Publications

TaleStream: Supporting Story Ideation with Trope Knowledge

UIST 2023

Publication date: November 1, 2023

Jean-Peïc Chou, Maneesh Agrawala, Alexa F Siu, Nedim Lipka, Ryan A. Rossi, Franck Dernoncourt

Story ideation is a critical and creative part of the story-writing process. It is challenging to support it computationally due to its exploratory and subjective nature. Tropes, which are narrative elements recurring across stories, are essential in stories as they shape the structure of narratives and our understanding of them. In this paper, we propose to use tropes as an intermediate representation of stories to approach story ideation. We present TaleStream, a mood board system that uses tropes as building blocks of stories and provides steerable suggestions of story ideas in the form of tropes. By leveraging data from the tvtropes.com wiki, our algorithms provide suggestions that would, on average, be more used than a baseline generating random tropes, as reported by participants 97% of the time. Our system evaluation suggests that TaleStream can support writers’ current workflows and greatly facilitates developing stories. Tropes, as a rich lexicon of narratives with available examples, play a key role in TaleStream and hold promise for story ideation support tools.