Dr Francesco Osborne
Senior Research Fellow
Biography
Professional biography
I am a Senior Research Fellow at the Knowledge Media Institute of The Open University (UK), where I lead the Scholarly Knowledge Mining (SKM) team. In the last few years, I have ranked among the top 0.3% most cited researchers in the United Kingdom in the field of Computer Science (source: SciVal 2022–2026).
The SKM team is internationally recognised as a leading research group in applying AI to analyse and support scientific research. In recent years, its focus has expanded to the intersection of generative AI and knowledge graph technologies, exploring applications across diverse domains such as scientific research, media analysis, big data, financial market analysis, education, astronomy, and tourism. We collaborate with a number of commercial organisations (e.g., Springer Nature, Elsevier, Microsoft, Digital Science), non-profit organisations, and universities.
Research interests
My primary research interests cover Artificial Intelligence, Information Extraction, Knowledge Graphs, Science of Science, Semantic Web, Research Analytics, and Semantic Publishing. I have authored over 170 peer-reviewed publications in top-tier journals and conferences within AI and semantic technologies, including Artificial Intelligence Review, Neurocomputing, Journal of Big Data, Future Generation Computer Systems, Knowledge-Based Systems, Engineering Applications of Artificial Intelligence, Technological Forecasting and Social Change, the Semantic Web Journal, ISWC, ESWC, and WebConf.
I have been recognised with several awards, including the Best Paper Award at the International Conference on Knowledge Engineering and Knowledge Management 2024, the Best In-Use Paper Award at the International Semantic Web Conference 2022, the Best Demo Award at the International Semantic Web Conference 2020, and the Semantic Publishing Award at the European Semantic Web Conference 2014.
I regularly organise scientific conferences and special issues. Most recently, I served as Program Chair for SEMANTICS 2026, Proceedings Chair of ESWC 2026, chaired the Industry Track at ISWC 2024, and acted as a guest editor for a special issue of the Semantic Web Journal. Additionally, I am a member of the Editorial Board of the Journal of Web Semantics and the Data Intelligence Journal. Over the years, I have organised more than 20 workshops at international conferences.
Impact and engagement
In 2025, I will serve as the Co-Investigator of the first UK project dedicated to exploring the use of large language models to support grant peer review. Additionally, I lead a project funded by Springer Nature focused on designing and developing AI services to assist editorial workflows, predict research dynamics, and inform editorial decisions. Furthermore, I collaborate with the Astronomy Department on developing advanced AI techniques to monitor and mitigate radiation damage in space telescopes as part of the Euclid Mission—a flagship project dedicated to exploring the dark universe.
Previously, I led the development of several innovative AI technologies and resources to support scientific research, metascience analysis, and academic publishing. I created the Computer Science Ontology (CSO, http://cso.kmi.open.ac.uk), a taxonomy of research topics which is an order of magnitude bigger than the most widely used alternative, the ACM Computing Classification, and has been adopted by Springer Nature and several other organisations for annotating scientific documents and educational material. Building on this work, I designed the Smart Topic Miner, a tool for automatically annotating scientific publications that has been in routine use at Springer Nature since 2016. This solution brought a 75% cost reduction and dramatically improved the quality of the annotations, resulting in 12M additional downloads from the SpringerLink portal. In 2020, my team produced the Academia/Industry DynAmics (AIDA) Knowledge Graph (http://w3id.org/aida), a knowledge graph that maps 25M publications and 8M patents to the relevant research topics and industrial sectors. In 2022, we released the Computer Science Knowledge Graph (http://w3id.org/cskg), a knowledge base that describes 25M methods, tasks, materials, and metrics automatically extracted from computer science articles.
In 2023, I published a highly influential survey paper on knowledge graphs, which has become one of the most cited works in this domain. In 2024, I launched several initiatives in the field of AI systems for automated literature reviews, producing in-depth analyses and providing key recommendations for future research.
External collaborations
I collaborate with a number of commercial organisations (e.g., Springer Nature, Elsevier, Microsoft, Digital Science, Figshare), non-profit organisations (e.g., OECD, CSET, FBK), and universities (e.g., Oxford, Cagliari, Trento, Karlsruhe Institute of Technology, Paris, Bologna, Vienna, and others). I am Visiting Professor at the Sorbonne Paris Nord University.
Projects
Deployment Of Rexplore-derived Solutions In The Springer Environment To Support The Editorial Activities Of Springer Editors - Extension 5
Deployment Of Rexplore-derived Solutions In The Springer Environment To Support The Editorial Activities Of Springer Editors - Extension 5
LLMs Supporting Grant Peer Review
Researchers needing funding to conduct studies typically submit a proposal to a UK government research council that explains their goal and methods as well as justifying their costs. These are then evaluated by three or more academic experts and given a score that feeds into a decision about whether to fund them. The reviewing process is very time consuming and slow, consuming a lot of expert time and delaying the start of the funded projects. We propose to use private versions of Large Language Models (LLMs) to support this process, potentially reducing the burden of peer review. Whilst Artificial Intelligence (AI) methods have been tried in the context of grant peer review before, none have been to the best of our knowledge successfully deployed in the UK in production. LLMs seem to be well suited to this task because they have a good capability to detect the quality of other genres of academic writing, including journal articles and conference papers. Small LLMs are already used to reduce the peer review burden by one research funder. This project aims to (a) test the accuracy of LLMs at grant reviewing on a large scale, (b) assess how they could be used in practice to support the process, and (c) provide a user-friendly interface to support decision makers using them and exploring potential uses. At the end of the project, the main UK research funder, UKRI, will have an evidence base to decide whether and how to use LLMs to reduce the peer review burden as well as a software environment to do so. The entire UK research system could potentially benefit from faster, more equitable peer review in addition to the reduced peer review burden.
Publications
Book
Special Issue: Scholarly Data Analysis (Semantics, Analytics, Visualisation) (2019)
DL4KG2019 - Workshop on Deep Learning for Knowledge Graphs (2019)
Book Chapter
Detection, Analysis, and Prediction of Research Topics with Scientific Knowledge Graphs (2021)
Ontology Extraction and Usage in the Scholarly Knowledge Domain (2020)
Journal Article
Does Diversity of Expertise Drive Citation Impact? Evidence from Computer Science (2026)
Knowledge graph validation by integrating LLMs and human-in-the-loop (2025)
A Survey on Knowledge Organization Systems of Research Fields: Resources and Challenges (2025)
Modelling big data platforms as knowledge graphs: the data platform shaper (2025)
Research hypothesis generation over scientific knowledge graphs (2025)
CS-KG 2.0: A Large-scale Knowledge Graph of Computer Science (2025)
The Epistemology of Fine-Grained News Classification (2025)
Triplétoile: Extraction of knowledge from microblogging text (2024)
Artificial intelligence for literature reviews: opportunities and challenges (2024)
Citation prediction by leveraging transformers and natural language processing heuristics (2023)
Data-Driven Methodology for Knowledge Graph Generation Within the Tourism Domain (2023)
Integrating Conversational Agents and Knowledge Graphs Within the Scholarly Domain (2023)
Knowledge Graphs: Opportunities and Challenges (2023)
AIDA: a Knowledge Graph about Research Dynamics in Academia and Industry (2022)
Editorial of the Special Issue on Deep Learning and Knowledge Graphs (2022)
The AIDA Dashboard: a Web Application for Assessing and Comparing Scientific Conferences (2022)
R-classify: Extracting research papers’ relevant concepts from a controlled vocabulary (2022)
Completing Scientific Facts in Knowledge Graphs of Research Concepts (2022)
Trans4E: Link Prediction on Scholarly Knowledge Graphs (2021)
New Trends in Scientific Knowledge Graphs and Research Impact Assessment (2021)
A decade of Semantic Web research through the lenses of a mixed methods approach (2020)
Editorial: Special Issue on Scholarly Data Analysis (Semantics, Analytics, Visualisation) (2019)
The Evolution of IJHCS and CHI: A Quantitative Analysis (2019)
Geographical trends in academic conferences: An analysis of authors’ affiliations (2019)
Reducing the effort for systematic reviews in software engineering (2019)
Research Articles in Simplified HTML: a Web-first format for HTML-based scholarly articles (2017)
How are topics born? Understanding the research dynamics preceding the emergence of new areas (2017)
User data discovery and aggregation: the CS-UDD algorithm (2014)
Anisotropic propagation of user interests in ontology-based user models (2013)
Presentation / Conference
Assessing Large Language Models for SPARQL Query Generation in Scientific Question Answering (2025)
Capturing the Viewpoint Dynamics in the News Domain (2024)
Enhancing Scientific Knowledge Graph Generation Pipelines with LLMs and Human-in-the-Loop (2024)
Classifying Scientific Topic Relationships with SciBERT (2024)
Workshop on Deep Learning and Large Language Models for Knowledge Graphs (DL4KG) (2024)
Leveraging Language Models for Generating Ontologies of Research Topics (2024)
Automating Citation Placement with Natural Language Processing and Transformers (2024)
Knowledge Graphs for Digital Transformation Monitoring in Social Media (2024)
Ethics and Executability: Tracing Decency in Decentralised Knowledge Graph Applications (2023)
An Architecture for a Decentralised Learning Analytics Platform (Positioning Paper) (2023)
Ontology-Based Generation of Data Platform Assets (2023)
CS-KG: A Large-Scale Knowledge Graph of Research Entities and Claims in Computer Science (2022)
Leveraging Knowledge Graph Technologies to Assess Journals and Conferences at Springer Nature (2022)
Session details: Theme: Artificial intelligence and agents: KG - knowledge graphs track (2022)
Enriching Data Lakes with Knowledge Graphs (2022)
Assessing Scientific Conferences through Knowledge Graphs (2021)
AIDA-Bot: A Conversational Agent to ExploreScholarly Knowledge Graphs (2021)
AI-KG: an Automatically Generated Knowledge Graph of Artificial Intelligence (2020)
The AIDA Dashboard: Analysing Conferences with Semantic Technologies (2020)
Integrating Knowledge Graphs for Analysing Academia and Industry Dynamics (2020)
Improving Editorial Workflow and Metadata Quality at Springer Nature (2019)
Smart Topics Miner 2: Improving Proceedings Retrievability at Springer Nature (2019)
Integrating Knowledge Graphs for Comparing the Scientific Output of Academia and Industry (2019)
Mining Scholarly Data for Fine-Grained Knowledge Graph Construction (2019)
Mining Scholarly Publications for Scientific Knowledge Graph Construction (2019)
Geographical trends in research: a preliminary analysis on authors' affiliations (2018)
Ontology-Based Recommendation of Editorial Products (2018)
Classifying Research Papers with the Computer Science Ontology (2018)
The Computer Science Ontology: A Large-Scale Taxonomy of Research Areas (2018)
Sustainability in Software Engineering (2018)
AUGUR: Forecasting the Emergence of New Research Topics (2018)
Pragmatic Ontology Evolution: Reconciling User Requirements and Application Performance (2018)
Forecasting the Spreading of Technologies in Research Communities (2017)
2100 AI: Reflections on the mechanisation of scientific discovery (2017)
Smart Book Recommender: A Semantic Recommendation Engine for Editorial Products (2017)
Forecasting Technology Migrations by means of the Technology-Topic Framework (2017)
Supporting Springer Nature Editors by means of Semantic Technologies (2017)
It ROCS! The RASH Online Conversion Service (2016)
Combining NLP and Semantics for Mining Software Technologies from Research Publications (2016)
TechMiner: Extracting Technologies from Academic Publications (2016)
Smart Topic Miner: Supporting Springer Nature Editors with Semantic Web Technologies (2016)
Automatic Classification of Springer Nature Proceedings with Smart Topic Miner (2016)
Klink-2: integrating multiple web sources to generate semantic topic networks (2015)
The RASH Framework: enabling HTML+RDF submissions in scholarly venues (2015)
Inferring semantic relations by user feedback (2014)
A hybrid semantic approach to building dynamic maps of research communities (2014)
Clustering citation distributions for semantic categorization and citation prediction (2014)
Rexplore: unveiling the dynamics of scholarly data (2014)
TellEat: sharing experiences on the move (2014)
Understanding research dynamics (2014)
Exploring scholarly data with Rexplore. (2013)
Granular semantic user similarity in the presence of sparse data (2013)
Making sense of research with Rexplore (2012)
Mining semantic relations between research areas (2012)
Property-based interest propagation in ontology-based user model (2012)
A new approach to social behavior simulation: the mask model (2011)
Propagating user interests in ontology-based user model (2011)
Presentation / Conference Contribution
CiteGen: A Web Application for Citation Recommendation Powered by LLMs and Knowledge Graphs (2025)
Optimizing Large Language Models for ESG Activity Detection in Financial Texts (2025)
Extracting licence information from web resources with a Large Language Model (2024)
Musical Meetups: a Knowledge Graph approach for Historical Social Network Analysis (2023)
ResearchFlow: Understanding the Knowledge Flow between Academia and Industry (2020)
The CSO Classifier: Ontology-Driven Detection of Research Topics in Scholarly Articles (2019)