Programming Historian Lesson on the Edinburgh Geoparser

The Programming Historian lesson on Geoparsing Text with the Edinburgh Geoparser was released yesterday. The Programming Historian site provides novice-friendly, peer-reviewed lessons that help humanists acquire skills on using different digital tools and techniques for research or teaching.

The lesson on the Edinburgh Geoparser is a step-by-step guide on how to download and set up the tool, how to geo-parse a text file and how to extract the geo-location information from the geoparser’s XML output into TSV format. We are hoping that anyone interested in mapping location mentions in text will try it out. We would like to thank the reviewers, Anouk Lang, Sarah Simpkin and Ian Milligan, for all of their useful comments and feedback.

Posted in Uncategorized | Comments Off on Programming Historian Lesson on the Edinburgh Geoparser

First Edinburgh Geoparser Workshop at the Digital Day of Ideas

Last week Beatrice Alex held the first workshop on using the Edinburgh Geoparser at the Digital Day of Ideas 2016. This was one in a set of hands-on workshops on using different tools and techniques relevant to Digital Humanities research, including visualisation in D3, Drupal, tweeting/blogging for academics and WordPress.

The Edinburgh Geoparser is a language processing tool designed to detect place name references in English text and ground them against an authoritative gazetteer so that they can be plotted on a map. It is operated via the command line. Given the event’s broad audience from the Humanities and Social Sciences, the workshop was targetted at participants with limited command line expertise.

The attendees were able to follow the material and made useful suggestions related to the inner workings of the tool. The workshop slides can be found here.

Posted in geoparser, workshop | Comments Off on First Edinburgh Geoparser Workshop at the Digital Day of Ideas

First Release of the Edinburgh Geoparser

The Edinburgh Geoparser (v1.0) has been released under the University of Edinburgh GPL license on Dec. 18th 2015.

It can now be used by other researchers in the field of text mining as well as scholars in the humanities and social sciences who would like to geoparse text and prefer to have more control over the tool.

More information on the Edinburgh Geoparser, its documentation, our publications about it and how to download it can be found here. An online demo of the Geoparser can be tested here.

We have used the Edinburgh Geoparser in many research projects and tailored it to different needs, for example to perform fine-grained geo-referencing for literature set in Edinburgh (Palimpsest) presented in the LitLong interface, to geo-reference volumes of the Survey of English Place Names (DEEP) or to geo-reference large historical collections related to commodity trading in the 19th century British Empire (Trading Consequences).  We adapted the geoparser to the ancient world for the GAP project, with its GapVis interface, and for Hestia Phase 2 which developed the interface further for use in undergraduate study of classical literature in translation. The geoparser has also been used in external research projects, including Prof. Ian Gregory‘s group on geo-referencing 19th century newspapers.

We welcome suggestions and future collaboration, so please get in touch if you have ideas about how we should develop the software (balex AT staffmail DOT ed DOT ac DOT uk).

Posted in Uncategorized | Comments Off on First Release of the Edinburgh Geoparser