envisioning a discussion dashboard for collective intelligence of web conversations...

Post on 11-May-2015

1.025 Views

Category:

Technology

0 Downloads

Preview:

Click to see full reader

DESCRIPTION

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

TRANSCRIPT

Copyright 2010 Digital Enterprise Research Institute. All rights reserved.

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 20122012-02-11Seattle, Washington

Digital Enterprise Research Institute

www.deri.ie

Discussions are ubiquitous…

2

Digital Enterprise Research Institute

www.deri.ie

Discussions are ubiquitous…

3

Digital Enterprise Research Institute

www.deri.ie

Discussions are ubiquitous…

4

Digital Enterprise Research Institute

www.deri.ie

Challenges

1. Discussion isn’t limited to a single platform, discussion space, or argumentation tool.

2. How do we identify & summarize disagreement on the Web?

3. Can we highlight the points of contention? Minority opinions?

5

Digital Enterprise Research Institute

www.deri.ie

Dashboard goals

Orient readers to discussions. Spot juicy/tough parts automatically. Provide a framework for integrating with

manual tools for analysis & sensemaking.

6

Digital Enterprise Research Institute

www.deri.ie

5W’s – a simple, familiar model

Who What When Where Why

7

Digital Enterprise Research Institute

www.deri.ie

Two Persuasive Messages

8

Digital Enterprise Research Institute

www.deri.ie

Why: Walton’s dialogue types

9

Digital Enterprise Research Institute

www.deri.ie

Knowledge-based Claims Vary

Use of statistics & impersonal information

10

Digital Enterprise Research Institute

www.deri.ie

Versus personal appeals…

Where opinions and personal values are explicit

11

Digital Enterprise Research Institute

www.deri.ie

Why: Knowledge, Emotion, Values as a Proxy

12

Digital Enterprise Research Institute

www.deri.ie

Purpose-related keywords

Knowledge statistics

Values truth secret

Rhetoric you can thank

Judgment/Opinion eradicate tough rejecting

13

Digital Enterprise Research Institute

www.deri.ie

Purpose matters

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

Digital Enterprise Research Institute

www.deri.ie

Thanks!

jodi.schneider@deri.orghttp://jodischneider.com/jodi.html@jschneider

Digital Enterprise Research Institute

www.deri.ie

Acknowledgments

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

Digital Enterprise Research Institute

www.deri.ie

17

Digital Enterprise Research Institute

www.deri.ie

Who

Reply networks Demographic statistics Organization, affiliation, …

18

Digital Enterprise Research Institute

www.deri.ie

Who

19

20

Digital Enterprise Research Institute

www.deri.ie

What

Hashtags Topic drift & variation

Word frequency

21

Digital Enterprise Research Institute

www.deri.ie

When

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

Digital Enterprise Research Institute

www.deri.ie

Where

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

Digital Enterprise Research Institute

www.deri.ie

Genre & source matters

24

Digital Enterprise Research Institute

www.deri.ie

Context to combine these?

25

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

Digital Enterprise Research Institute

www.deri.ie

Why

27

Digital Enterprise Research Institute

www.deri.ie

Standpoints Web

28

Digital Enterprise Research Institute

www.deri.ie

Standpoints Web

29

Digital Enterprise Research Institute

www.deri.ie

Transform Debates into Argument Frameworks

(1) Households should pay tax for their garbage.

(4) (1) Paying tax for garbage increases recycling, so households should pay.

(3) (1)Recycling more is good, so people should pay tax for their garbage.

30

Arrow: premise

Wyner, van Engers, & Bahreini. From Policy-making Statements to First-order Logic. EGOV 2010

Digital Enterprise Research Institute

www.deri.ie

Calculate best options (non-contradictory opinions)

31

Wyner, van Engers, & Bahreini. From Policy-making Statements to First-order Logic.

EGOV 2010

top related