Letting Emotions Flow: Success Prediction by Modeling the Flow of Emotions in Books

TL;DR

This paper models the emotional flow in books using recurrent neural networks to predict their success, demonstrating that emotional dynamics are useful indicators of a book's popularity.

Contribution

It introduces a novel approach to quantify emotional flow in books and applies it to success prediction using neural networks, achieving notable performance.

Findings

Achieved a weighted F1-score of 69% in success prediction

Modeling emotional flow improves prediction accuracy

Multitask learning predicts success and genre simultaneously

Abstract

Books have the power to make us feel happiness, sadness, pain, surprise, or sorrow. An author's dexterity in the use of these emotions captivates readers and makes it difficult for them to put the book down. In this paper, we model the flow of emotions over a book using recurrent neural networks and quantify its usefulness in predicting success in books. We obtained the best weighted F1-score of 69% for predicting books' success in a multitask setting (simultaneously predicting success and genre of books).