The Use of Emotion Flows in the Analysis of Creative Writing

Previous work on the analysis of emotional arcs in books has shown that books that are considered to be more successful follow very specific emotional arcs. Following this line of thought we propose to use a more nuanced depiction of emotions than is traditionally used in our field. Instead of extracting some sort of summary, or average, of the sentiment in a given text, we generate a time line of emotions. In this talk, I will show two example applications where using this emotional landscape boosts prediction performance: predicting whether readers will like a book, and assigning tags to movies from plot synopsis.
Thamar Solorio is an Associate Professor in the Department of Computer Science at the University of Houston (UH). She is the founder and director of the Research in Text Understanding and Analysis of Language (RiTUAL) group at UH. Her main research interests include stylistic modeling of text, syntactic analysis of mixed language data, and computational models of creative writing for success prediction. She is the recipient of a CAREER award for her work in authorship analysis, and the 2014 Denice Denton Emerging Leaders ABIE Award. She serves as editorial board member for Computer Speech and Language Journal.