Knowledge Graph Integration for Enhancing Semantic Search and Intelligent Information Retrieval

Noëlle van Dijk

Knowledge Graph Integration for Enhancing Semantic Search and Intelligent Information Retrieval

Author(s)	Noëlle van Dijk
Country	Netherlands
Abstract	The increasing availability of digital information has created significant challenges for search systems required to interpret complex queries and retrieve contextually relevant documents. Conventional information retrieval techniques commonly depend on lexical similarity between user queries and indexed content. Although these methods provide efficient mechanisms for identifying documents containing relevant keywords, they may encounter limitations when search queries involve ambiguous terminology, alternative entity names, implicit relationships, or multiple connected concepts. Knowledge graphs offer a structured approach to representing entities, attributes, and semantic relationships, creating opportunities to improve information retrieval through explicit contextual knowledge. The present paper develops a hypothetical methodological framework for investigating knowledge graph integration in semantic search and intelligent information retrieval. Four retrieval configurations are considered: BM25 lexical retrieval, entity-aware query expansion, knowledge graph-based relationship expansion, and hybrid semantic retrieval with graph-informed reranking. The corresponding knowledge graph contains 2,400 entities and 7,200 relationship triples representing conceptual connections among creators, artworks, historical periods, artistic movements, and collection objects. The proposed methodology incorporates textual preprocessing, entity recognition, entity disambiguation, graph construction, ontology alignment, relationship-based query processing, and comparative retrieval evaluation. A hypothetical collection of 240 information-seeking queries is organized into exact-entity, alias-based, relationship-oriented, and multi-hop categories. Two illustrative analytical tables describe the evaluation dataset and comparative ranking performance. Normalized Discounted Cumulative Gain, Recall, and Mean Reciprocal Rank are considered principal evaluation measures. All numerical values are manually constructed and do not represent completed retrieval experiments. The methodological discussion examines semantic ambiguity, knowledge graph completeness, relationship accuracy, computational complexity, and evaluation reliability. Particular attention is given to distinguishing valid knowledge graph relationships from inferred or unsupported connections.
Keywords	Knowledge Graph, Semantic Search, Intelligent Information Retrieval, Entity Linking, Ontology, Linked Data, Graph-Based Query Expansion, Hybrid Retrieval, Semantic Relationships, Information Ranking.
Field	Engineering
Published In	Volume 2, Issue 4, July-August 2026
Published On	2026-07-30

View / Download PDF File

E-ISSN: 3067-5073

doi

CrossRef DOI is assigned to each research paper published in our journal.

IJMLAIDSE DOI prefix is
10.00000/IJMLAIDSE

Downloads

Research Paper Format Copyright Permission and Undertaking Form

All research papers published on this website are licensed under Creative Commons Attribution-ShareAlike 4.0 International License, and all rights belong to their respective authors/researchers.

CC-BY-SA

About IJMLAIDSE Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us	+1-872-302-3851	editor@uscse.com

International Journal of Machine Learning, AI & Data Science Evolution

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Monthly Scholarly International Journal

Knowledge Graph Integration for Enhancing Semantic Search and Intelligent Information Retrieval

Share this