Year: 2026
Type: conference-paper
Abstract: ChronoLearn is a KG-LLM framework to structure and explore user-fed Arabic historical narratives.Traditional history learning methods often rely on fragmented, text-heavy resources that lack contextualisation, interactivity, and clear relational structure.Chronolearn transforms unstructured texts into knowledge graphs KG using an ETL-based Natural Language Processing (NLP) pipeline for entity and relation extraction, followed by schema-guided graph construction.The system integrates KG retrieval with Large Language Model (LLM) generation (GRAG) to produce grounded and explainable narratives.The approach is evaluated in heterogeneous Palestinian and Jordanian sources, including Nakba-related content, using both quantitative metrics and comparative analysis.Additionally, an interactive platform is provided to support the exploration of structured historical knowledge through graph visualisations and narrative storylines, enabling users to explore historical events in a coherent, interactive and interpretable manner.The results demonstrate improved factual grounding and structured reasoning, addressing limitations of text-only approaches in the processing of historical knowledge in Arabic Language
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W7166536212