Ananiadou, Sophia
PROFILE

Sophia Ananiadou

Personal Information

Position: Adjunct Researcher
Email: Sophia.Ananiadou_AT_manchester.ac.uk

Over the past 10 years, I have been active in the field of text mining, with particular emphasis in biomedicine, where I enjoy an internationally leading status, placing me in the top 30 most cited scholars worldwide in text mining (h-index 52 with over 10,500 citations). My research is deeply interdisciplinary: I combine text mining with machine learning methods for biomedical applications. Since 2004, I have served as director, and was responsible for the creation of, the 1st publicly funded text-mining centre in the world, the National Centre for Text Mining (NaCTeM, www.nactem.ac.uk) (funding of €3,423,000). I have successfully directed NaCTeM to be a fully sustainable centre, carrying out novel, world-leading research on text mining that then informs its provision of tools, resources and text mining infrastructure, to a variety of users from systems biology but also translational medicine and public health. NaCTeM is deliberately located in the Manchester Institute of Biotechnology to facilitate collaboration between experts in machine reading, systems biology and bioengineering. I have advanced the state of the art in text mining and contributed in novel ways to a number of research areas: the automatic extraction of concepts and their normalization, the development of large scale terminologies for biomedicine using distributional semantics, string similarity measures, and alignment, e.g., BioLexicon; and development of scalable semantic search systems for indirect association mining FACTA+ and for massive analysis of full papers e.g. Europe PubMedCentral (3.4M papers) all supported by an interoperable text mining platform, Argo. Research novelties include the top performing event extraction system (EventMine), unsupervised methods for document clustering and classification, faceted search, extraction of discourse information from text for search and linking text with signaling pathways (PathText). Industry collaborations have included: extraction of angiogenesis bioprocesses (AstraZeneca); species disambiguation (Pfizer); curation of metabolic pathways (Unilever), tools for scholarly communications and publishing (Elsevier, Nature), risk assessment for health insurance (Pacific Life) and health and safety (Lloyds Foundation). Overall, I have attracted over €18M throughout my academic career, and supervised over 45 researchers and 18 PhD students. NaCTeM is an internationally leading research centre for text mining research due to my leadership.