A Hybrid AI Methodology for Generating Ontologies of Research Topics from Scientific Paper Corpora

2025-08-06

AI Summary

Traditional scholarly topic ontologies (e.g., MeSH, CSO) rely on manual curation, suffering from high labor costs, temporal lag, and coarse granularity. To address these limitations, this paper proposes an automated methodology for constructing research topic ontologies. First, latent topics are extracted from large-scale scholarly corpora; second, semantic relations among topics are identified by jointly leveraging encoder-based language models (SciBERT) and co-occurrence statistics from the literature; finally, a structured ontology is generated with built-in support for dynamic expansion. The approach employs a multi-stage pipeline integrating semi-automated techniques. Evaluated on 21,649 human-annotated triples, it achieves an F1-score of 0.951—significantly outperforming baseline methods. It has been successfully applied to extend the CSO ontology in the cybersecurity domain, thereby enhancing the organization, accessibility, and AI-readiness of scientific knowledge.

Technology Category

• Knowledge Representation and Reasoning: Ontologies
• Data Mining & Knowledge Management: Semantic Web
• Application Domains: Humanities & Computational Social Science

Application Category

• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Web Mining and Content Analysis: Topic discovery and tracking
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

Abstract

Taxonomies and ontologies of research topics (e.g., MeSH, UMLS, CSO, NLM) play a central role in providing the primary framework through which intelligent systems can explore and interpret the literature. However, these resources have traditionally been manually curated, a process that is time-consuming, prone to obsolescence, and limited in granularity. This paper presents Sci-OG, a semi-auto-mated methodology for generating research topic ontologies, employing a multi-step approach: 1) Topic Discovery, extracting potential topics from research papers; 2) Relationship Classification, determining semantic relationships between topic pairs; and 3) Ontology Construction, refining and organizing topics into a structured ontology. The relationship classification component, which constitutes the core of the system, integrates an encoder-based language model with features describing topic occurrence in the scientific literature. We evaluate this approach against a range of alternative solutions using a dataset of 21,649 manually annotated semantic triples. Our method achieves the highest F1 score (0.951), surpassing various competing approaches, including a fine-tuned SciBERT model and several LLM baselines, such as the fine-tuned GPT4-mini. Our work is corroborated by a use case which illustrates the practical application of our system to extend the CSO ontology in the area of cybersecurity. The presented solution is designed to improve the accessibility, organization, and analysis of scientific knowledge, thereby supporting advancements in AI-enabled literature management and research exploration.

Problem

• Automating ontology generation for research topics
• Improving accuracy in topic relationship classification
• Enhancing scientific knowledge organization and accessibility

Innovation

• Hybrid AI for automated ontology generation
• Multi-step topic discovery and classification
• Encoder-based model with literature features