University of Cambridge > > PublicHealth@Cambridge > Text mining for public health reviews (The Robot Analyst)

Text mining for public health reviews (The Robot Analyst)

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Dr Tennie Videler.

The unstructured and ambiguous nature of language in public health literature is a barrier to the accessibility and discovery of information. I will discuss the limitations of conventional keyword-based search, which are not well suited for the development of sensitive search strategies. Semantic search functionalities (e.g., faceted search, automatic query expansion, queries as natural language questions) offered by semantic systems developed by the National Centre for Text Mining will be presented. Then methods which reduce the burden of semi-automatic citation screening will be presented within the context of a novel system, the RobotAnalyst, developed for Public Health England.

CV Sophia Ananiadou is Professor of Computer Science in the School of Computer Science, University of Manchester and director of the National Centre for Text Mining (NaCTeM). Her main areas of research are semantic text mining and semantic search techniques for applications in domains such as medicine, systems biology, public health, chemistry, biodiversity and history of medicine. She is also involved in developing large-scale terminological resources (BioLexicon) and interoperable text mining platforms (Argo). Her current and recent projects include semantic search for Europe PubMedCentral, supporting evidence-based systematic reviews in collaboration with NICE , supporting the development of biomarker tests in the Manchester Molecular Pathology Innovation Centre (MMPathIC), mining time sensitive information from historical medical documents and extracting complex claims for the development of networks, hypothesis generation and experimental testing in Cancer Biology (Big Mechanism).

This talk is part of the PublicHealth@Cambridge series.

This talk is part of the PublicHealth@Cambridge series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.


© 2006-2024, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity