LIT-GRAPH: Evaluating Deep vs. Shallow Graph Embeddings for High-Quality Text Recommendation in Domain-Specific Knowledge Graphs

2026-02-07

AI Summary

This study addresses the limitations of conventional English literary recommendation practices in high school instruction—namely, their static content, lack of diversity, and misalignment with pedagogical objectives—by proposing a knowledge graph–based recommendation system grounded in an English literature ontology. For the first time in educational text recommendation, relation-aware deep graph learning is introduced. Through comparative experiments involving shallow graph embedding methods such as DeepWalk, Biased Random Walk, and Hybrid approaches against the Relational Graph Convolutional Network (R-GCN), the study demonstrates that R-GCN significantly outperforms these baselines in both semantic ranking quality and instructional relevance, owing to its relation-specific message-passing mechanism. Results indicate that the proposed approach effectively delivers high-quality, diverse, and pedagogically aligned literary recommendations.

Technology Category

• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Machine Learning: Graph-based Machine Learning
• Natural Language Processing: Sentence-level Semantics, Textual Inference, etc.

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

This study presents LIT-GRAPH (Literature Graph for Recommendation and Pedagogical Heuristics), a novel knowledge graph-based recommendation system designed to scaffold high school English teachers in selecting diverse, pedagogically aligned instructional literature. The system is built upon an ontology for English literature, addressing the challenge of curriculum stagnation, where we compare four graph embedding paradigms: DeepWalk, Biased Random Walk (BRW), Hybrid (concatenated DeepWalk and BRW vectors), and the deep model Relational Graph Convolutional Network (R-GCN). Results reveal a critical divergence: while shallow models excelled in structural link prediction, R-GCN dominated semantic ranking. By leveraging relation-specific message passing, the deep model prioritizes pedagogical relevance over raw connectivity, resulting in superior, high-quality, domain-specific recommendations.

Problem

• curriculum stagnation
• text recommendation
• pedagogical alignment
• knowledge graph
• literature selection

Innovation

• graph embedding
• knowledge graph
• R-GCN
• pedagogical recommendation
• relation-aware message passing