From Once Upon a Time to Happily Ever After: Tracking Emotions in Novels and Fairy Tales

TL;DR

This paper demonstrates how sentiment analysis and visualization techniques can quantify and compare emotional content in large literary collections, revealing differences between fairy tales and novels.

Contribution

It introduces emotion word density as a new metric and applies it to large corpora, enhancing search and analysis of literary texts.

Findings

Fairy tales exhibit a wider range of emotion word densities than novels.

Emotion associations can be derived from co-occurring words in large corpora.

Visualization aids in understanding emotional trajectories in texts.

Abstract

Today we have access to unprecedented amounts of literary texts. However, search still relies heavily on key words. In this paper, we show how sentiment analysis can be used in tandem with effective visualizations to quantify and track emotions in both individual books and across very large collections. We introduce the concept of emotion word density, and using the Brothers Grimm fairy tales as example, we show how collections of text can be organized for better search. Using the Google Books Corpus we show how to determine an entity's emotion associations from co-occurring words. Finally, we compare emotion words in fairy tales and novels, to show that fairy tales have a much wider range of emotion word densities than novels.