ANANDA, DEA (2025) PENERAPAN ALGORITMA CONTENT BASED FILTERING DAN KNEAREST NEIGHBORS UNTUK SISTEM REKOMENDASI KONTEN TIKTOK FAKULTAS ILMU KOMPUTER UNIVERSITAS MERCU BUANA. S1 thesis, Universitas Mercu Buana Jakarta.
|
Text (HAL COVER)
01 COVER.pdf Download (1MB) | Preview |
|
![[img]](https://repository.mercubuana.ac.id/style/images/fileicons/text.png) |
Text (BAB I)
02 BAB 1.pdf Restricted to Registered users only Download (73kB) |
|
|
Text (BAB II)
03 BAB 2.pdf Restricted to Registered users only Download (187kB) |
|
|
Text (BAB III)
04 BAB 3.pdf Restricted to Registered users only Download (153kB) |
|
|
Text (BAB IV)
05 BAB 4.pdf Restricted to Registered users only Download (702kB) |
|
|
Text (BAB V)
06 BAB 5.pdf Restricted to Registered users only Download (30kB) |
|
|
Text (DAFTAR PUSTAKA)
07 DAFTAR PUSTAKA.pdf Restricted to Registered users only Download (127kB) |
|
|
Text (LAMPIRAN)
08 LAMPIRAN.pdf Restricted to Registered users only Download (815kB) |
Abstract
The use of social media, especially TikTok, continues to increase in Indonesia, with high popularity among the younger generation. The Faculty of Computer Science, Mercu Buana University utilizes this platform as an effort to increase engagement through educational and promotional content. However, in intense competition, an effective strategy is needed to ensure content can reach a wider audience. This research aims to develop a TikTok content recommendation system that can increase engagement by utilizing the Content-Based Filtering and K-Nearest Neighbors (KNN) algorithms. The Content-Based Filtering algorithm is used to analyze content characteristics, such as keywords, categories and video duration, to provide recommendations for similar content based on user preferences. Meanwhile, the KNearest Neighbors (KNN) algorithm is applied to identify content similarities based on distance or similarity of features to other popular content. It is hoped that the results of this research will provide more accurate content recommendations, thereby increasing the chances of the Faculty of Computer Science's content being recommended by the TikTok algorithm. With this recommendation system, the Faculty of Computer Science, Mercu Buana University can achieve better engagement on the TikTok platform. Keywords: TikTok, Recommendation System, Content-Based Filtering, K-Nearest Neighbors, Engagement, Preprocessing Penggunaan media sosial, terutama TikTok, terus meningkat di Indonesia, dengan popularitas yang tinggi di kalangan generasi muda. Fakultas Ilmu Komputer Universitas Mercu Buana memanfaatkan platform ini sebagai upaya untuk meningkatkan engagement melalui konten edukatif dan promosi. Namun, dalam persaingan yang ketat, diperlukan strategi yang efektif untuk memastikan konten dapat menjangkau audiens yang lebih luas. Penelitian ini bertujuan untuk mengembangkan sistem rekomendasi konten TikTok yang dapat meningkatkan engagement dengan memanfaatkan algoritma Content-Based Filtering dan K-Nearest Neighbors (KNN).Algoritma Content-Based Filtering digunakan untuk menganalisis karakteristik konten, seperti kata kunci, kategori, dan durasi video, guna memberikan rekomendasi konten serupa berdasarkan preferensi pengguna. Sedangkan algoritma K-Nearest Neighbors (KNN) diterapkan untuk mengidentifikasi kemiripan konten berdasarkan jarak atau kesamaan fitur dengan konten populer lainnya. Hasil penelitian ini diharapkan dapat memberikan rekomendasi konten yang lebih akurat, sehingga meningkatkan peluang konten Fakultas Ilmu Komputer untuk direkomendasikan oleh algoritma TikTok. Dengan sistem rekomendasi ini, Fakultas Ilmu Komputer Universitas Mercu Buana dapat mencapai engagement yang lebih baik di platform TikTok. Kata kunci: TikTok, Sistem Rekomendasi, Content-Based Filtering, K-Nearest Neighbors, Engagement, Preprocessing
Actions (login required)
 |
View Item |
