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

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.

[1]  Jerome Bellegarda,et al.  Emotion Analysis Using Latent Affective Folding and Embedding , 2010, HLT-NAACL 2010.

[2]  R. Plutchik.  A GENERAL PSYCHOEVOLUTIONARY THEORY OF EMOTION , 1980 .

[3]  Francisco J. Ruiz,et al.  The consumer’s reaction to delays in service , 2002 .

[4]  D. Bellos.  Review. Persuasion in the French Personal Novel: Studies of Chateaubriand, Constant,Balzac, Nerval and Fromentin. Bales, Richard , 1999 .

[5]  Marshall S. Smith,et al.  The general inquirer: A computer approach to content analysis. , 1967 .

[6]  Patrick Mannix.  The Rhetoric of Antinuclear Fiction: Persuasive Strategies in Novels and Films , 1992 .

[7]  David Martins de Matos,et al.  Fairy Tale Corpus Organization Using Latent Semantic Mapping and an Item-to-item Top-n Recommendation Algorithm , 2010, LREC.

[8]  Saif Mohammad,et al.  Even the Abstract have Color: Consensus in Word-Colour Associations , 2011, ACL.

[9]  Richard Bales,et al.  Persuasion in the French Personal Novel: Studies of Chateaubriand, Constant, Balzac, Nerval, and Fromentin , 1997 .

[10]  Erez Lieberman Aiden,et al.  Quantitative Analysis of Culture Using Millions of Digitized Books , 2010, Science.

[11]  Peter D. Turney,et al.  Emotions Evoked by Common Words and Phrases: Using Mechanical Turk to Create an Emotion Lexicon , 2010, HLT-NAACL 2010.

[12]  Philip J. Stone,et al.  Extracting Information. (Book Reviews: The General Inquirer. A Computer Approach to Content Analysis) , 1967 .

[13]  Carlo Strapparava,et al.  WordNet Affect: an Affective Extension of WordNet , 2004, LREC.

[14]  Laurette Dubé,et al.  The antecedents of brand switching, brand loyalty and verbal responses to service failure , 1996 .

[15]  Saif Mohammad,et al.  Tracking Sentiment in Mail: How Genders Differ on Emotional Axes , 2011, WASSA@ACL.

[16]  S. Jones,et al.  The fairy tale : the magic mirror of imagination , 1997 .

[17]  Saif Mohammad,et al.  Generating High-Coverage Semantic Orientation Lexicons From Overtly Marked Words and a Thesaurus , 2009, EMNLP.

[18]  Verena Kast.  Through Emotions to Maturity: Psychological Readings of Fairy Tales , 1993 .

[19]  Cecilia Ovesdotter Alm,et al.  Emotions from Text: Machine Learning for Text-based Emotion Prediction , 2005, HLT.

[20]  Cecilia Ovesdotter Alm,et al.  Emotional Sequencing and Development in Fairy Tales , 2005, ACII.

[21]  A. Lehrer.  Semantic fields and lexical structure , 1974 .

[22]  David Yarowsky,et al.  Word-Sense Disambiguation Using Statistical Models of Roget’s Categories Trained on Large Corpora , 2010, COLING.

[23]  Michael L. Littman,et al.  Measuring praise and criticism: Inference of semantic orientation from association , 2003, TOIS.

[24]  Catherine Orenstein,et al.  Little Red Riding Hood Uncloaked: Sex, Morality, and the Evolution of a Fairy Tale , 2002 .