PENERAPAN METODE SURF DAN FLANN UNTUK MENDETEKSI TERBITAN SPAM PADA INSTAGRAM
Abstract
Social media is a new media that utilizes the internet to share information, interact, participate and others, and to be used with each other. Currently there are many social media circulating, one of which is Instagram. At first Instagram was only used to share photos, then along with the development of technology and media, Instagram also developed into being able to share videos and shop on Instagram. Instagram is also one of the social media specifically used to upload images and videos. The growing use of Instagram in supporting promotion makes Instagram faced with various problems, one of which is the emergence of spam issues. For example, the publication of spam on Instagram is published by several sellers of products or the like continuously. It's good to promote a product. But on the other hand, it will interfere with other users if the spam often appears. This is exacerbated by the mass use of popular hashtags, done with the aim of getting more views. Popular hashtags are hashtags that are followed by many Instagram users. Based on these problems, it takes a computer program to detect spam issues based on certain hashtags on Instagram. In this final task, the Speeded-Up Robust Features (SURF) and Fast Library for Approximate Nearest Neighbor (FLANN) methods will be applied to detect spam publications on Instagram. The results of experiments that have been conducted on 12 images that produce 66 comparisons, the application of SURF and FLANN methods can be said to be very good in detecting the similarity of images between Instagram publications that indicate that the same image is a spam issue, which is with a maximum accuracy value of 100%.
References
[2] N. A. Haqimi, N. Rokhman, dan S. Priyanta, “Detection of spam comments on instagram using complementary naïve bayes,” IJCCS (Indonesian Journal of Computing and Cybernetics Systems), vol. 13, no. 3, hlm. 263–272, 2019.
[3] Y. Lukito, “Deteksi komentar spam Bahasa Indonesia pada Instagram menggunakan naïve bayes,” Ultimatics: Jurnal Teknik Informatika, vol. 9, no. 1, hlm. 50–58, 2017.
[4] A. WAHYUNINGTYAS, I. S. SITANGGANG, dan H. KHOTIMAH, “Deteksi Spam pada Twitter Menggunakan Algoritme Naïve Bayes Spam Detection on Twitter using Naïve Bayes Algorithm,” vol, vol. 7, hlm. 31–40.
[5] A. R. Chrismanto, Y. Lukito, dan J. D. W. Sudirohusodo, “Identifikasi Komentar Spam Pada Instagram,” Lontar Komputer, vol. 8, no. 3, hlm. 219–231, 2017.
[6] R. Oksaputri, E. Ernawati, dan D. Andreswari, “Implementasi Content Based Image Retrieval (CBIR) Pada Citra Batik Besurek Yang Tidak Utuh Menggunakan Metode Speeded Up Robust Features (SURF) dan Fast Library Approximated Nearest Neighbor (FLANN),” Pseudocode, vol. 5, no. 2, hlm. 18–28, 2018.
[7] R. Oksaputri, E. Ernawati, dan D. Andreswari, “Implementasi Content Based Image Retrieval (CBIR) Pada Citra Batik Besurek Yang Tidak Utuh Menggunakan Metode Speeded Up Robust Features (SURF) dan Fast Library Approximated Nearest Neighbor (FLANN),” Pseudocode, vol. 5, no. 2, hlm. 18–28, 2018.
[8] M. Feldi, S. Solahuddin, dan L. Yuswanita, “Implementasi Content Based Video Retrieval Menggunakan Speeded-up Robus Features (Surf),” SINTAKSIS: Jurnal Ilmiah Pendidikan, vol. 1, no. 1, hlm. 57–75, 2021.
[9] T. RD dan K. Alan, “Novi,‘Pengolahan Citra Digital Untuk Mendeteksi Warna Model Normalisasi Rgb,’ Semantik, vol. 17, no,” 2011.
[10] H. Bay, T. Tuytelaars, dan L. Van Gool, “Surf: Speeded up robust features,” dipresentasikan pada Computer Vision–ECCV 2006: 9th European Conference on Computer Vision, Graz, Austria, May 7-13, 2006. Proceedings, Part I 9, Springer, 2006, hlm. 404–417.
