Ariputra, Radithya Markarito (2025) KOMPARASI ALGORITMA K-MEANS DAN DBSCAN DALAM KLASTERISASI SUASANA HATI MUSIK R&B PADA PLATFORM SPOTIFY. Undergraduate thesis, UPN Veteran Jawa Timur.
![[img]](https://repository.upnjatim.ac.id/style/images/fileicons/text.png) |
Text
21082010237.-cover.pdf Download (4MB) |
|
Text
21082010237.-bab1.pdf Download (530kB) |
|
Text
21082010237.-bab2.pdf Restricted to Repository staff only until 15 September 2027. Download (364kB) |
|
Text
21082010237.-bab3.pdf Restricted to Repository staff only until 15 September 2027. Download (326kB) |
|
Text
21082010237.-bab4.pdf Restricted to Repository staff only until 15 September 2027. Download (2MB) |
|
Text
21082010237.-bab5.pdf Download (155kB) |
|
Text
21082010237.-daftarpustaka.pdf Download (129kB) |
|
Text
21082010237.-lampiran.pdf Restricted to Repository staff only until 15 September 2027. Download (1MB) |
Abstract
The R&B genre is known for its rich emotional nuances and has shown significant growth in various parts of the world. Grouping songs based on mood is important because music has a unique ability to influence the emotions and mental well-being of its listeners. This study aims to compare the performance of two clustering algorithms, K-Means and DBSCAN, in grouping R&B songs on the Spotify platform based on mood. The grouping is done using the Thayer Model as a reference, which divides mood into four categories: tense, sad, calm, and happy, based on two main dimensions: energy level and stress level. These two dimensions are represented through two main attributes from the Spotify API, namely Valence and Energy, which respectively describe the level of happiness and intensity of a song. Modeling was performed using the CRISP-DM approach, which consists of the stages of data understanding, data preparation, modeling, evaluation, and deployment into a web based application. Model evaluation used two metrics, namely the Silhouette Coefficient and Davies-Bouldin Index (DBI). The evaluation results showed that the K-Means algorithm produced clusters of higher quality compared to DBSCAN, with a Silhouette Score of 0.3895 and a DBI of 0.8398. The web application allows users to receive song recommendations based on their mood and save them directly to their Spotify accounts.
| Item Type: | Thesis (Undergraduate) | ||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Contributors: |
|
||||||||||||
| Subjects: | T Technology > T Technology (General) | ||||||||||||
| Divisions: | Faculty of Computer Science > Departemen of Information Systems | ||||||||||||
| Depositing User: | Radithya Radithya Ariputra | ||||||||||||
| Date Deposited: | 15 Sep 2025 06:50 | ||||||||||||
| Last Modified: | 15 Sep 2025 06:50 | ||||||||||||
| URI: | https://repository.upnjatim.ac.id/id/eprint/43459 |
Actions (login required)
 |
View Item |