Investigating entity-centric methods for information exploration and discovery in big digital archives

A fully-funded AHRC Collaborative Doctoral Partnership PhD studentship is available in the area of investigating entity-centric methods for information exploration and discovery in big digital archives, a collaboration between the University of Sheffield and The National Archives. The studentship is available to start in October 2015.

The National Archives seeks to collect and secure the future of the public record in all its forms and to make it as accessible as possible. One of our largest digital collections is the UK Government Web Archive (UKGWA) which holds digital information published online by Government since 1996. We are seeking a PhD student to help shape the future of information exploration and discovery in big digital archives such as the UKGWA. There is a clear need for cultural heritage institutions (archives, libraries and museums) to provide systems that go beyond keyword-based search and support more diverse information seeking behaviours, such as browsing and exploration of large collections. Entities, such as people, places, organisations and events, can be extracted from the archive and linked to form a network that users can explore in addition to navigating the content directly. This project builds on existing work to create linked data annotations and ontologies to support the exploration of content within the UKGWA.

The UKGWA is the preservation and access solution for digital content that is published online by government. It is free to use and is one of the largest and most heavily used web archives in the world receiving more than twenty million page views each month. The collection is comprised of the contents of over 3000 websites and social media channels, including 2.5 billion web pages dating from 1996 to the present.

The project consists of two main strands: (1) investigating the performance of entity-centric techniques for selecting/aggregating metadata to support user browsing and exploration; and (2) development of prototype systems to investigate how entity-based networks can best support users’ interaction in more exploratory tasks. The project is quite broad in its scope and could appeal to students from a range of disciplines, although the work will require a computational background to enable algorithm and prototype software development. However, system development is only a means to facilitate research and the student would be free to explore directions that are of greater interest, for example developing a suitable evaluation framework for assessing exploration; design and prototyping of the user interface; novel algorithm development for entity extraction and linking; development of novel interface functionalities to support exploration and discovery on top of Linked Open Data; and analysis of users’ information behaviours and needs when using the digital archive.

Candidates should have a background in computer science, information retrieval, library and information science, or a related discipline. The post offers an outstanding opportunity for a dedicated and motivated individual to investigate methods for information exploration and discovery in big digital archives. The successful candidate will be primarily based in the Information School, but will collaborate closely with members of The National Archives and will be expected to spend some time working on-site at The National Archives. Results from this project are likely to benefit academics, practitioners and users of big digital archives.

To apply, please email Professor Paul Clough ([Email Address Removed]) attaching your CV, an example of a piece of recent written work that demonstrates your ability to carry out research and your writing skills (such as a thesis, dissertation, or project report), and a cover letter indicating why you are interested in this project, your reasons for applying to do a PhD and what you could bring to the position.

The closing date for applications is 18th May 2015. Early applications are welcome. Selected candidates will be invited to interview in June at the University of Sheffield. Our final decision will be made by 29th July. The start date for the PhD is 1st October 2015.

For further information please see:

The National Archives: http://www.nationalarchives.gov.uk/
Information School, University of Sheffield: http://www.sheffield.ac.uk/is
UK Government Web Archive: http://www.nationalarchives.gov.uk/webarchive/
AHRC Collaborative Doctoral Awards: http://www.ahrc.ac.uk/Funding-Opportunities/Pages/Collaborative-Doctoral-Awards.aspx