Nidhi Zare

Publication Date

Spring 2024

Degree Type

Master's Project

Degree Name

Master of Science in Computer Science (MSCS)


Computer Science

First Advisor

Ching-Seh Wu

Second Advisor

Mark Stamp

Third Advisor

Navrati Saxena


Apache Spark, big data, deep learning, machine learning, music genre classification, sentiment analysis


Music is one of the most common source of entertainment. Every user has their own taste of music and prefer to listen music that adheres to their taste and mood. There are various categories, called as music genres in which music can be classified. This research project addresses the challenge in music genre classification by using various deep learning models such as Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), Very Deep Convolutional Networks (VGGNet), ResNet and others. The primary objective of this research is to enhance the accuracy of music genre classification using a distributed computing framework Apache Spark. We explore and analyze different features from the audio files like Spectrograms and Mel-frequency cepstral coefficients (MFCCs). These diverse feature extraction helps to improve the performance of the deep learning models used for the genre classification. Additionally, we classify the sentiment of the music. The combination of genre classification and sentiment analysis would help improve and refine the music recommendation systems. One of the key aspect of this project is the use of Apache Spark for distributed processing of music data as well as leveraging it for model execution enabling the system to be more scalable for large number of audio files. Through this research, we seek to develop a deep understanding of the audio content through its genre and sentiment classification with an accuracy of approximately 90%. Ultimately, the outcomes of this study contribute to the advancement of music recommendation systems and the widens the field of music analysis.

Available for download on Friday, May 23, 2025