eScholar project
Overview
Manchester eScholar is a search facility at the University of Manchester that gives researchers access to scholarly work produced by individuals associated with the university. NaCTeM, in collaboration with the University of Manchester Library (UML), will enrich the current faceted search capabilities of eScholar by customising, adapting and combining existing text mining tools and algorithms to foster the discovery of interdisciplinary links.
The advancement of new interdisciplinary research is reliant on identifying potential synergies between the work of different groups within the university. Often, researchers in different schools or departments may not be aware of potential overlaps between their respective research and therefore collaborative opportunities may be missed. One way of discovering potential research links is to examine the papers and articles produced by different groups in order to identify possible commonalities in previously reported research. This project aims to automate the process of discovering such links through the application of advanced text mining techniques.
Techniques
The project will involve:
- keyword extraction, similar to TerMine, to discover important terminology related to a query;
- named entity recognition to foster semantic search, e.g., looking for “chemical:lead” should return a narrower, more focused set of results than the more general and ambiguous query “lead”;
- topic clustering to discover diverse groups of semantically related documents across various domains and dimensions/facets.
The proposed text mining techniques have been previously proven in other services such as Europe PubMed Central, in which NaCTeM introduced semantic querying, and search systems developed by NaCTeM, including the clinical trials faceted search engine and a news-based search engine developed in the context of the ISHER project.
Project Team
Principal Investigator: Prof. Sophia Ananiadou
Featured News
- Shared Task on Financial Misinformation Detection at FinNLP-FNP-LLMFinLegal
- New Named Entity Corpus for Occupational Substance Exposure Assessment
- FinNLP-FNP-LLMFinLegal @ COLING-2025 - Call for papers
- Keynote talk at Manchester Law and Technology Conference
- Keynote talk at ACM Summer School on Data Science, Athens
- Congratulations to PhD student Panagiotis Georgiades
Other News & Events
- Invited talk at the 8th Annual Women in Data Science Event at the American University of Beirut
- Invited talk at the 2nd Symposium on NLP for Social Good (NSG), University of Liverpool
- Invited talk at Annual Meeting of the Danish Society of Occupational and Environmental Medicine
- Advances in Data Science and Artificial Intelligence Conference 2024
- New review article on emotion detection for misinformation