BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Digging into (Historical) Data: Tracking global commodity trading 
 in the nineteenth century - Prof Ewan Klein - University of Edinburgh
DTSTART:20130522T131500Z
DTEND:20130522T141500Z
UID:TALK44785@talks.cam.ac.uk
CONTACT:David Greaves
DESCRIPTION:Trade in the nineteenth century focused primarily on commoditi
 es\, usually raw materials. The global economy expanded as Western nations
  colonized frontiers rich with natural resources and began to reshape the 
 environment\, introducing plants and animals into new ecosystems\, and tra
 nsporting natural resources back to consumer markets at home.\n\nThe talk 
 will describe Trading Consequences\, a collaborative project funded by JIS
 C's Digging into Data programme that uses text mining to explore digitised
  historical documents related to commodity trading during the nineteenth c
 entury. Prior historical research into commodity flows has focused on a sm
 all handful of widely traded natural resources\, and one of our goals is t
 o build a more accurate picture of how many hundreds of different commodit
 y types were transported across the world. The data that we extract from t
 ext is used to populate a relational database\; via both a conventional qu
 ery interface and an interactive visual interface\, this database will all
 ow historians to explore global trends of commodity trading at different t
 imes and at different locations while still being able to investigate ment
 ions of individual commodities in context.\n\nOne of the main challenges f
 aced in processing the historical text corpora available to us is the low 
 quality of the Optical Character Recognition output\, and the talk will de
 scribe some of our attempts to mitigate this problem. A second challenge i
 s the paucity of resources which would allow us to recognise mentions of c
 ommodities in text. Our current approach takes as its starting point a lis
 t of commodities that we have manually extracted from nineteenth century B
 ritish custom records. This list of terms is incorporated into a SKOS thes
 aurus\; most of the terms can be linked to DBPedia concepts\, which are al
 ready grouped into Wikipedia-derived page categories. The initial thesauru
 s is then expanded by querying DBpedia's SPARQL endpoint for all instances
  of these page categories. We are currently evaluating the performance of 
 the expanded thesaurus against a manually annotated portion of the histori
 cal text.
LOCATION:Lecture Theatre 1\, Computer Laboratory
END:VEVENT
END:VCALENDAR