One of the building blocks of language technology is named entity recognition: identifying the proper nouns and names of real-world items. For people and locations, it’s pretty easy. For organizations and products it gets a bit more ambiguous, since organizations and products often take their names from everyday items (e.g., apple). But the hardest entities to identify are titles.
We report findings from an analysis of top US song titles from 1890-2012. "Love" isn't what it used to be.