The Comparison of the Most Listened-to songs of 2000-2020 from within Network Science Perspective and the investigation and explanation of their effects on Human Psychology

This thesis examines music from an engineering perspective, specifically through the analyzability of lyrics. It explores how machine learning and natural language processing techniques can be integrated alongside traditional music analysis methods to understand the evolution and emotional expression of music. The thesis aims to understand music from both an artistic and technical perspective by examining the history of music analysis, how it has changed with advancing technology, and what methods are used today. In particular, it examines the role of lyrics in musical structure and how these lyrics can be analyzed by forming a network. This network analysis allows us to gain a deeper understanding of the emotional expression and intrinsic connections of music. By evaluating the impact of machine learning and natural language processing techniques on music analysis, it explores the role of these technologies in enriching the meaning of music. Finally, this thesis examines the advantages and limitations of music analysis software. It sheds light on the future development of music analysis software, focusing on programs that are better able to analyze certain genres of music, as well as the inability to fully understand emotional expressions. It also offers a perspective on understanding the evolution of music and changes in listener preferences, using machine learning and natural language processing techniques to assess trends in the music world.