Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.

Envisioning a discussion dashboard for collective intelligence of web conversations -cscw2012-collective-intelligence

1,528 views

Published on

Can we use Walton's discussion types to provide context for discussions?

Presentation for a CSCW2012 workshop on Collective Intelligence as Community Discourse and Action, focusing on the *why* of discussions, and detecting that with textmining.

See the position paper, Envisioning A Discussion Dashboard for Collective Intelligence of Web Conversations, at
http://events.kmi.open.ac.uk/cscw-ci2012/wp-content/uploads/2012/02/SchneiderPassant-cscw12-w33.pdf

Published in: Technology, Health & Medicine

Envisioning a discussion dashboard for collective intelligence of web conversations -cscw2012-collective-intelligence

  1. 1. Digital Enterprise Research Institute www.deri.ie Envisioning a Discussion Dashboard for Collective Intelligence of Web Conversations Jodi Schneider and Alexandre Passant Collective Intelligence as Community Discourse and Action at CSCW 2012 2012-02-11 Seattle, Washington© Copyright 2010 Digital Enterprise Research Institute. All rights reserved.
  2. 2. Discussions are ubiquitous…Digital Enterprise Research Institute www.deri.ie 2
  3. 3. Discussions are ubiquitous…Digital Enterprise Research Institute www.deri.ie 3
  4. 4. Discussions are ubiquitous…Digital Enterprise Research Institute www.deri.ie 4
  5. 5. ChallengesDigital Enterprise Research Institute www.deri.ie n Discussion isn’t limited to a single platform, discussion space, or argumentation tool. n How do we identify & summarize disagreement on the Web? n Can we highlight the points of contention? Minority opinions? 5
  6. 6. Dashboard goalsDigital Enterprise Research Institute www.deri.ie  Orient readers to discussions.  Spot juicy/tough parts automatically.  Provide a framework for integrating with manual tools for analysis & sensemaking. 6
  7. 7. 5W’s – a simple, familiar modelDigital Enterprise Research Institute www.deri.ie  Who  What  When  Where  Why 7
  8. 8. Two Persuasive MessagesDigital Enterprise Research Institute www.deri.ie 8
  9. 9. Why: Walton’s dialogue typesDigital Enterprise Research Institute www.deri.ie 9
  10. 10. Knowledge-based Claims VaryDigital Enterprise Research Institute www.deri.ie  Use of statistics & impersonal information 10
  11. 11. Versus personal appeals…Digital Enterprise Research Institute www.deri.ie  Where opinions and personal values are explicit 11
  12. 12. Why: Knowledge, Emotion, Valuesas a ProxyDigital Enterprise Research Institute www.deri.ie 12
  13. 13. Purpose-related keywordsDigital Enterprise Research Institute www.deri.ie  Knowledge  statistics  Values  truth  secret  Rhetoric  you can thank  Judgment/Opinion  eradicate  tough  rejecting 13
  14. 14. Purpose mattersDigital Enterprise Research Institute www.deri.ie  Knowledge-oriented discussions are straightforward to reuse  Opinion-oriented discussion types may require caveating or balancing  emotion makes a discussion more interesting  can also indicate the potential for bias. 14
  15. 15. Thanks!Digital Enterprise Research Institute www.deri.ie jodi.schneider@deri.org http://jodischneider.com/jodi.html @jschneider
  16. 16. AcknowledgmentsDigital Enterprise Research Institute www.deri.ie  Thanks to our collaborators!  Katie Atkinson, Trevor Bench-Capon, Adam Wyner (Liverpool)  DERI Social Software Unit  Rhetorical Structure, W3C Health Care and Life Sciences  Funding  Science Foundation Ireland Grant No. SFI/08/CE/I1380 (Líon-2)  Short-term scientific mission (STSM 1868) from the COST Action ICO801 on Agreement Technologies 16
  17. 17. Digital Enterprise Research Institute www.deri.ie 17
  18. 18. WhoDigital Enterprise Research Institute www.deri.ie  Reply networks  Demographic statistics  Organization, affiliation, … 18
  19. 19. WhoDigital Enterprise Research Institute www.deri.ie 19
  20. 20. 20
  21. 21. WhatDigital Enterprise Research Institute www.deri.ie  Hashtags  Topic drift & variation  Word frequency 21
  22. 22. WhenDigital Enterprise Research Institute www.deri.ie  Message order  Out of date  Superceded  ‘First mover advantage’  ‘Last word’  Timelines  Depth of the reply network  Tends to indicate what has been most heavily discussed 22
  23. 23. WhereDigital Enterprise Research Institute www.deri.ie  Geographic information  Assumed viewpoints  Likely biases  Genre and source  How big are individual messages?  Do they stand on their own? Require reply context?  How fast does the conversation move? 23
  24. 24. Genre & source mattersDigital Enterprise Research Institute www.deri.ie 24
  25. 25. Context to combine these?Digital Enterprise Research Institute www.deri.ie 25
  26. 26. Digital Enterprise Research Institute www.deri.ie  What are the turning points in a discussion?  Which viewpoints have diverse support?  What justifications are given for viewpoints? 26
  27. 27. WhyDigital Enterprise Research Institute www.deri.ie 27
  28. 28. Standpoints WebDigital Enterprise Research Institute www.deri.ie 28
  29. 29. Standpoints WebDigital Enterprise Research Institute www.deri.ie 29
  30. 30. Transform Debates into Argument FrameworksDigital Enterprise Research Institute www.deri.ie (1) Households should pay tax for their garbage. (4) (1) Paying tax for garbage increases recycling, so households should Arrow: premise pay. (3) (1) Wyner, van Engers, & Bahreini. Recycling more is good, so people From Policy-making Statements to First-order Logic. should pay tax for their garbage. EGOV 2010 30
  31. 31. Calculate best options (non-contradictory opinions)Digital Enterprise Research Institute www.deri.ie Wyner, van Engers, & Bahreini. From Policy-making Statements to First-order Logic. EGOV 2010 31

×