IJCCS (Indonesian Journal of Computing and Cybernetics Systems) Vol.15, No.3, July 2021, pp. 265~274 ISSN (print): 1978-1520, ISSN (online): 2460-7258 DOI: https://doi.org/10.22146/ijccs.65623 ◼ 265 Received May 2 th ,2021; Revised July 31 th , 2021; July 31 th , 2021 Online Learning Video Recommendation System Based on Course and Sylabus Using Content-Based Filtering Faisal Ramadhan* 1 , Aina Musdholifah 2 1 Bachelor Program of Computer Science, FMIPA UGM, Yogyakarta, Indonesia 2 Department of Computer Science and Electronics, FMIPA UGM, Yogyakarta, Indonesia e-mail: * 1 faisalramadhan@mail.ugm.ac.id, 2 aina_m@ugm.ac.id Abstrak Pembelajaran menggunakan media video seperti menonton video di YouTube menjadi salah satu alternatif cara belajar yang sering digunakan. Akan tetapi, video pembelajaran tersedia begitu melimpah sehingga mencari video yang kontennya tepat menjadi sulit dan memakan waktu. Oleh karena itu, penelitian ini membangun sistem rekomendasi yang dapat merekomendasikan video berdasarkan mata kuliah dan silabus. Sistem rekomendasi bekerja dengan mencari kedekatan antara mata kuliah dan silabus dengan anotasi video menggunakan metode cosine similarity. Anotasi video tersebut merupakan judul dan deksripsi video yang diambil secara real-time dari YouTube menggunakan YouTube API. Sistem rekomendasi ini akan menghasilkan rekomendasi berupa lima buah video berdasarkan mata kuliah dan silabus yang dipilih. Hasil pengujian menunjukkan persentase kinerja rata-rata adalah 81.13% dalam pencapaian tujuan sistem rekomendasi yaitu relevance, novelty, serendipity dan increasing recommendation diversity. Kata kunci—sistem rekomendasi, video pembelajaran, content-based filtering, cosine similarity Abstract Learning using video media such as watching videos on YouTube is an alternative method of learning that is often used. However, there are so many learning videos available that finding videos with the right content is difficult and time-consuming. Therefore, this study builds a recommendation system that can recommend videos based on courses and syllabus. The recommendation system works by looking for similarity between courses and syllabus with video annotations using the cosine similarity method. The video annotation is the title and description of the video captured in real-time from YouTube using the YouTube API. This recommendation system will produce recommendations in the form of five videos based on the selected courses and syllabus. The test results show that the average performance percentage is 81.13% in achieving the recommendation system goals, namely relevance, novelty, serendipity and increasing recommendation diversity. Keywords—recommendation system, learning videos, content-based filtering, cosine similarity