Open Access Repository

PaperMiner - a real-time spatiotemporal visualization for newspaper articles

Kutty, S, Nayak, R, Turnbull, P ORCID: 0000-0002-7101-1538, Chernich, R, Kennedy, G and Raymond, K 2020 , 'PaperMiner - a real-time spatiotemporal visualization for newspaper articles' , Digital Scholarship in the Humanities, vol. 35, no. 1 , pp. 83-100 , doi:

PDF (Final author version)
142166 - Paperm...pdf | Download (1MB)

| Preview


In 2005, the National Library of Australia (NLA) began a pilot project to selectively digitize back issues of major Australian newspapers to provide free public access to over 60 million digitized newspaper articles, dating from the first years of Australian colonization to the early 1960s. Trove, a faceted search engine maintained by NLA, provides access to this very large collection. Unfortunately, Trove lacked any means to filter by location, which raised the tantalizing possibility of using advanced computational techniques to identify long-term patterns and trends in newspaper reportage of people, events, concepts, and many other historical entities. PaperMiner, which utilizes text mining techniques for extracting metadata information, was developed that enabled the inclusion of geolocations of the places cited in the newspaper articles and supported the searching of articles by location and visualizing the results of searches using both location and time using a map of Australia. Using PaperMiner, researchers could see when and where the anti-Chinese leagues movement started in Australia and how it spread, to better focus their subsequent research. PaperMiner can be used as a digital humanities tool to assist in research by replacing the tedium of a shallow scan through thousands of Trove search results with a more efficient method that draws the researchers’ attention to more significant times and places where their time can be better spent in deeper analysis. In this article, we describe the techniques utilized in creating PaperMiner and discuss its usability testing with a group of leading researchers in Australian history.

Item Type: Article
Authors/Creators:Kutty, S and Nayak, R and Turnbull, P and Chernich, R and Kennedy, G and Raymond, K
Keywords: Digital Humanities
Journal or Publication Title: Digital Scholarship in the Humanities
Publisher: Oxford University Press
ISSN: 2055-7671
DOI / ID Number:
Copyright Information:

Copyright The Author(s) 2019. Published by Oxford University. This is a pre-copyedited, author-produced version of an article accepted for publication in Digital Scholarship in the Humanities following peer review. The version of record, Sangeetha Kutty, Richi Nayak, Paul Turnbull, Ron Chernich, Gavin Kennedy, Kerry Raymond, PaperMiner—a real-time spatiotemporal visualization for newspaper articles, Digital Scholarship in the Humanities, Volume 35, Issue 1, April 2020, Pages 83–100, is available online at:

Related URLs:
Item Statistics: View statistics for this item

Actions (login required)

Item Control Page Item Control Page