Doctoral candidate Kahyun Choi successfully defended her dissertation, "Computational Lyricology: Quantitative Approaches to Understanding Song Lyrics and Their Interpretations."
Her committee included Professor J. Stephen Downie (chair); Professor Michael Twidale; Professor Ted Underwood; and Sally Jo Cunningham, associate professor of computer science at The University of Waikato.
From the abstract – This dissertation research investigates song lyric complexity and how it might be measured computationally. The research proposes two different lyric complexity scores: one based on song lyrics that aims to capture concreteness of song lyrics, one of quantitative dimensions of text complexity, and the other based on user-generated interpretations of song lyrics that aims to capture some qualitative dimensions of text complexity. This work revealed that (1) concreteness of popular song lyrics fell from the middle of the 1960s until the 1990s and rose after that-the advent of Hip-Hop/Rap and the number of words in song lyrics are highly correlated with the rise in concreteness after the early 1990s; (2) interpretations are a good input source for automatic topic detection algorithms because they are more useful than song lyrics as input for an automatic song lyrics topic classification task across various feature representations; and 3) the interpretation-based lyric complexity metric looks promising because (a) it may capture the inverted-U relationship between music complexity and preference, and (b) it may also capture the theory that lexically difficult song lyrics could lead to more diverse interpretations.