro dan kontra terhadap gerakan LGBT. Riset ini termasuk dalam penelitian data mining kuantitatif dan terbagi dalam dua tahap. Pertama, analisis text mining wordclouds dan dilanjutkan analisis sentiment dalam tweet. Pendekatan sub metode bags of word dilakukan untuk merangkai sentiment dari twitter. Negative dan positive words murni melakukan perubahan dari sentiment lexicon Bing Liu dengan melakukan adaptasi ke bahasa Indonesia. Stop words yang merupakan bagian dari analisis text mining juga disesuaikan untuk kebutuhan analisis. Hasil yang didapat mengenai gerakan LGBT cukup konsisten dengan kondisi terkini, hasil dari wordclous simetris dengan histogram analisis sentiment, dimana frekuensi kata seperti “kumpul kebo”, “moral”, “Indonesia”, “perbincangan”, “dibui”, “pindah”, “ditantang”, “garis batas” terbilang tinggi, dan sebanyak 379 tweet beropini netral, 79 menyatakan positif dengan gerakan LGBT dan 27 menyatakan sikap negative.

 

Abstract. Aim of this study is to describe the frequency of tweets on Twitter opinion related to the pros and cons of the LGBT movement. The core method research on text mining and sentiment analysis wordclouds with R was aplicated for this research. Bags of word method is done to assemble the sentiment of twitter. Negative and positive word of pure change of sentiment lexicon Bing Liu are adapted to Indonesian. Stop words that are part of the analysis of text mining is also made to meet up the needs of analysis. The results of the LGBT movement is quite consistent with the current conditions, the results of wordclous symmetrical with the analysis of sentiment, where the frequency of words such as "cohabiting", "moral", "Indonesia", "conversation", "jail", "move", " challenged "," borderline "is high, and as many as 379 is neutral tweet opinion, 79 expressed positive with the LGBT movement and 27 expressed negative attitudes toward it.

Keywords

text mining, sentiment analysis, machine learning, LGBT movement

Full Text:

PDF

References

Alim, S. (2015). Analysis of Tweets Related to Cyberbullying: Exploring Information Diffusion and Advice Available for Cyberbullying Victims. International Journal of Cyber Behavior, Psychology and Learning, 5(4), 31-52, October-December 2015.

Blatnik, A. jarm, K. & Meza, M. (2015). Movie sentiment analysis based on public tweets. ELEKTROTEHNIˇSKI VESTNIK 81(4) : 160–166, 2014.

Carchiolo, V. Longheu, A. & Malgeri, M. (2015). Using Twitter Data and Sentiment Analysis to Study Diseases Dynamics. M.E. Renda et al. (Eds.): ITBAM 2015, LNCS 9267, pp. 16–24, 2015.

Hon, L, C. & Varathan, K, D. (2015). Cyberbullying Detection System on Twitter. International Journal of Information System and Engineering. Vol 1 (No.1), April 2015.

Kouloumpis, E. Wilson, T. & Moore, J. (2011). Twitter Sentiment Analysis – The Good and The Bad and The OMG!. Proceedings of the Fifth International AAAI Conference on Weblogs and Social Media.

Liu, B. (2015). Sentiment Analysis. Cambridge University Press. www.cambridge.org

Leismester, C. (2015). Mastering Machine Learning with R. Published by Packt Publishing Ltd. Livery Place 35 Livery Street

Ming-Xu, J. Zhu, X. & Bellmore, A. (2012). Fast Learning for Sentiment Analysis on Bullying. WISDOM ’12, August 12 2012, Beijing, China. Copyright 2012 ACM 978-1-4503-1543-2/12/08

Ohri, A. (2014). R for Cloud Computing. Springer Science+Business Media New York 2014

Pak, A. & Paroubek, P. (2010). Twitter as Corpus for Sentiment Analysis and Opinion Mining. In Proceeding in LREC

Pang, B. & Lee, L. (2008). Opinion Mining and Sentiment Analysis. Foundations and Trends In Information Retrieval Vol. 2, Nos. 1–2 (2008) 1–135 C 2008 B. Pang and L. Lee

Pathak, M, A. (2014). Beginning Data Science with R. Springer International Publishing Switzerland 2014.

Talbot, R. Acheampong, C. & Wicentowski, R. (2015). SWASH: A Naive Bayes Classifier for Tweet Sentiment Identification. Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015), pages 626–630.

Witten, I,H. Frank, E. & Hall, M, A. (2011). Data Machine – practical machine learning tools and technique. Morgan Kaufmann Publisher is in imprint Elsevier. USA

https://github.com/masdevid/ID-OpinionWords Grishman, R. 2012.cs.nyu.edu/~fergus/teaching/vision_2012/9_BoW.pd

Refbacks

  • There are currently no refbacks.


Bookmark and Share


Creative Commons License
This work is licensed under a  Creative Commons Attribution 4.0 International License.