Analisis Pengguna Berpengaruh Di Media Sosial Twitter Menggunakan Metode Twitterrank
DOI:
https://doi.org/10.34818/eoe.v7i2.12790Abstract
Abstrak Twitter adalah jejaring sosial yang berkembang pesat saat ini, karena pengguna dapat berinteraksi dengan pengguna lainnya (disebut user) dimanapun dan kapanpun. Twitter memberi akses pada para pengguna- nya untuk mengirimkan pesan singkat yang terdiri dari maksimal 140 karakter (disebut tweet). Melalui tweet ini, pengguna dapat berinteraksi dan menyebarkan informasi kepada pengguna lainnya. Peneliti- an ini menggunakan metode TwitterRank yang bertujuan untuk melakukan klasifikasi dan mengevaluasi pengguna yang paling berpengaruh pada penyebaran informasi berdasarkan hashtag #KartiniDay. Meto- de ini dihitung berdasarkan tweet yang dibuat pengguna dengan tiga indikator, yaitu Followers Influence (FI), Retweet Influence (RI), dan Favorite Influence (FVI). Kemudian, pengguna diklasifikasikan kedalam beberapa kelompok pengguna berdasarkan nilai indikator yang didapat, yaitu kelompok pengguna highly influential user, influential user, potential influential user, dan not influential user. Hasil pengukuran penga- ruh pengguna dengan menggunakan perhitungan akurasi yaitu 0.614 atau 61.4%, perhitungan presisi yaitu 0.266 atau 26.6%, perhitungan recall yaitu 0.0878 atau 8.78%, dan perhitungan f-measure yaitu 0.071 atau 7.1%. Kata kunci : TwitterRank, hashtag, peringkat, klasifikasi. Abstract Twitter is a social network that is growing rapidly nowadays, because users can interact with other users (called users) wherever and whenever. Twitter gives users access to send short messages consisting of up to 140 characters (called tweets). Through this tweet, users can interact and spread information to other users. This research uses TwitterRank method which aims to identify the ranking of the most influential users on information spreading based on the hashtag #KartiniDay. This method is calculated based on tweets made by the user with three indicators, namely Followers Influence (FI), Retweet Influence (RI), and Favorite Influence (FVI). Then, users are classified into several groups of users based on the obtained indicator values, namely the group of highly influential users, influential users, potential influential users, and not influential users. The results of measuring the influence of the user by using an accuracy calculation are 0.614 or 61.4%, the precision calculation is 0.266 or 26.6%, the recall calculation is 0.0878 or 8.78%, and for the f-measure calculation is 0.071 or 7.1%. Keywords: TwitterRank, hashtag, rank, classification
Downloads
References
[1] I. Anger and C. Kittl. Measuring influence on twitter. Proceedings of the 11th International Conference on Knowledge Management and Knowledge Technologies, pages 1–4, 2011.
[2] T. J. Bristol. Twitter: Consider the possibilitiesfor continuing nursing education. The Journal of Continuing Education in Nursing, pages 199–200, 2010.
[3] M. Cha, H. Haddadi, F. Benevenuto, and K. P. Gummadi. Measuring user influence in twitter: The million follower fallacy. Proceedings of the 4th International AAAI Conference on Weblogs and Social Media, pages 10–17, 2010.
[4] A. Gupta, H. Lamba, P. Kumaguru, and A. Joshi. Faking sandy: Characterizing and identifying fake images on twitter during hurricane sandy. Proceedings of the 22nd International Conference on World Wide Web Companion, pages 729–736, 2013.
[5] Junaidi. Deskripsi data melalui box-plot. 2015.
[6] X. Ma, C. Li, J. Bailey, and S. Wijewickrema. Finding influentials in twitter: A temporal influence ranking model. ArXiv, 2017.
[7] F. Maclean, D. Jones, G. Carin-Levy, and H. Hunter. Understanding twitter. British Journal of Occupational Therapy, pages 295–298, 2013.
[8] M. Montangero and M. Furini. Trank: ranking twitter users according to specific topics. 12th Annual IEEE Consumer Communication and Networking Conference (CNCC), pages 767–772, 2015.
[9] S. Notoatmodjo. Metodologi Penelitian Kesehatan. Rineka Cipta, 2012.
[10] K. Rosman. On twitter, more ’favoriting’: Why more people are pushing the favorite button. The Wallstreet Journal, 2013.
[11] G. Stringhini, G. Wang, M. Egele, C. Kruegel, G. Vigna, H. Zheng, and B. Y. Zhao. Follow the green: Growth and dynamics in twitter follower marketers. Proceeding of the 2013 Conference on Internet Measurement Conference, pages 163–176, 2013.
[12] B. J. P. Utomo, M. A. Bijaksana, and A. Romadhony. Answer classification using multiple features extraction. e-Proceeding of Engineering, 3:3700–3710, 2016.
[13] J. Weng, E.-P. Lim, J. Jiang, and Q. He. Twitterrank: Finding topic-sensitive influential twitter. Proceeding of The Third ACM International Conference on Web Search and Data Mining, pages 261–270, 2010.



