What motivates library
crowdsourcing volunteers?
Experiences at the California Digital Newspaper
Collection and the
Cambri...
Photo held by John Oxley Library, State Library of Queensland. Original from
Courier-mail, Brisbane, Queensland, Australia...
Crowd
Properties
In it he says ...
In 2004 James Surowiecki published ...
The Wisdom of Crowds: Why
the Many Are Smarter Than
the Few and H...
... a crowd of persons that are
diverse ...
... independent ...
... and
decentralized ...
usually make
better
judgements or
decisions than
single persons
“Country Fair” by Grandma Moses. Original painting 1950.
wisdom of crowds
in summary
James Surowiecki, The Wisdom of Crowds: Why the Many Are Smarter Than the Few and How Collecti...
Crowdsourcing
Short history
“crowdsourcing”
was coined by Jeff Howe in “The rise of
crowdsourcing” published in Wired
magazine June 2006.
web trends for
“crowdsourcing”
Jan-2006 to Jan-2013
• On the date of publication of Jeff Howe’s Wired
magazine article, 1-Jun-2007, Wikipedia did not have
an entry (list) of ...
Crowdsourcing is the practice of obtaining
needed services, ideas, or content by
soliciting contributions from a large gro...
Amazon Mechanical Turk was launched Nov 2005
Alexa global / USA rank of Amazon Mechanical Turk (Jun 2013): 8,242 / 3,060
A...
CAPTCHA is a Completely Automated Public Turing test to tell Computers and Human
Apart
Started as a computer science proje...
Open Street Map was 1st launched in 2007
Alexa global / Belarus / USA traffic rank of Open Street Map (Jun 2013): 8,853 / ...
Zooniverse was 1st launched July 2007
Alexa global / USA traffic rank of Zooniverse (Jun 2013): 275,960 / 153,853
Alexa re...
Kickstarter was launched in 2009
Alexa global / USA traffic rank of Kickstarter (Jun 2013): 798 / 361
Alexa reputation (Ju...
crowdcollaboration
• Began 2001
• Now in 285 languages
• 40 wikipedia
languages with more
than 100,000 articles
• 112 wikipedia
languages wit...
Wikipedia contributors, "List of crowdsourcing projects," Wikipedia, The Free Encyclopedia, http://
en.wikipedia.org/wiki/...
Crowdsourcing
and Libraries
Family Search Indexing was 1st launched (beta) 2004
Alexa global / USA traffic rank of FamilySearch (Jun 2013): 4,664 / 1,...
• Started (beta) 2004
• More than 780,000 worldwide registered volunteers
from ~25 countries index records relevant to fam...
Project Gutenberg was 1st launched Dec 1971
Alexa global traffic rank of Project Gutenberg (Jun 2013): 6,709
Alexa reputat...
• Started Dec 1971
• Worldwide volunteers transcribe or proofread OCR’d
public domain books through Distributed Proofreade...
Alexa global / Australia traffic rank of National Library of Australia (June 2013): 15,435 / 411
Trove gets ~77% of all Na...
National Library of
Australia
• Online since 2008
• More than 9,830,000 / 96,000,000 newspaper
pages / articles (May 2013)...
Alexa global / country traffic rank of National Library of Finland
2,535,854 (31-Oct-2012) / 199 (2-Apr-2012)
National Library of
Finland
• Digitalkoot is a project to improve OCR text in
digitized newspapers -- by playing games!
• ...
Alexa global / USA traffic rank of UC Riverside (June 2013): 12,584 / 4,382
CDNC gets ~1.6% of all UC Riverside web traffi...
California Digital
Newspaper Collection
• CDNC began digitizing newspapers in 2005 as
part of NDNP
• Newspapers digitized ...
OCR text correction
• OCR text correction added Aug 2011
• Corrections are done line by line
• 1340 registered / 599 activ...
Cambridge Public Library
Historic Newspaper Collection
• Cambridge Historic Newspapers online since Jan 2012.
• Cambridge ...
Crowdsourcing
Motivation
Cognitive surplus
... people are learning to use their free time for creative
activities rather than consumptive ones [suc...
User Lines corrected
1 379,578
2 136,637
3 56,996
4 52,093
5 46,102
6 39,617
7 35,878
8 33,204
9 31,319
10 30,408
Lines co...
Motivation
genealogists and family
historians
• National Library of Australia’s 2012 Trove
status report showed that ~50% ...
User survey
• CDNC and Cambridge Public Library published a user
survey in Mar 2013 (it’s still online)
• 604 / 32 respons...
User demographic
genealogists and family historians
User demographic
no spring chickensX
User demographic
reasons for use
User demographic
types of information
“I enjoy the correction - it’s a great way to learn more about
past history and things of interest whilst doing a ‘service...
“I am interested in all kinds of history. I have pursued genealogy
as a hobby for many years. I correct text at CDNC becau...
“I only correct the text on articles of local interest - nothing at
state, national or international level, no advertiseme...
“I am correcting text for the Coronado Tent City Program for
1903.  It is important to correct any problems with personal
...
“I have always been interested in history, especially the
development of the American West, and nothing brings it alive
be...
CDNC is an excellent source of information matching my
personal interest in such topics as sea history, development
of shi...
As an amateur historical researcher my time for research is very
limited.  Making time to travel to archives, libraries, a...
Graphic from Kaufmann et al. “More than fun and money. Worker Motivation
in Crowdsourcing – A Study on Mechanical Turk.”
M...
Crowdsourcing
Interesting fact
the long tail* of crowdsourced
OCR text correction
a probability distribution has a long tail if a larger share
of the pop...
OCR text correction long tails
0
75000
150000
225000
300000
CDNC lines corrected by text corrector
0
750,000
1,500,000
2,2...
Website traffic
Website traffic
After a crowdsourcing transcription project of diaries from the
American War Between the States, Nicole Sa...
Website traffic
Website traffic at CDNC before / after implementing
crowdsourcing
before crowdsourcing
11-Jun-2011 / 12-Ju...
Website traffic
Accuracy
“His Accuracy Depends on Ours!"
Office for Emergency Management. Office of War
Information. Domestic Operations B...
Why correct OCR text?
Here’s why ...
Deaths. lln»rieff, Esq. of <c .. Qn.
Sunday, the till. greatly Drandrellt, of
Orms4irJi.- ~ ; ;✓ ' • * On ijfr r inn
l j j...
Accuracy
• Edwin Kiljin (Koninklijke Bibliotheek the Netherlands)
reports raw OCR character accuracies of 68% for early 20...
Accuracy
MAPPING TEXTS* assesses digitization quality of
digital newspapers by comparing the number of words
recognized to...
uncorrected OCR accuracy by
newspaper title
Title
OCR character
accuracy
~OCR word
accuracy*
PRP Pacific Rural Press 1871 ...
OCR accuracy by newspaper title
Title
OCR character
accuracy
Corrected
accuracy
PRP Pacific Rural Press 1871 - 1922 92.6% ...
corrected accuracy
by newspaper title
Title
OCR character
accuracy
~OCR word
accuracy*
Corrected
accuracy
~Corrected
word ...
correction accuracy by user
User
Average OCR
accuracy
Correction
accuracy
A 70.4% 100.0%
B 87.1% 99.5%
C 95.4% 99.5%
D 86....
How does low text accuracy affect search recall?
The Facts
• Average uncorrected OCR character accuracy of the
CDNC sample...
ARNDT
ARNDT
ARNDT
ARNDT ARNDT
ARNDT
ARNDT
ARNDT
ARNDT
ARNDT
Search recall no text correction
instances of “ARNDT” found in...
Accuracy
The Facts
• Average corrected character accuracy of the CDNC
sample data is ~99.4%
• Average word accuracy of CDN...
ARNDT
ARNDT
ARNDT
ARNDT ARNDT
ARNDT
ARNDT
ARNDT
ARNDT
ARNDT
instances of “ARNDT” found instances of “ARNDT” not found
Sear...
A search for “Arndt” at Chronicling America gives
10,267 results*
• If Chronicling America text accuracy is 55.8% (same as...
Accuracy
Suppose the word/name is longer than 5
characters?
The Facts
• Assume that average uncorrected / corrected OCR
ch...
Accuracy
Name
Number of
search results
Missing results with
raw text accuracy
Missing results with
corrected text accuracy...
Crowdsourcing
economic benefits
Public domain photo courtesy of US Navy
$
Economic benefits
Financial value of outsourced OCR text correction
for newspapers?
The Assumptions
• 25 to 50 character...
$
Economics
$ 578,000 lines x 40 characters per line x
1/1000 x $0.50 = $11,560
$ 68,908,757 lines x 40 characters per lin...
$
Economics
Financial value of in-house OCR text
correction?
The Assumptions
• Correction takes 15 seconds per line
• Cost...
$
Economics
$ 578,000 lines x 15 seconds per line x 1/3600 hrs
per second x $10.00 per hr = $24,083
$ 68,908,757 lines x 1...
Crowdsourcing
other benefits
Public domain photo “A useful instruction for young sailors from the Royal Hospital
School, G...
“when someone transcribes a document, they are
actually better fulfilling the mission of a cultural
heritage organization ...
“in addition to increasing search accuracy or lowering
the costs of document transcription, crowdsourcing is
the single gr...
Crowdsourcing considerations
• How to market / advertise
crowdsourcing?
• How to motivate
crowdsourcers?
• Is authenticati...
Conclusions
Conclusion of the Sonata for piano #32, opus 111 by
Ludwig van Beethoven
• Lots of crowdsourcing in cultural h...
Resources
Public domain photo “A useful instruction for young sailors from the Royal
Hospital School, Greenwich” from the ...
Comprehensive worldwide list of online
newspaper archives
Wikipedia contributors, "List of online newspaper archives," Wik...
Search many digital newspaper
collections at once!
As of June 2013 elephind (http://www.elephind.com) has indexed 1,032 ne...
Correct California newspapers at http://cdnc.ucr.edu
Correct Cambridge MA newspapers http://bit.ly/cambridgepublic
Correct...
Hãy thử crowdsourcing!
Or try Russian language periodicals http://bit.ly/russianperiodicals
Correct Vietnamese newspapers ...
Other resources
Mapping Texts at http://mappingtexts.stanford.edu/
Wragge Labs at http://wraggelabs.com/
Wikipedia list of...
?Brian Geiger
bgeiger@ucr.edu
Frederick Zarndt
frederick@frederickzarndt.com
Photo held by John Oxley Library, State Libra...
20130630 What motivates library crowdsourcing volunteers? [ALA LITA]
20130630 What motivates library crowdsourcing volunteers? [ALA LITA]
20130630 What motivates library crowdsourcing volunteers? [ALA LITA]
20130630 What motivates library crowdsourcing volunteers? [ALA LITA]
Upcoming SlideShare
Loading in …5
×

20130630 What motivates library crowdsourcing volunteers? [ALA LITA]

808
-1

Published on

Published in: Education, Technology
0 Comments
0 Likes
Statistics
Notes
  • Be the first to comment

  • Be the first to like this

No Downloads
Views
Total Views
808
On Slideshare
0
From Embeds
0
Number of Embeds
5
Actions
Shares
0
Downloads
15
Comments
0
Likes
0
Embeds 0
No embeds

No notes for slide

20130630 What motivates library crowdsourcing volunteers? [ALA LITA]

  1. 1. What motivates library crowdsourcing volunteers? Experiences at the California Digital Newspaper Collection and the Cambridge Public Library Newspapers Collection Brian Geiger Director, Center for Bibliographical Studies and Research California Digital Newspaper Collection Frederick Zarndt Chair, IFLA Newspapers Section
  2. 2. Photo held by John Oxley Library, State Library of Queensland. Original from Courier-mail, Brisbane, Queensland, Australia. 1. crowds, properties of 2.crowdsourcing, short history of 3.crowdsourcing and libraries, especially digital newspapers collections 4.crowdsourcing, motivations for 5.crowdsourcing, interesting fact 6.crowdsourcing, website traffic 7. crowdsourcing, accuracy of 8.crowdsourcing, economic benefits of 9.crowdsourcing, other benefits of
  3. 3. Crowd Properties
  4. 4. In it he says ... In 2004 James Surowiecki published ... The Wisdom of Crowds: Why the Many Are Smarter Than the Few and How Collective Wisdom Shapes Business, Economies, Societies and Nations
  5. 5. ... a crowd of persons that are diverse ...
  6. 6. ... independent ...
  7. 7. ... and decentralized ...
  8. 8. usually make better judgements or decisions than single persons
  9. 9. “Country Fair” by Grandma Moses. Original painting 1950.
  10. 10. wisdom of crowds in summary James Surowiecki, The Wisdom of Crowds: Why the Many Are Smarter Than the Few and How Collective Wisdom Shapes Business, Economies, Societies and Nations, Anchor Books, New York, 2005. Diversity Each person should have private information even if it's just an eccentric interpretation of the known facts. Independence People's opinions aren't determined by the opinions of those around them. Decentralization People are able to specialize and draw on local knowledge. Aggregation Some mechanism exists for turning private judgments into a collective decision.
  11. 11. Crowdsourcing Short history
  12. 12. “crowdsourcing” was coined by Jeff Howe in “The rise of crowdsourcing” published in Wired magazine June 2006.
  13. 13. web trends for “crowdsourcing” Jan-2006 to Jan-2013
  14. 14. • On the date of publication of Jeff Howe’s Wired magazine article, 1-Jun-2007, Wikipedia did not have an entry (list) of crowdsourcing projects*. • On 25-Jan-2010 Wikipedia’s list of crowdsourcing projects had 35 entries*. • On 17-Mar -2013 Wikipedia’s list of crowdsourcing projects had 158 entries+. * From Internet Archives’ Wayback Machine. + Wikipedia contributors, "List of crowdsourcing projects," Wikipedia, The Free Encyclopedia, https:// en.wikipedia.org/wiki/List_of_crowdsourcing_projects (accessed March 17, 2013).
  15. 15. Crowdsourcing is the practice of obtaining needed services, ideas, or content by soliciting contributions from a large group of people, and especially from an online community, rather than from traditional employees or suppliers. ... [It] is different from ordinary outsourcing since it is a task or problem that is outsourced to an undefined public rather than a specific, named group. Wikipedia contributors, "Crowdsourcing," Wikipedia, The Free Encyclopedia, http://en.wikipedia.org/wiki/ Crowdsourcing (accessed March 17, 2013)
  16. 16. Amazon Mechanical Turk was launched Nov 2005 Alexa global / USA rank of Amazon Mechanical Turk (Jun 2013): 8,242 / 3,060 Alexa reputation (Jun 2013): 1.344 crowdsourcing
  17. 17. CAPTCHA is a Completely Automated Public Turing test to tell Computers and Human Apart Started as a computer science project at Carnegie Mellon Each day 200,000,000 recaptcha’s are solved by humans around the world
  18. 18. Open Street Map was 1st launched in 2007 Alexa global / Belarus / USA traffic rank of Open Street Map (Jun 2013): 8,853 / 1,373 / 20,114 Alexa reputation (Jun 2013): 28,368
  19. 19. Zooniverse was 1st launched July 2007 Alexa global / USA traffic rank of Zooniverse (Jun 2013): 275,960 / 153,853 Alexa reputation (Jun 2013): 502 Registered users (Jun 2013): 848,140 citizen science
  20. 20. Kickstarter was launched in 2009 Alexa global / USA traffic rank of Kickstarter (Jun 2013): 798 / 361 Alexa reputation (Jun 2013): 85,591 43,000+ projects successfully funded with more than USD $669,000,000 crowdfunding
  21. 21. crowdcollaboration
  22. 22. • Began 2001 • Now in 285 languages • 40 wikipedia languages with more than 100,000 articles • 112 wikipedia languages with more than 10,000 articles • 400,000,000 unique visitors per month • 3,900,000+ articles in English, 1,400,000+ in German, 1,250,000+ in French, 1,050,000 in Dutch • 85,000 active contributors / more than 300,000 have edited Wikipedia more than 10 times • Alexa global / USA traffic rank (Jun 2013): 7 / 8 • Alexa reputation (Jun 2013): 2,102,569
  23. 23. Wikipedia contributors, "List of crowdsourcing projects," Wikipedia, The Free Encyclopedia, http:// en.wikipedia.org/wiki/List_of_crowdsourcing_projectss (accessed Jun 2013).
  24. 24. Crowdsourcing and Libraries
  25. 25. Family Search Indexing was 1st launched (beta) 2004 Alexa global / USA traffic rank of FamilySearch (Jun 2013): 4,664 / 1,373 Alexa reputation (Jun 2013): 8,140
  26. 26. • Started (beta) 2004 • More than 780,000 worldwide registered volunteers from ~25 countries index records relevant to family history • Approximately 100,000 active volunteers each month • UI in Chinese, English, German, French, Italian, Japanese, Korean, Portuguese, and Russian • Blind double-key entry with arbitration / reconciliation • More than 1,500,088,741 records indexed (July 2012) • Accuracy typically > 99.95%
  27. 27. Project Gutenberg was 1st launched Dec 1971 Alexa global traffic rank of Project Gutenberg (Jun 2013): 6,709 Alexa reputation (Jun 2013): 31,190
  28. 28. • Started Dec 1971 • Worldwide volunteers transcribe or proofread OCR’d public domain books through Distributed Proofreaders • 40,000 books completed (July 2012) • Partner / affiliated projects for Australia, Canada, Europe, Germany, Luxembourg, Philippines, Runeberg (Nordic literature), Russia, Taiwan
  29. 29. Alexa global / Australia traffic rank of National Library of Australia (June 2013): 15,435 / 411 Trove gets ~77% of all National Library web traffic. Alexa reputation (Jun 2013): 8,788
  30. 30. National Library of Australia • Online since 2008 • More than 9,830,000 / 96,000,000 newspaper pages / articles (May 2013) • Top text corrector 1,911,000+ lines (May 2013) • 2,661,140 lines corrected each month (average for 1st 5 months 2013) • 96,304,337 lines corrected as of May 2013, up from 66,527,535 lines corrected May 2012 • 95,299 / 8,519 registered / active users (May 2013)
  31. 31. Alexa global / country traffic rank of National Library of Finland 2,535,854 (31-Oct-2012) / 199 (2-Apr-2012)
  32. 32. National Library of Finland • Digitalkoot is a project to improve OCR text in digitized newspapers -- by playing games! • Digitalkoot is a collaboration between the National Library and Microtask • Players correct OCR text by playing Myyräsillassa (Mole Bridge) or Myyräjahdissa (Mole Hunt) • National Library has 4,000,000+ digitized pages • 109,321 registered players (October 2012) • Since February 2011 8,024,530 micro-tasks have been completed
  33. 33. Alexa global / USA traffic rank of UC Riverside (June 2013): 12,584 / 4,382 CDNC gets ~1.6% of all UC Riverside web traffic.
  34. 34. California Digital Newspaper Collection • CDNC began digitizing newspapers in 2005 as part of NDNP • Newspapers digitized to article-level as well as to page-level as required by NDNP • Hosted on Veridian beginning 2009 • Collection size 61,351 issues, 544,474 pages, 6,327,491 articles (May 2013)
  35. 35. OCR text correction • OCR text correction added Aug 2011 • Corrections are done line by line • 1340 registered / 599 active users (Jun 2013) • ~1,160,465+ lines of text corrected (Jun 2013) • ~1.1% of the collection corrected, 98.9% to go! • Top corrector 379,573 lines > 2x 2nd corrector
  36. 36. Cambridge Public Library Historic Newspaper Collection • Cambridge Historic Newspapers online since Jan 2012. • Cambridge Massachusetts Public Library digitized local newspapers (http://cambridge.dlconsulting.com/) • Newspapers digitized to article-level • Collection size 6,346 issues, 59,070 pages, 669,406 articles (May 2013) • Collection includes 13,099 obituary cards
  37. 37. Crowdsourcing Motivation
  38. 38. Cognitive surplus ... people are learning to use their free time for creative activities rather than consumptive ones [such as watching TV] ... ... the total human cognitive effort in creating all of Wikipedia in every language is about one hundred million hours ... ... Americans alone watch two hundred billion hours of TV every year, or enough time, if it would be devoted to projects similar to Wikipedia, to create about 2000 of them ... Clay Shirky. Cognitive surplus: Creativity and generosity in a connected age. Penguin Press. New York. 2010.
  39. 39. User Lines corrected 1 379,578 2 136,637 3 56,996 4 52,093 5 46,102 6 39,617 7 35,878 8 33,204 9 31,319 10 30,408 Lines corrected User 1,456,906 1 1,385,369 2 1,010,360 3 960,230 4 847,340 5 786,147 6 657,187 7 600,513 8 582,276 9 565,384 10
  40. 40. Motivation genealogists and family historians • National Library of Australia’s 2012 Trove status report showed that ~50% of Trove users are family historians • National Library of New Zealand survey found that ~50% of PapersPast users are genealogists • A 2012 Utah Digital Newspapers survey showed that 72% of its users are genealogists* PAPERSPAST *John Herbert and Randy Olsen. “Small town papers: Still delivering the news”. Paper given at 2012 World Library and Information Congress. Helsinki. August 2012.
  41. 41. User survey • CDNC and Cambridge Public Library published a user survey in Mar 2013 (it’s still online) • 604 / 32 responses • surveys are (mostly) identical except for organization name Survey is on home pages at http://cdnc.ucr.edu and http://cambridge.dlconsulting.com/
  42. 42. User demographic genealogists and family historians
  43. 43. User demographic no spring chickensX
  44. 44. User demographic reasons for use
  45. 45. User demographic types of information
  46. 46. “I enjoy the correction - it’s a great way to learn more about past history and things of interest whilst doing a ‘service to the community’ by correcting text for the benefit of others.” “I have recently retired from IT and thought that I could be of some assistance to the project. It benefits me and other people. It helps with family research.” From Rose Holley in “Many Hands Make Light Work.” National Library of Australia March 2009. Motivation Trove users’ report
  47. 47. “I am interested in all kinds of history. I have pursued genealogy as a hobby for many years. I correct text at CDNC because I see it as a constructive way to contribute to a worthwhile project. Because I am interested in history, I enjoy it.” Wesley, California Personal communications with CDNC text correctors. Motivation CDNC users’ report
  48. 48. “I only correct the text on articles of local interest - nothing at state, national or international level, no advertisements, etc.  The objective is to be able to help researchers to locate local people, places, organizations and events using the on-line search at CDNC.  I correct local news & gossip, personal items, real estate transactions, superior court proceedings, county and local board of supervisors meetings, obituaries, birth notices, marriages, yachting news, etc.” Ann, California Personal communications with CDNC text correctors. Motivation CDNC users’ report
  49. 49. “I am correcting text for the Coronado Tent City Program for 1903.  It is important to correct any problems with personal names and other information so that researchers will be able to search by keyword and be assured of retrieving desired results. ... type fonts cause a great deal of difficulty in digitizing the text and can cause problems for searchers.  Also, many of the guests' names at Tent City and Hotel Del Coronado were taken from the registration books and reported in the Program.  This led to many problems in spelling of last names and the editors were not careful to be consistent in the spellings.  This Program is an important resource since it provides an excellent picture of daily life in Tent City and captures much of the history of Coronado itself.” Gene, California Personal communications with CDNC text correctors. Motivation CDNC users’ report
  50. 50. “I have always been interested in history, especially the development of the American West, and nothing brings it alive better than newspapers of the time. I believe them to be an invaluable source of knowledge for us and future generations.” David, United Kingdom Personal communications with CDNC text correctors. Motivation CDNC users’ report
  51. 51. CDNC is an excellent source of information matching my personal interest in such topics as sea history, development of shipbuilding, clippers and other ships etc. ... Unfortunately, the quality of text ... is rather poor I’m afraid. This is why I started to do all corrections necessary for myself ... and to leave the corrected text for use of others. .... I am not doing this very regularly as this is just my hobby and pleasure. Jerzey, Poland Personal communications with CDNC text correctors. Motivation CDNC users’ report
  52. 52. As an amateur historical researcher my time for research is very limited.  Making time to travel to archives, libraries, and historical societies does not happen as often as I would like.  The Cambridge Public Library’s online newspaper collection has been an invaluable resource and it is fun.  I am very grateful for all the help I have received over the years from so many research organizations. Correcting text has several benefits.  It makes it much more likely that I will find a story if I decide to search for it in the future.  It is a way of saying ‘thank you’ to the Cambridge Library for having such a great resource available and maybe I can make the next person’s research a little easier. It is my own little historical preservation project. Daniel, Massachusetts Personal communications with Cambridge text correctors. Motivation Cambridge users’ report
  53. 53. Graphic from Kaufmann et al. “More than fun and money. Worker Motivation in Crowdsourcing – A Study on Mechanical Turk.” Motivation
  54. 54. Crowdsourcing Interesting fact
  55. 55. the long tail* of crowdsourced OCR text correction a probability distribution has a long tail if a larger share of the population rests within its tail than would be the case if the population were normally distributed. the most productive users represent a small fraction of the total user population and complete ~50% of total production. said a different way, less productive users represent the largest fraction of the user population and also complete ~50% of the total production. The phrase “long tail” was popularized by Chris Anderson in the October 2004 Wired magazine article The Long Tail and by Clay Shirky’s February 2003 essay “Power laws, web logs, and inequality”.
  56. 56. OCR text correction long tails 0 75000 150000 225000 300000 CDNC lines corrected by text corrector 0 750,000 1,500,000 2,250,000 3,000,000 NLA lines corrected by text corrector top corrector 242,965 top corrector 1,456,906 50% 50% 50% 50% Statistics from Oct 2012
  57. 57. Website traffic
  58. 58. Website traffic After a crowdsourcing transcription project of diaries from the American War Between the States, Nicole Saylor, Head of Digital Library Services at the University of Iowa Libraries, reported “On June 9, 2011, we went from about 1000 daily hits to our digital library on a really good day to more than 70,000.” Nicole Saylor interviewed by Trevor Owens. “Crowdsourcing the Civil War: Insights Interview with Nicole Saylor” blog post at http://blogs.loc.gov/digitalpreservation/2011/12/crowdsourcing-the-civil-war-insights-interview-with-nicole-saylor/. Dec 6, 2011.
  59. 59. Website traffic Website traffic at CDNC before / after implementing crowdsourcing before crowdsourcing 11-Jun-2011 / 12-Jul-2011 after crowdsourcing 11-Jun-2012 / 12-Jul-2012 change visits 17,485 21,488 +22.9% unique visitors 11,381 13,376 +17.5% visit duration 9m 24s 11m 7s +18.3% bounce rate 51.3% 44.5% -6.8% pages per visit 14.9 11.7 -21.5%
  60. 60. Website traffic
  61. 61. Accuracy “His Accuracy Depends on Ours!" Office for Emergency Management. Office of War Information. Domestic Operations Branch. Bureau of Special Services. [Photo held at US National Archives and Records Administration]
  62. 62. Why correct OCR text? Here’s why ...
  63. 63. Deaths. lln»rieff, Esq. of <c .. Qn. Sunday, the till. greatly Drandrellt, of Orms4irJi.- ~ ; ;✓ ' • * On ijfr r inn l j j j i l F i i j ' 1 1 f H a v o d i v y d , Carnarvonshire, S ; **" *- ' « ' March Oxford, F. Tfovmeud, Uerald. » • V . •On Tncsdav last, Mr. Charles. IWilinson, this 8 ; had vf thesis#,, a week ago, which tcrminate<i'iu his death. . / ' ■ O'i Sunday, dJst nit. at. AsbtCnvHall, mar Lancaster, Mr.,Geo. Worn ick, many years house'steward hit late Once The Hamilton and Brandon. He locked himself h»oWn'r«wte<: soon. twelve o'clock" that dny, and fii»-d a loaded pistol "through Ins bead, 1 which instantaneously killed him. Coronet's Verdict, shot himself in a temporary fit of Friday week, raw OCR text Excerpt from The British Newspaper Archive, Chester Courant, Tuesday 6-Apr-1819, page 3. newspaper image
  64. 64. Accuracy • Edwin Kiljin (Koninklijke Bibliotheek the Netherlands) reports raw OCR character accuracies of 68% for early 20th century newspapers • Rose Holley (National Library of Australia) reports raw OCR character accuracy varied from 71% to 98% on a sample Trove digitized newspapers Rose Holley. “How good can it get? Analysing and improving OCR accuracy in large scale historic newspaper digitisation programs. D-Lib Magazine. March/April 2009. Edwin Kiljin. “The current state-of-art in newspaper digitization.” D-Lib Magazine. January/February 2008. Public domain graphic courtesy of Wikimedia Commons.
  65. 65. Accuracy MAPPING TEXTS* assesses digitization quality of digital newspapers by comparing the number of words recognized to the total number of words scanned * Mapping texts is a collaboration between the University of North Texas and Stanford University aimed at experimenting with new methods for finding and analyzing meaningful patterns embedded in massive collections of digital newspapers.
  66. 66. uncorrected OCR accuracy by newspaper title Title OCR character accuracy ~OCR word accuracy* PRP Pacific Rural Press 1871 - 1922 92.6% 68.1% SFC San Francisco Call 1890 - 1913 92.6% 68.1% LAH Los Angeles Herald 1873 - 1910 88.7% 54.9% LH Livermore Herald 1877 - 1899 88.6% 54.6% DAC Daily Alta California 1841 - 1891 88.2% 53.4% CFJ California Farmer and Journal of Useful Sciences 1855 - 1880 86.5% 48.4% SN Sausalito News 1885 - 1922 70.4% 17.3% *Word accuracy assumes average word length is 5 characters
  67. 67. OCR accuracy by newspaper title Title OCR character accuracy Corrected accuracy PRP Pacific Rural Press 1871 - 1922 92.6% 99.3% SFC San Francisco Call 1890 - 1913 92.6% 99.6% LAH Los Angeles Herald 1873 - 1910 88.7% 99.1% LH Livermore Herald 1877 - 1899 88.6% 99.9% DAC Daily Alta California 1841 - 1891 88.2% 99.9% CFJ California Farmer and Journal of Useful Sciences 1855 - 1880 86.5% 99.8% SN Sausalito News 1885 - 1922 70.4% 100.0%
  68. 68. corrected accuracy by newspaper title Title OCR character accuracy ~OCR word accuracy* Corrected accuracy ~Corrected word accuracy* PRP 1871 - 1922 92.6% 68.1% 99.3% 96.5% SFC 1890 - 1913 92.6% 68.1% 99.6% 98.0% LAH 1873 - 1910 88.7% 54.9% 99.1% 95.6% LH 1877 - 1899 88.6% 54.6% 99.9% 99.5% DAC 1841 - 1891 88.2% 53.4% 99.9% 99.5% CF 1855 - 1880 86.5% 48.4% 98.3% 91.8% SN 1885 - 1922 70.4% 17.3% 100.0% 100.0% *Word accuracy assumes average word length is 5 characters
  69. 69. correction accuracy by user User Average OCR accuracy Correction accuracy A 70.4% 100.0% B 87.1% 99.5% C 95.4% 99.5% D 86.5% 98.3% E 95.3% 100.0% F 91.0% 100.0% G 91.0% 99.8% H 90.5% 99.0% I 96.6% 99.8% J 94.8% 100.0% K 86.8% 99.3%
  70. 70. How does low text accuracy affect search recall? The Facts • Average uncorrected OCR character accuracy of the CDNC sample data is ~89% • Average length of an English word is 5 characters • Average word accuracy is 89% x 89% x 89% x 89% x 89% = 55.8% - round up to 60% or 6 out of 10 words correct Accuracy
  71. 71. ARNDT ARNDT ARNDT ARNDT ARNDT ARNDT ARNDT ARNDT ARNDT ARNDT Search recall no text correction instances of “ARNDT” found instances of “ARNDT” not found
  72. 72. Accuracy The Facts • Average corrected character accuracy of the CDNC sample data is ~99.4% • Average word accuracy of CDNC corrected text is 99.4% x 99.4% x 99.4% x 99.4% x 99.4% = 97.0%
  73. 73. ARNDT ARNDT ARNDT ARNDT ARNDT ARNDT ARNDT ARNDT ARNDT ARNDT instances of “ARNDT” found instances of “ARNDT” not found Search recall with text correction
  74. 74. A search for “Arndt” at Chronicling America gives 10,267 results* • If Chronicling America text accuracy is 55.8% (same as uncorrected CDNC sample), then 8,133 instances of “Arndt” were not found • If text accuracy is 97.0%, then 317 instances of “Arndt” were not found Accuracy * Search performed 31 Oct 2012
  75. 75. Accuracy Suppose the word/name is longer than 5 characters? The Facts • Assume that average uncorrected / corrected OCR character accuracy is ~89% / ~99% same as CDNC. Name Name length Raw text accuracy Corrected text accuracy Eklund 6 49.7% 94.2% Kennedy 7 44.2% 93.25 Espinosa 8 39.4% 92.3% Bonaparte 9 35.0% 91.4% Chatterjee 10 31.2% 90.4%
  76. 76. Accuracy Name Number of search results Missing results with raw text accuracy Missing results with corrected text accuracy Eklund 2,951 2,987 182 Kennedy 360,723 455,392 26,111 Espinosa 1,918 2,950 160 Bonaparte 44,664 82,947 4,203 Chatterjee 19 42 2 Chronicling America searches done 19-Mar-2013 (6,025,474 pages from 1836 to 1922).
  77. 77. Crowdsourcing economic benefits Public domain photo courtesy of US Navy
  78. 78. $ Economic benefits Financial value of outsourced OCR text correction for newspapers? The Assumptions • 25 to 50 characters per line in a newspaper column: Assume 40 characters per line (CDNC sample average) • Outsourced text transcription or correction costs USD $0.35 to $1.20 per 1000 characters: Assume $0.50 per 1000 characters
  79. 79. $ Economics $ 578,000 lines x 40 characters per line x 1/1000 x $0.50 = $11,560 $ 68,908,757 lines x 40 characters per line x 1/1000 x $0.50 = $1,378,175
  80. 80. $ Economics Financial value of in-house OCR text correction? The Assumptions • Correction takes 15 seconds per line • Cost is hourly wage plus benefits of lowest level employee, $10 for CDNC, $41.88* for Australia AUD $40.38 = USD $41.88 is the actual labor value assumed by the National Library of Australia to calculate avoided costs due to crowdsourced OCR text correction in its 2012 Trove Status Report.
  81. 81. $ Economics $ 578,000 lines x 15 seconds per line x 1/3600 hrs per second x $10.00 per hr = $24,083 $ 68,908,757 lines x 15 seconds per line x 1/3600 hrs per second x $41.88 per hr = $12,024,578
  82. 82. Crowdsourcing other benefits Public domain photo “A useful instruction for young sailors from the Royal Hospital School, Greenwich” from the National Maritime Museum.
  83. 83. “when someone transcribes a document, they are actually better fulfilling the mission of a cultural heritage organization than someone who simply stops by to flip through the pages” Other benefit Paraphrased from Trevor Owen’s blog http://www.trevorowens.org/2012/03/ crowdsourcing-cultural-heritage-the-objectives-are-upside-down/ (accessed June 2013).
  84. 84. “in addition to increasing search accuracy or lowering the costs of document transcription, crowdsourcing is the single greatest advancement in getting people using and interacting with library collections” Other benefit Paraphrased from Trevor Owen’s blog http://www.trevorowens.org/2012/03/ crowdsourcing-cultural-heritage-the-objectives-are-upside-down/ (accessed June 2013).
  85. 85. Crowdsourcing considerations • How to market / advertise crowdsourcing? • How to motivate crowdsourcers? • Is authentication / identity of crowdsourcers an issue? • How to administer crowdsourced data? Photo of Aleister Crowley [Public domain] from Wikimedia Commons
  86. 86. Conclusions Conclusion of the Sonata for piano #32, opus 111 by Ludwig van Beethoven • Lots of crowdsourcing in cultural heritage organizations and elsewhere • Benefits are multi-faceted: Economic, data accuracy, patron engagement, increased web traffic
  87. 87. Resources Public domain photo “A useful instruction for young sailors from the Royal Hospital School, Greenwich” from the National Maritime Museum.
  88. 88. Comprehensive worldwide list of online newspaper archives Wikipedia contributors, "List of online newspaper archives," Wikipedia, The Free Encyclopedia, https:// en.wikipedia.org/wiki/Wikipedia:List_of_online_newspaper_archives (accessed March 17, 2013).
  89. 89. Search many digital newspaper collections at once! As of June 2013 elephind (http://www.elephind.com) has indexed 1,032 newspapers from 13 historical digital collections comprising 1,097,928 issues and 45,243,443 pages/articles.
  90. 90. Correct California newspapers at http://cdnc.ucr.edu Correct Cambridge MA newspapers http://bit.ly/cambridgepublic Correct Australian newspapers http://trove.nla.gov.au Correct Tennessee newspapers http://tndp.lib.utk.edu Correct Virginia newspapers http://virginiachronicle.com Try crowdsourcing!
  91. 91. Hãy thử crowdsourcing! Or try Russian language periodicals http://bit.ly/russianperiodicals Correct Vietnamese newspapers http://bit.ly/nationallibraryofvietnam Попробуйте краудсорсинга!
  92. 92. Other resources Mapping Texts at http://mappingtexts.stanford.edu/ Wragge Labs at http://wraggelabs.com/ Wikipedia list of crowdsourcing projects https://en.wikipedia.org/wiki/ List_of_crowdsourcing_projects
  93. 93. ?Brian Geiger bgeiger@ucr.edu Frederick Zarndt frederick@frederickzarndt.com Photo held by John Oxley Library, State Library of Queensland. Original from Courier-mail, Brisbane, Queensland, Australia.
  1. A particular slide catching your eye?

    Clipping is a handy way to collect important slides you want to go back to later.

×