Optimizing AI-Driven Digital Resources in Vocational English Learning Using Plithogenic n-SuperHyperGraph Structures for Adaptive Content Recommendation

Abstract

Digital vocational English learning systems face challenges in addressing diverse learner 
profiles, incomplete feedback, and dynamic content requirements. Traditional 
recommendation models often lack the flexibility to manage multi-dimensional attributes 
such as profession, language level, and media preferences under uncertain conditions. 
This paper proposes a novel adaptive recommendation framework based on Plithogenic 
n-SuperHyperGraph structures, which integrate AI and plithogenic logic to model 
complex learner-resource interactions. Each interaction is represented using neutrosophic 
logic values  truth, indeterminacy, and falsity  and is dynamically updated based on 
learner feedback. Through defined mathematical formulations and real-world numerical 
examples, the model demonstrates its capacity to deliver personalized, uncertainty-aware 
content. The approach offers a scalable, mathematically grounded solution for enhancing 
digital 
vocational 
recommendations. 

DOI: 10.5281/zenodo.15786262