Center for Machine Learning and Intelligent Systems
About  Citation Policy  Donate a Data Set  Contact

Repository Web            Google
View ALL Data Sets

× Check out the beta version of the new UCI Machine Learning Repository we are currently testing! Contact us if you have any issues, questions, or concerns. Click here to try out the new site.

Turkish Music Emotion Dataset Data Set
Download: Data Folder, Data Set Description

Abstract: There are four different classes of music emotions in the dataset: happy, sad, angry, and relax.

Data Set Characteristics:  


Number of Instances:




Attribute Characteristics:

Integer, Real

Number of Attributes:


Date Donated


Associated Tasks:


Missing Values?


Number of Web Hits:



Mehmet Bilal Er, '@', Harran University

Data Set Information:

The dataset is designed as a discrete model, and there are four classes in the dataset: happy, sad, angry, relax. To prepare the dataset, verbal and non-verbal music are selected from different genres of Turkish music. A total of 100 music pieces are determined for each class in the database to have an equal number of samples in each class. There are 400 samples in the original dataset as 30 seconds from each sample.

Number of Data in Each class
Happy 100
Sad 100
Angry 100

Attribute Information:

Features such as Mel Frequency Cepstral Coefficients (MFCCs), Tempo, Chromagram, Spectral and Harmonic features have been extracted to analyze the emotional content in music signals. MIR toolbox is used for feature extraction.

Relevant Papers:


Citation Request:

If you use this dataset, please cite: Bilal Er, M., & Aydilek, I. B. (2019). Music emotion recognition by using chroma spectrogram and deep visual features. Journal of Computational Intelligent Systems, 12(2), 1622–1634. International Journal of Computational Intelligence Systems, , DOI: [Web Link] [Web Link]

Supported By:

 In Collaboration With:

About  ||  Citation Policy  ||  Donation Policy  ||  Contact  ||  CML