An automated predictive model for evaluating narrative cohesion in children’s stories: a computational linguistic approach considering Gérard Genette’s narrative structure theory
Jawharah Alasmari, Mohammed Alzyoudi, Masheal Alshehri, Rana Alshammari, Reyouf Aldakan · International Journal of Adolescence and Youth · 2025
This study develops a machine learning model to predict narrative cohesion in children’s stories, classifying cohesion as complete, partial, or absent, using Gérard Genette’s narrative structure theory as a framework. It analyzes both human-created and AI-generated stories, including those from ChatGPT, by assessing linguistic, rhetorical, and stylistic elements such as narrative style, character development, time specification, event sequencing, and dialogue. The study employs a Decision Tree model to evaluate narrative cohesion, achieving optimal results with both recall and precision at 100%. These results demonstrate the model’s high accuracy in classifying narrative texts. By providing insights into narrative cohesion, the study enhances our understanding of children’s stories, offering a tool for better emotional comprehension and communication. Furthermore, it highlights the potential of AI and machine learning in analysing narrative structures. This research contributes to improving narrative text analysis and storytelling techniques, making it valuable for future applications in education, especially in enhancing the quality and coherence of children’s literature.