Storytelling with Adjustable Narrator Styles and Sentiments

  • Boyang Li
  • Mohini Thakkar
  • Yijie Wang
  • Mark O. Riedl
Conference paper

DOI: 10.1007/978-3-319-12337-0_1

Part of the Lecture Notes in Computer Science book series (LNCS, volume 8832)
Cite this paper as:
Li B., Thakkar M., Wang Y., Riedl M.O. (2014) Storytelling with Adjustable Narrator Styles and Sentiments. In: Mitchell A., Fernández-Vara C., Thue D. (eds) Interactive Storytelling. ICIDS 2014. Lecture Notes in Computer Science, vol 8832. Springer, Cham

Abstract

Most storytelling systems to date rely on manually coded knowledge, the cost of which usually restricts such systems to operate within a few domains where knowledge has been engineered. Open Story Generation systems are capable of learning knowledge necessary for telling stories in a given domain. In this paper, we describe a technique that generates and communicates stories in language with diverse styles and sentiments based on automatically learned narrative knowledge. Diversity in storytelling style may facilitate different communicative goals and focalization in narratives. Our approach learns from large-scale data sets such as the Google N-Gram Corpus and Project Gutenberg books in addition to crowdsourced stories to instill storytelling agents with linguistic and social behavioral knowledge. A user study shows our algorithm strongly agrees with human judgment on the interestingness, conciseness, and sentiments of the generated stories and outperforms existing algorithms.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Boyang Li
    • 1
  • Mohini Thakkar
    • 1
  • Yijie Wang
    • 1
  • Mark O. Riedl
    • 1
  1. 1.School of Interactive ComputingGeorgia Institute of TechnologyAtlantaUSA

Personalised recommendations