Invited talks programme
All invited talks are from 16:15-17:15. They will consist of a 45 min talk with 15 min for discussion. The invited talks are free and open to all participants.
Monday 3 June
Speaker: Stephen Andrews
Title:Semantic enrichment in the Envia information discovery system
Abstract: The talk will discuss the JISC-funded EnviLOD project in the context of the British Library's environmental sciences programme. The aim of the project, a collaboration between The British Library, the University of Sheffield and HR Wallingford, is to demonstrate the value of using Linked Open Data (LOD) vocabularies in the field of environmental science. This has been achieved using GATE tools to semantically enrich environmental science documents and metadata and by developing an intuitive user interface that allows environmental researchers to search without the complexity of the SPARQL semantic search language. The outcomes of the EnviLOD project and the potential application of semantic technologies to the Library's new information discovery tool for environmental science, Envia, will be presented.
About the speaker: Stephen Andrews leads on the development of products and services within the Science Technology Medicine team at the British Library. He is the project manager of the Envia environmental sciences initiative and was actively involved in the scoping work that led to the EnviLOD project. Within the science portfolio, Stephen has been involved in a number of collaborations with external organisations that include the implementation of UK (now Europe) PubMed Central, the Names project (with the University of Manchester) and a joint project with Microsoft Research prototyping a Virtual Research Environment within the researcher's desktop.
Tuesday 4 June
Speaker: Richard Jackson
Title: Text mining Electronic Health Records for Research - Common Issues and Strategies
Abstract: The Case Register Interactive Search project (CRIS) is one of the largest datasets of its kind, providing mental health researchers with full access to anonymous electronic health records (EHRs) from the South London and Maudsley NHS trust. While a vast quantity of clinical data is held in structured fields, an estimated additional 60% of the data is stored in free text clinical notes, generated by healthcare professionals in their day to day activities. Over the last four years, the Biomedical Research Centre at the Maudsley Hospital has collaborated with the GATE team to develop text mining algorithms to unlock this for use in epidemiology. This talk will focus on the specific opportunities and challenges presented by the text mining of electronic health records, and the strategies that have been developed for dealing with them.
About the speaker: Richard Jackson is a bioinformatician by training, and has previously worked in the pharmaceutical industry where he specialised in text mining literature on toxicology. He has been working for the biomedical research centre at the Maudsley hospital since October 2012.
Wednesday 5 June
Speaker: Steven Brewer
Title: Text Mining - Commercial Application and Opportunities
Abstract: What is it about the present day that makes the commercial opportunities for text mining so attractive at a time when organisations are tightening the belt, cutting expenditure and generally derisking their operations? This is a story of timing, technology, innovation and knowledge management told through the experiences of a relatively new entrant into the market, Text Mining Solutions. We consider the opportunity that exists in the market, the innovative step required to succeed, and the products and services the current technology enables us to create in response to customer needs. All illustrated with some real examples of how text mining is coming of age and delivering sustainable competitive advantage to businesses across many different market sectors.
About the speaker: Steven is currently Director of Text Mining Solutions Limited, a knowledge and information management company based in York in the United Kingdom. Between 1997 and 2011 Steven was employed by the Food and Environment Research Agency where he was responsible for building strong, sustainable relationships with clients, interpreting complex technical requirements into value adding solutions and ensuring success by delivering through open innovation networks. Steven has a wide range of experience in sales and account management, business development, innovation management and translating customer insights into sustainable competitive advantage. In 2011 Steven set up Text Mining Solutions, a knowledge management business helping companies prioritise their activities and enabling informed decisions to be taken based on meaningful insights, reference materials and evidence. Text Mining Solutions uses the GATE technology platform and helps its clients with: product optimisation and market customisation; customer experience management and benchmarking activities; partnership and innovation development; reviewing online social media strategies for brand awareness, and corporate knowledge management.