ABSTRAKMedia sosial adalah salah satu media yang menghubungkan orang-orang diseluruh dunia. Namun media sosial juga menjadi sarana untuk penyebaran hal-hal negatif seperti pornografi. Berita pornografi yang mendapat banyak perhatian ditahun 2017 yaitu pornografi pada kaum homoseksual yang melakukan pesta seks di beberapa kota di Indonesia. Kehadiran para kaum homoseksual dilarang di Indonesia dan mendapat diskriminasi dari masyarakat. Penolakan yang dialami membuat kaum homoseksual membuat kaum tersebut menggunakan media sosial seperti Twitter untuk membuka diri di khalayak umum, mencari pasangan sejenis, dan mencari penghasilan. Penelitian ini dilakukan sentimen analisis pada tweet Twitter sebagai text mining menggunakan metode Naïve Bayes. Tujuan penelitian ini adalah mengetahui hasil sentimen positif dan negatif terhadap data uji tweet dan berdasarkan hasil pengujian tersebut dapat disampaikan kepada pengguna Twitter secara luas untuk menggunakan Twitter secara tepat. Selain itu juga, perhitungan Naive Bayes dibandingkan dengan k-Nearest Neighbor (k-NN) untuk mengetahui tingkat akurasi. Hasil sentimen analisis terhadap 500 data uji menunjukkan bahwa nilai sentimen negatif sangat tinggi yaitu 68.4%. Sedangkan hasil perbandingan akurasi kedua metode adalah metode Naïve Bayes sebesar 87.48% dan k-NN 85.40% dimana metode Naïve Bayes lebih akurasi dibanding metode k-NN.Kata kunci: twitter, sentimen analisis, homoseksual, naïve bayes, k-NN. ABSTRACT Social media is one of media that connects people around the world. However, social media is also a media for the spread of negative things such as pornography. The pornography news that gets a lot of attention in 2017 is
Social media is a communication media that is often used to connect many people around the world. The inappropriate use of social media will have a negative impact. The example is the spread of hoaxes. Hoax is a topic that shared by many accounts on social media. These accounts are referred as influencers. This research aims to identify influencers in social media. This research use hoax dataset. The methods are Social Network Analysis (SNA) and weighting of SNA measurements. The results of this study are a list of SNA measurement results which are then combined using weighting. The results indicate the social media accounts that act as the major influencers and their relationships with other accounts. The relation is shown in a model to know the path of the spread.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.