Introduction for skills seminar on Search and Data Mining, Master of European History, University of Luxembourg, 11 December 2014
Post on 19-Jul-2015
441 Views
Preview:
Transcript
Search & Data Mining
SKILLS SEMINAR Master of European History, University of Luxembourg, 11 December 2014
Gerben Zaagsma Lichtenberg-Kolleg,
Why historians should be interested:
Old New CHANGE
Analogue resources Digital resources
SCALE Small data Big data
Close reading Distant reading TECHNOLOGY
the Big Data revolution?
Big data and claims about a paradigm change in the humanities Data driven history
the Big Data revolution?
Big data and claims about a paradigm change in the humanities Data driven history Patterns and structures: a new essentialism?
the Big Data revolution?
Big data and claims about a paradigm change in the humanities Data driven history Patterns and structures: a new essentialism? Based upon changes of scale & method: humanities supposedly becoming more ‘scientific’ > results can be checked and replicated, but can they? Interpretation.
the Big Data revolution?
Big data and claims about a paradigm change in the humanities Data driven history Patterns and structures: a new essentialism? Based upon changes of scale & method: humanities supposedly becoming more ‘scientific’ > results can be checked and replicated, but can they? Interpretation. Politics: funding & valorisation
“One of the problems confronting data enthusiasts in the humanities is that we feel a need to convince our more old-fashioned colleagues about what can be done. But our role as advocates of data shouldn't mean that we lose our critical sense as scholars.
[....] there is a risk that we look more carefully at the technical components of the datasets than the historical context of the information that they represent.
Andrew Prescott, ‘The Deceptions of Data’, Digital Riffs (13 January 2013).
Frédéric Clavert, ‘Lecture des sources historiennes à l’ère numérique’ (14 November 2012)
Integrate approaches & methods/
hybridity
zoeken op Internet algemeen:
er is veel meer dan Google
filter bubble? bekijk eens: http://dontbubble.us
zoeken op Internet algemeen:
er is veel meer dan Google
filter bubble? bekijk eens: http://dontbubble.us
http://www.langreiter.com/exec/yahoo-vs-google.html
zoeken op Internet algemeen:
er is veel meer dan Google
filter bubble? bekijk eens: http://dontbubble.us
http://yometa.com
but be aware of selection: focus on elites and organisations that highlight German Jewry’s process of emancipation :
• classical vision in historiography on German Jewry?• reinforcement of existing master narratives?
Die Sammlung umfasst die 110 wichtigsten jüdischen Zeitungen und Zeitschriften des deutschsprachigen Raumes aus den Jahren 1806-1938. Die Periodika repräsentieren die
gesamte religiöse, politische, soziale, literarische oder wissenschaftliche Bandbreite der jüdischen Gemeinschaft.
•Google/ Bing/ Yahoo
• er is veel meer ...
• resultaten verschillen per zoekmachine
• en er is een filter bubbel
•--> kortom: weten wat je zoekt en zoekstrategie cruciaal
http://eculture.cs.vu.nl/europeana/session/search
Semantic web and linking data
•Google/ Bing/ Yahoo
• er is veel meer ...
• resultaten verschillen per zoekmachine
• en er is een filter bubbel
•--> kortom: weten wat je zoekt en zoekstrategie cruciaalhttp://eculture.cs.vu.nl/europeana/session/search
•Google/ Bing/ Yahoo
• er is veel meer ...
• resultaten verschillen per zoekmachine
• en er is een filter bubbel
•--> kortom: weten wat je zoekt en zoekstrategie cruciaal
At its simplest, data mining is the process of extracting new knowledge (usually in terms of previously unknown
patterns) from sets of data already in existence.
Jonathan Hagood
Data mining (the analysis step of the "Knowledge Discovery in Databases" process, or KDD), an interdisciplinary subfield of
computer science, is the computational process of discovering patterns in large data sets involving methods at the intersection
of artificial intelligence, machine learning, statistics, and database systems.
The overall goal of the data mining process is to extract information from a data set and transform it into an
understandable structure for further use.
Wikipedia
“What is too often forgotten, though, is that our digital helpers are full of ‘theory’ and ‘judgement’ already. As with any methodology, they rely on sets of assumptions, models, and strategies. Theory is already at work on the most basic level when it comes to defining units of analysis, algorithms, and visualisation procedures.”
Bernhard Rieder and Theo Röhle, ‘Digital Methods: Five Challenges’ in: David M Berry ed., Understanding Digital
Humanities (Houndmills: Palgrave Macmillan, 2012) 67-85, 70.
Tools & workflows
Voyant Tools Voyant Tools Documentation Programming Historian DIRT: Digital Research Tools Turkel, William J., Kevin Kee, and Spencer Roberts, ‘A Method for Navigating the Infinite Archive’ in: Toni Weller ed., History in the Digital Age (London; New York: Routledge, 2013). William J. Turkel: How To
Further reading
Special issue on Digital History, BMGN - Low Countries Historical Review, 128/4 (2013). Haber, Peter, Digital Past : Geschichtswissenschaft Im Digitalen Zeitalter (München: Oldenbourg Verlag, 2011). Boonstra, Onno, Leen Breure, and Peter Doorn, Past, Present and Future of Historical Information Science (Amsterdam: NIWI-KNAW, 2004). Ciravegna, Fabio, Mark Greengrass, Tim Hitchcock, Sam Chapman, Jamie McLaughlin, and Ravish Bhagdev, ‘Finding Needles in Hay- Stacks: Data-Mining in Distributed Historical Datasets’ in: Mark Greengrass and Lorna M Hughes eds., The Virtual Representation of the Past (Ashgate, 2008). Cohen, D, F Gibbs, T Hitchcock, G Rockwell, J Sander, R Shoemaker, S Sinclair, S Takats, W J Turkel, and C Briquet. "Data Mining with Criminal Intent." Final white paper (2011). Hagood, Jonathan, "A Brief Introduction to Data Mining Projects in the Humanities." Bulletin of the American Society for Information Science and Technology 38/4 (2012). Hitchcock, Tim, "Big Data for Dead People: Digital Readings and the Conundrums of Positivism." (9 December 2013). Leonard, Peter, "Mining Large Datasets for the Humanities”, IFLA WLIC 2014.
Dr. Gerben Zaagsma
http://gerbenzaagsma.org de.linkedin.com/in/gerbenzaagsma/ https://twitter.com/gerbenzaagsma https://uni-goettingen.academia.edu/GerbenZaagsma https://www.researchgate.net/profile/Gerben_Zaagsma https://www.slideshare.net/gerbenzaagsma
Image credits
The Field Museum Library, Hall 37 Geology overview. URL: https://www.flickr.com/photos/field_museum_library/3333920156/in/set-72157614881700424. The U.S. National Archives, Photograph of Card Catalog in Central Search Room, 1942. URL: http://www.flickr.com/photos/usnationalarchives/3873932255/. Witch computer 1951: Wolverhampton and Staffordshire College of Technology in 1961, The National Computing Museum and Computer Conservation Society/UKAEA/Wolverhampton Express and Star, via: http://www.wired.com/2009/09/britan-oldest-computer/. Code: https://www.flickr.com/photos/lord_james/4696338852/. Tools: Flickr Commons The droids we're googling for: https://www.flickr.com/photos/st3f4n/3951143570/. Jaws (Steven Spielberg) original movie poster: https://en.wikipedia.org/wiki/File:JAWS_Movie_poster.jpg Structured/unstructured data: http://www.emc.com/collateral/demos/microsites/emc-digital-universe-2011/index.htm Macbook Data Mining: http://www.flickr.com/photos/17208993@N00/442531562/. Topic Modeling Martha Ballard’s Diary: http://www.cameronblevins.org/posts/topic-modeling-martha-ballards-diary/. Boolean operators: http://uksourcers.co.uk/2012/capital-letters-the-key-to-boolean-success/ Miami University students in laboratory classroom 1908: https://www.flickr.com/photos/muohio_digital_collections/3199691495/
top related