Intelligent information retrieval is a requirement with today’s massive data available online. Researchers and private-sector companies are investing time into developing methods to progress information retrieval in many areas; including music. Music Emotion Recognition allows content providers to automatically recognize the emotion in music audio tracks and use this knowledge to improve user experience. Extreme Gradient Boosting Classifier was used in this research to classify Arabic music tracks recommended by listeners, on Arousal and Valence labels both separately and jointly, based on five acoustic features. Four evaluation metrics were used to evaluate the model’s performance: Accuracy, Precision, Recall, and F1-Score. Results show that the model was able to predict Arousal labels better than it did with Valence ratings or Arousal/Valence labels jointly.
-
Notifications
You must be signed in to change notification settings - Fork 0
mhd-shadi/Arabic-Music-Emotion-Recognition
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Folders and files
Name | Name | Last commit message | Last commit date | |
---|---|---|---|---|
Repository files navigation
About
Music Emotion Recognition for Arabic Tracks Using Extreme Gradient Boosting
Topics
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published