Storytelling

The book

• The Shapes of Stories: Sentiment Analysis for Narrative (Cambridge Elements in Digital Literary Studies, Cambridge University Press, 2022, ISBN 978-1-009-27039-7). Develops ensemble methods for diachronic sentiment analysis applied to narrative texts; SentimentArcs is one implementation of the methodology. The book introduces a vocabulary for narrative shape that includes storyteller curves, curves-on-a-hill, curves-in-a-hole, tragic curves, person-on-the-plain, and distributed hero(ine), and proposes middle reading as a methodological middle path between distant and close reading. Cross-listed with Emotion and Language.

The methodology is now infrastructure across cognitive science, NLP, AI visualization, digital humanities, and the Cambridge Elements series. Engaged in Hamilton, Wilkens & Piper's NarraBench at EACL 2026, Yeh et al.'s Story Ribbons at IEEE TVCG 2026, Scientific Reports (He, Breithaupt, Kübler & Hills 2023, 25,728 retellings), Digital Scholarship in the Humanities (Lee on Shakespeare sonnets, 2025), Digital Humanities Quarterly (Rebora field survey, 2023), and across the Cambridge Elements series.

Subsequent work on narrative

• “Can Sentiment Analysis Reveal Structure in a ‘Plotless' Novel?” (Elkins and Chun, arXiv 1910.01441, 2019) — original venue for the distributed hero(ine) concept.
• “Beyond Plot” (Elkins, Journal of Cultural Analytics, 2025) — middle reading applied to narrative beyond traditional plot analysis.
• “The Shapes of Cinderella” (Elkins, Humanities, 2025) — comparative narrative analysis across cultures.

The AI Fiction Paradox

• “AI Fiction Paradox” (Elkins, arXiv 2603.13545, 2026) — names what AI-generated narrative can and cannot do, identifying systematic failures in narrative causation, informational revaluation, and multi-scale emotional architecture. Cross-listed with Creativity.