Publication Date
Spring 4-16-2025
Presentation Length
Poster/Gallery presentation
College
College of Sciences & Mathematics
Department
Math and Computer Science, Department of
Student Level
Undergraduate
SPARK Category
Research
Faculty Advisor
Christina Davis
SPARK Session
Data Science
Presentation Type
Poster
Summary
Music evokes a wide range of emotions, yet most music recommendation systems focus on sound and listening patterns rather than the meaning of lyrics. This project enhances lyric-based emotion recognition by applying Natural Language Processing (NLP) and Machine Learning (ML) to classify song lyrics into emotional categories.
I used eight datasets from Kaggle, including collections of lyrics, emotion labels, and audio features, providing a strong foundation for analysis. Our approach combines traditional NLP techniques (like TF-IDF and Word2Vec) with advanced deep learning models (such as BERT and XLNet) to classify lyrics into categories like happy, sad, angry, calm, romantic, and energetic. I also experiment with integrating audio features to improve accuracy.
Model performance is measured using precision, recall, F1-score, and accuracy, with results visualized through an interactive dashboard. By bridging lyric sentiment analysis with multimodal learning, this project aims to improve music recommendations, mental health applications, and the study of music and emotions.
Recommended Citation
Syed, Mahad, "Analyzing Musical Emotions: A Multi-Dataset Approach to Sentiment and Mood Classification in Songs" (2025). SPARK Symposium Presentations. 87.
https://repository.belmont.edu/spark_presentations/87
