Abstract
Popular music lyrics are brief in length yet sophisticated in narrative content, emotional expressiveness, and structural aesthetics. In this chapter, we propose a graph-based analysis and interpretation framework for popular music lyrics using semantic word embedding representation. This framework explores the temporal and structural information in music lyrics, such as word sequential pattern, lyric format pattern, and predominant song forms, to enhance the understanding of the semantic and structural properties of music lyrics. Our proposed analysis and interpretation framework provides extensive tools for representing various properties of music lyrics as graph structural elements, and then we implemented feature extraction tools for a comprehensive characterization of the lyric graph using graph analysis or complex network methodologies. Empirical studies based on contrasting music genres demonstrated the strong statistical significance of the proposed semantic and structural features and connect the statistical analysis results to musicological concepts and interpretations.