Autores
Gelbukh Alexander
Título From Words to Paragraphs: Modeling Sentiment Dynamics in Notes from Underground with GPT-4 by Differential Equations Via Quantile Regression Analysis
Tipo Revista
Sub-tipo CONACYT
Descripción Computación y Sistemas
Resumen This study examines how the sentiment values in the first part of the book entitled as “Underground” of Fyodor Dostoevsky’s”Notes from Underground” change from words to sentences to paragraphs. Using the GPT-4 language model, we conducted a descriptive analysis of standardized sentiment values and calculated cumulative binned values of the sentiment trajectories over the text. We then created differential equation models to model the sentiment tones using quantile regression analysis. We show that binned values can reveal a more dynamic and potentially chaotic structure when applied to the cumulative sum of sentiments for word, sentence, and paragraph levels. We model differential equations derived for word, sentence, and paragraph levels via quantile regression. They demonstrate how the rate and acceleration of sentiment change are influenced by their current state and rate of change. In conclusion, this study’s findings are important for enhancing the capabilities of AI-driven chatbots in sentiment analysis, particularly in dissecting and understanding the layered emotional landscapes of literary works. © 2024 Instituto Politecnico Nacional. All rights reserved.
Observaciones DOI 10.13053/CyS-28-1-4905
Lugar Ciudad de México
País Mexico
No. de páginas 55-73
Vol. / Cap. v. 28 no. 1
Inicio 2024-01-01
Fin
ISBN/ISSN