Sentiment Dynamics of Success: Fractal Scaling of Story Arcs Predicts Reader Preferences
This addresses the problem of predicting reader preferences for literary works, but it is incremental as it applies an existing method (Hurst exponent) to a new domain (fairy tales).
The study investigated how the fractal scaling of sentiment arcs in H. C. Andersen's fairy tales correlates with reader preferences on GoodReads, finding that degrading Hurst exponents lead to lower quality scores and identifying a sweet spot between 0.55 and 0.65 for literary appreciation.
We explore the correlation between the sentiment arcs of H. C. Andersen's fairy tales and their popularity, measured as their average score on the platform GoodReads. Specifically, we do not conceive a story's overall sentimental trend as predictive \textit{per se}, but we focus on its coherence and predictability over time as represented by the arc's Hurst exponent. We find that degrading Hurst values tend to imply degrading quality scores, while a Hurst exponent between .55 and .65 might indicate a "sweet spot" for literary appreciation.