Ade Kurnia Putra, . (2025) PENERAPAN ALGORITMA CONTENT BASED FILTERING UNTUK SISTEM REKOMENDASI FILM DAN LAYANAN STREAMING FILM. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.
![[img]](http://repository.upnvj.ac.id/style/images/fileicons/text.png) |
Text
ABSTRAK.pdf Download (12kB) |
|
Text
AWAL.pdf Download (365kB) |
|
Text
BAB 1.pdf Restricted to Repository UPNVJ Only Download (98kB) |
|
Text
BAB 2.pdf Restricted to Repository UPNVJ Only Download (287kB) |
|
Text
BAB 3.pdf Restricted to Repository UPNVJ Only Download (322kB) |
|
Text
BAB 4.pdf Restricted to Repository UPNVJ Only Download (1MB) |
|
Text
BAB 5.pdf Download (82kB) |
|
Text
DAFTAR PUSTAKA.pdf Download (154kB) |
|
Text
RIWAYAT HIDUP.pdf Restricted to Repository UPNVJ Only Download (128kB) |
|
Text
LAMPIRAN.pdf Restricted to Repository UPNVJ Only Download (990kB) |
|
Text
HASIL PLAGIARISME.pdf Restricted to Repository staff only Download (17MB) |
|
Text
ARTIKEL KI.pdf Restricted to Repository staff only Download (703kB) |
Abstract
The abundance of movies and streaming services often hinders user decision-making. This research aims to overcome these difficulties by designing a movie recommendation system and movie streaming services based on content-based filtering. Movie data is obtained by scraping from The Movie Database API with a total of 15,813 data. The data goes through preprocessing stages of case folding, cleaning, tokenizing, and stemming. Model is created using CountVectorizer technique to convert the film's textual content into vectors and Cosine Similarity to measure the similarity. The model is evaluated using MAP@K metrics which gets the largest score on MAP@1 with a score of 0,7577. The model is integrated on the website created using ReactJs framework as the frontend and Flask as the backend. The website functionality was tested with black box testing with successful results in all scenarios. Furthermore, user assessment was tested using user acceptance testing (UAT) with beta testing method which received a final score of 4.58 out of 5. These results prove that content-based filtering approach with CountVectorizer and Cosine Similarity is effective and suitable for building movie recommendation systems and movie streaming services that are personalized and satisfying for users.
| Item Type: | Thesis (Skripsi) |
|---|---|
| Additional Information: | [No.Panggil: 2110511053] [Dosen Pembimbing 1: Indra Permana Solihin] [Dosen Pembimbing 2: Kharisma Wiati Gusti] [Penguji 1: Nurhafifah Matondang] [Penguji 2: Nurul Afifah Arifuddin] |
| Uncontrolled Keywords: | Content based filtering, CountVectorizer, Cosine Similarity, Movie, Movie Streaming Services |
| Subjects: | Q Science > QA Mathematics > QA76 Computer software |
| Divisions: | Fakultas Ilmu Komputer > Program Studi Informatika (S1) |
| Depositing User: | ADE KURNIA PUTRA |
| Date Deposited: | 06 Aug 2025 07:03 |
| Last Modified: | 06 Aug 2025 07:03 |
| URI: | http://repository.upnvj.ac.id/id/eprint/37522 |
Actions (login required)
 |
View Item |