Love is a central theme in modern music, but do women andmen differ in their expressions of love? Results from empiri-cal studies on gender differences in love attitudes have evolvedfrom showing consistent differences to more similarities overtime and witnessed gender convergence in relationship expec-tations, housework responsibilities, and sexual attitudes. Inde-pendently, pop culture studies have shown how music can beused as a contextual artifact whose lyrics can reflect a culture’schanging psychological processes and ideologies. We combinethese two research areas to explore whether the gender con-vergence reported in psychological studies is mirrored in lovesongs. Using a corpus of lyrics and song metadata from 1960to 2009, we present a computational analysis of the lexical dis-tribution of lyrics across genre, gender and time. We show thatlove songs between vocalists who are men vs. women havebecome significantly more similar in their lyrical expressionsof love.

Word class conversion refers to the extended use of a wordfrom one grammatical class to another without overt morpho-logical marking. Noun-to-verb conversion, or denominaliza-tion, is one form of word class conversion studied extensivelyin the literature. Previous work has suggested that novel de-nominal verb usages are comprehensible if the listener cancompute the intended meaning based on shared knowledgewith the speaker. However, no existing work has explored thecomputational mechanism under this proposal. We proposea frame-semantic generative model, Noun2Verb, that supportsthe inference and generation of novel denominal verb usagesvia semi-supervised learning. We evaluate this framework ina dataset of denominal verbs drawn from adults and childrenagainst a state-of-the-art model from natural language process-ing. Our results show that Noun2Verb aligns better with humaninterpretation and bridges the gap between machines and hu-mans in lexical innovation.