Klasifikasi Hashtag Buzzer/bot Menggunakan Algoritma Random Forest Dengan Atribut Komunitas Untuk Mengurangi Disinformasi Pada Twitter
DOI:
https://doi.org/10.34818/eoe.v9i3.17994Abstract
Abstrak Saat ini persebaran informasi terjadi secara cepat pada sosial media. Namun, tidak semua informasi yang beredar pada sosial media belum tentu merupakan informasi yang benar. Twitter sebagai salah satu media sosial terbesar didunia juga mengalami masalah yang sama. Banyak sekali informasi dan juga hashtag yang tersebar pada twitter merupakan informasi dan hashtag yang disebarluaskan oleh buzzer. Dalam tugas akhir ini, penulis membangun sebuah sistem klasifikasi yang dapat membedakan antara sebuah hashtag natural dan hashtag yang dibuat oleh buzzer pada sosial media twitter. Penulis memakai algoritma random forest dengan memanfaatkan atribut komunitas untuk melakukan klasifikasi hashtag pada sistem yang dibuat. Penulis juga akan mencari tahu apa saja atribut yang paling berpengaruh dalam proses klasifikasi tersebut. Pada penelitian ini, didapatkan bahwa sistem mampu mendeteksi hashtag buzzer dengan tingkat akurasi sebesar 98% dan tingkat fmeasure sebesar 98% berdasarkan dataset yang telah penulis dapatkan. Didapatkan juga bahwa atribut atribut yang berpengaruh dalam proses klasifikasi antara lain adalah atribut seperti unique_user_pertweet dan q1_rasio Kata kunci : buzzer, random forest, hashtag, trending topic, twitterReferences
[1] A. J. Panatra, F. B. Chandra, W. Darmawan, H. L. H. S. Warnars, W. H. Utomo, and T. Matsuo, “Buzzer Detection to Maintain Information Neutrality in 2019 Indonesia Presidential Election,” Proc. - 2019 8th Int. Congr. Adv. Appl. Informatics, IIAI-AAI 2019, pp. 873–876, 2019, doi: 10.1109/IIAI-AAI.2019.00177.
[2] K. M. Carley, M. Malik, M. Kowalchuck, J. Pfeffer, and P. Landwehr, “Twitter Usage in Indonesia,” SSRN Electron. J., 2018, doi: 10.2139/ssrn.2720332.
[3] M. Cheong, “What are you Tweeting about ?’: A survey of Trending Topics within Twitter,” Search, pp. 1–12, 2009, [Online]. Available: http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.158.4679.
[4] A. Suciati, A. Wibisono, and P. Mursanto, “Twitter Buzzer Detection for Indonesian Presidential Election,” ICICOS 2019 - 3rd Int. Conf. Informatics Comput. Sci. Accel. Informatics Comput. Res. Smarter Soc. Era Ind. 4.0, Proc., 2019, doi: 10.1109/ICICoS48119.2019.8982529.
[5] S. Bradshaw and P. N. Howard, “The Global Disinformation Order 2019 Global Inventory of Organised Social Media Manipulation,” Univ. Oxford, p. 25, 2019, [Online]. Available: https://comprop.oii.ox.ac.uk/wp-content/uploads/sites/93/2019/09/CyberTroop-Report19.pdf.
[6] S. Sugiono, “Fenomena Industri Buzzer Di Indonesia: Sebuah Kajian Ekonomi Politik Media,” Commun. J. Ilmu Komun., vol. 4, no. 1, pp. 47–66, 2020, doi: 10.15575/cjik.v4i1.7250.
[7] C. Juditha, “Buzzer di Media Sosial Pada Pilkada dan Pemilu Indonesia Buzzer in Social Media in Local Elections and Indonesian Elections,” pp. 199–212, 2019.
[8] B. Arianto, “Salah Kaprah Ihwal Buzzer: Analisis Percakapan Warganet di Media Sosial,” J. Ilm. Ilmu Pemerintah., vol. 5, no. 1, pp. 1–20, 2020, doi: 10.14710/jiip.v5i1.7287.
[9] D. Kotsakos, P. Sakkos, I. Katakis, and D. Gunopulos, “#tag: Meme or event?,” ASONAM 2014 - Proc. 2014 IEEE/ACM Int. Conf. Adv. Soc. Networks Anal. Min., no. Asonam, pp. 391–394, 2014, doi: 10.1109/ASONAM.2014.6921615.
[10] E. Ferrara, “Disinformation and social bot operations in the run up to the 2017 French presidential election,” First Monday, vol. 22, no. 8, 2017, doi: 10.5210/fm.v22i8.8005.
[11] Z. Chu, S. Gianvecchio, H. Wang, and S. Jajodia, “Detecting automation of Twitter accounts: Are you a human, bot, or cyborg?,” IEEE Trans. Dependable Secur. Comput., vol. 9, no. 6, pp. 811–824, 2012, doi: 10.1109/TDSC.2012.75.
[12] T. A. Small, “WHAT THE HASHTAG ? Tamara A . Small WHAT THE HASHTAG ? A content analysis of Canadian politics on Twitter,” vol. 4462, no. May, 2011, doi: 10.1080/1369118X.2011.554572.
[13] C. Juditha, B. Besar, P. Komunikasi, and B. Makassar, “FENOMENA TRENDING TOPIC DI TWITTER : ANALISIS WACANA TWIT # SAVEHAJILULUNG TRENDING TOPIC PHENOMENON ON TWITTER : DISCOURSE ANALYSIS OF TWEET # SAVEHAJILULUNG,” vol. 16, no. 2, pp. 138–154, 2015.
[14] G. Magno and T. Rodrigues, “Benevenuto2010,” Ceas, no. Seventh annual Collaboration, Electronic messaging, AntiAbuse and Spam Conference, p. 10, 2010.
[15] M. Ibrahim, O. Abdillah, A. F. Wicaksono, and M. Adriani, “Buzzer Detection and Sentiment Analysis for Predicting Presidential Election Results in a Twitter Nation,” Proc. - 15th IEEE Int. Conf. Data Min. Work. ICDMW 2015, pp. 1348–1353, 2016, doi: 10.1109/ICDMW.2015.113.
[16] M. T. Juzar and S. Akbar, “Buzzer Detection on Twitter Using Modified Eigenvector Centrality,” Proc. 2018 5th Int. Conf. Data Softw. Eng. ICoDSE 2018, pp. 1–5, 2018, doi: 10.1109/ICODSE.2018.8705788.
[17] R. Mustika, “Pergeseran Peran Buzzer Ke Dunia Politik Di Media Sosial,” Diakom J. Media dan Komun., vol. 2, no. 2, pp. 144–151, 2019, doi: 10.17933/diakom.v2i2.60.
[18] M. Jeon, S. Jun, and E. Hwang, “Hashtag Recommendation Based on User Tweet and Hashtag Classi fi cation on Twitter,” pp. 325–336, 2014, doi: 10.1007/978-3-319-11538-2.
[19] G. Valkanas, A. Saravanou, and D. Gunopulos, “A faceted crawler for the Twitter service,” Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), vol. 8787, pp. 178–188, 2014, doi: 10.1007/978-3-319-11746-1_13.
[20] J. E. Sembodo, E. B. Setiawan, and A. Baizal, “Data Crawling Otomatis pada Twitter,” no. October 2018, pp. 10–16, 2016, doi: 10.21108/INDOSC.2016.111.
[21] A. Ambarwari, Q. Jafar Adrian, and Y. Herdiyeni, “Analysis of the Effect of Data Scaling on the Performance of the Machine Learning Algorithm for Plant Identification,” J. RESTI (Rekayasa Sist. dan Teknol. Informasi), vol. 4, no. 1, pp. 117–122, 2020, doi: 10.29207/resti.v4i1.1517.
[22] I. M. Nasir et al., “Pearson correlation-based feature selection for document classification using balanced training,” Sensors (Switzerland), vol. 20, no. 23, pp. 1–18, 2020, doi: 10.3390/s20236793.
[23] L. Yu and H. Liu, “Efficient Feature Selection via Analysis of Relevance and Redundancy,” vol. 5, pp. 1205–1224, 2004.
[24] P. Schober and L. A. Schwarte, “Correlation coefficients: Appropriate use and interpretation,” Anesth. Analg., vol. 126, no. 5, pp. 1763–1768, May 2018, doi: 10.1213/ANE.0000000000002864.
[25] A. Cutler, D. R. Cutler, and J. R. Stevens, “Ensemble Machine Learning,” Ensemble Mach. Learn., no. February 2014, 2012, doi: 10.1007/978-1-4419-9326-7.
[26] L. E. O. Breiman, “Random Forests,” pp. 5–32, 2001.
[27] L. E. O. Bbeiman, “Bagging Predictors,” vol. 140, pp. 123–140, 1996.
[28] T. Yui, “Understanding Random Forest. How the Algorithm Works and Why it Is So Effective,” Towards Data Science, 2019. https://towardsdatascience.com/understanding-random-forest-58381e0602d2 (accessed Jan. 31, 2022).
[29] T. M. Oshiro, P. S. Perez, and J. A. Baranauskas, “How many trees in a random forest?,” Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), vol. 7376 LNAI, pp. 154–168, 2012, doi: 10.1007/978-3-642-31537-4_13.
[30] T. K. Ho, “The Random Subspace Method for Constructing Decision Forests,” vol. 20, no. 8, pp. 832–844, 1998.
[31] L. Rokach and O. Maimon, “Chapter 9,” no. August 2015, 2005, doi: 10.1007/0-387-25465-X.
[32] S. Visa, B. Ramsay, A. Ralescu, and E. Van Der Knaap, “Confusion matrix-based feature selection,” in CEUR Workshop Proceedings, 2011, vol. 710, pp. 120–127.
