A reading group presentation about Turning social disputes into knowledge representations, based primarily on two papers:
Toni and Torroni. Bottom-up Argumentation. In: First International Workshop on the Theory and Applications of Formal Argumentation 2011 (TAFA), 16-22 July, 2011, Barcelona, Spain. http://www.doc.ic.ac.uk/~ft/PAPERS/tafaPT.pdf
Benn, Buckingham Shum, Domingue, and Mancini. Ontological Foundations for Scholarly Debate Mapping Technology. In: 2nd International Conference on Computational Models of Argument (COMMA '08), 28-30 May, 2008, Toulouse, France. http://oro.open.ac.uk/11939/
Human Factors of XR: Using Human Factors to Design XR Systems
Turning social disputes into knowledge representations DERI reading group 2012-03-28
1. Digital Enterprise Research Institute www.deri.ie
Turning social disputes into
knowledge representations
Jodi Schneider
DERI Reading Group, Galway, Ireland Wednesday 28th March 2012
Copyright 2011 Digital Enterprise Research Institute. All rights reserved.
Enabling Networked Knowledge
2. What can we learn from opinions
and social media discussions?
Digital Enterprise Research Institute www.deri.ie
Enabling Networked Knowledge
3. Digital Enterprise Research Institute www.deri.ie
Toni and Torroni. Bottom-up Argumentation. In: First
International Workshop on the Theory and Applications
of Formal Argumentation 2011 (TAFA), 16-22 July, 2011,
Barcelona, Spain.
http://www.doc.ic.ac.uk/~ft/PAPERS/tafaPT.pdf
Benn, Buckingham Shum, Domingue, and Mancini.
Ontological Foundations for Scholarly Debate Mapping
Technology. In: 2nd International Conference on
Computational Models of Argument (COMMA '08), 28-30
May, 2008, Toulouse, France.
http://oro.open.ac.uk/11939/
Enabling Networked Knowledge
3
4. From a Facebook thread to logic
Digital Enterprise Research Institute www.deri.ie
Enabling Networked Knowledge
6. Can we make sense of it?
Digital Enterprise Research Institute www.deri.ie
Enabling Networked Knowledge
7. Discussion features
Digital Enterprise Research Institute www.deri.ie
Purpose and specific focus are not clear.
Can extract and recognize arguments.
Arguments emerge, bottom-up.
Enabling Networked Knowledge
8. Parts of the discussion
Digital Enterprise Research Institute www.deri.ie
Comment
Opinion
Links relationships between Comments & Opinions
Enabling Networked Knowledge
9. Comment
“This is what my kitchen tap used to look like…”
Opinion
“Separate taps are common in GB”
Links
“This is what my kitchen tap used to look like…”
supports “Separate taps are common in GB”
10. Comment
“This is what my kitchen tap used to look like…”
Opinion
“Separate taps are common in GB”
Links
“This is what my kitchen tap used to look like…”
supports “Separate taps are common in GB”
11. Comment
“This is what my kitchen tap used to look like…”
Opinion
“Separate taps are common in GB”
Links
“This is what my kitchen tap used to look like…”
supports “Separate taps are common in GB”
12. Comment
“This is what my kitchen tap used to look like…”
Opinion
“Separate taps are common in GB”
Links
“This is what my kitchen tap used to look like…”
supports “Separate taps are common in GB”
14. objectsTo link
Digital Enterprise Research Institute www.deri.ie
Links
“Separate taps are inconvenient because they freeze/ burn hands”
objectsTo “Separate taps are not inconvenient as basin solves
temperature problem”
Enabling Networked Knowledge
15. Logical framework
Digital Enterprise Research Institute www.deri.ie
Assumption-Based Argumentation
basedOn(o3) ← c2, l_3_2
Enabling Networked Knowledge
15
16. Logical framework
Digital Enterprise Research Institute www.deri.ie
Assumption-Based Argumentation
alink(l_4_17,o4,o17)
Enabling Networked Knowledge
16
17. Mapping a debate based
on its Wikipedia article
Digital Enterprise Research Institute www.deri.ie
Enabling Networked Knowledge
18. Extracting scholars’
opinions from Wikipedia
Digital Enterprise Research Institute www.deri.ie
Enabling Networked Knowledge
22. Debate elements
Digital Enterprise Research Institute www.deri.ie
Issue
Is aborting a zygote, embryo, or fetus a violation of human rights?
Proposition
The existence and moral right to life of human organisms begins at
or near conception
Argument
All or almost all abortion should be illegal
Enabling Networked Knowledge
25. Cognitive Coherence Relations
Digital Enterprise Research Institute www.deri.ie
Additive/Causal
Positive/Negative
Semantic/Pragmatic
Basic/Non-Basic
Enabling Networked Knowledge
26. Cognitive Coherence Relations
Digital Enterprise Research Institute www.deri.ie
Additive/Causal
Weak correlation
Strong correlation
Positive/Negative
Pos: “Because he had political experience, he was elected president”
Neg: “He did not have any political experience, yet he was elected”
Semantic/Pragmatic
Factual content
Speech Act – (“Are you warm?” implies “Can I open the window?”)
Basic/Non-Basic
Presentation order
Enabling Networked Knowledge
27. Cognitive Coherence Relations
Digital Enterprise Research Institute www.deri.ie
“Because he had political experience, he was elected
president.”
Causal
Positive
Semantic
Basic order
“He did not have any political experience, yet he was elected
president”
Additive
Negative
Non-basic order
Enabling Networked Knowledge
30. Relationship to my work
Digital Enterprise Research Institute www.deri.ie
Enabling Networked Knowledge
31. What can we do with it?
Digital Enterprise Research Institute www.deri.ie
Enabling Networked Knowledge
31
32. “ELIZA for arguments”
Digital Enterprise Research Institute www.deri.ie
Snaith, Lawrence, & Reed, “Mixed initiative argument in public deliberation,” ODET 2010
Enabling Networked Knowledge
32
33. Highlight Controversies
Digital Enterprise Research Institute www.deri.ie
Ennals, R., Trushkowsky, B., & Agosta, J. M. (2010). Highlighting Disputed
Claims on the Web. In WICOW at WWW 2010.
Enabling Networked Knowledge
34. Transform Debates into
Argument Frameworks
Digital 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 pay. Arrow: premise
(3) (1)
Recycling more is good, so people should van Engers, & Bahreini.
Wyner,
pay tax for their garbage. From Policy-making Statements
to First-order Logic.
EGOV 2010
34 Enabling Networked Knowledge
35. 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
Enabling Networked Knowledge
35
36. How do we make one?
Digital Enterprise Research Institute www.deri.ie
Enabling Networked Knowledge
36
38. Acknowledgments
Digital Enterprise Research Institute www.deri.ie
Thanks to our collaborators!
Katie Atkinson, Trevor Bench-Capon, Adam Wyner (Liverpool)
DERI Social Software Unit
Rhetorical Structure Taskforce, W3C Health Care/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
Upcoming: SFI Travel Supplement
Enabling Networked Knowledge
38
39. Thanks!
Digital Enterprise Research Institute www.deri.ie
jodi.schneider@deri.org
http://jodischneider.com/jodi.html
@jschneider
Enabling Networked Knowledge
Editor's Notes
From http://www.sendareview.com/The Web is full of opinions & commentary.A lot of it disagrees.How do we learn from other people, when they disagree?
==== based on ====Paper title: Ontological Foundations for Scholarly Debate Mapping TechnologyAuthors: Neil Benn, Simon Buckingham Shum, John Domingue, Clara ManciniPublished at: Computational Models of Argument 2008Abstract: Mapping scholarly debates is an important genre of what can be calledKnowledge Domain Analytics (KDA) technology – i.e. technology whichcombines both quantitative and qualitative methods of analysing specialistknowledge domains. However, current KDA technology research has emergedfrom diverse traditions and thus lacks a common conceptual foundation. Thispaper reports on the design of a KDA ontology that aims to provide thisfoundation. The paper then describes the argumentation extensions to theontology for supporting scholarly debate mapping as a special form of KDA anddemonstrates its expressive capabilities using a case study debate.Link: http://oro.open.ac.uk/11939/ANDPaper title: Bottom-Up ArgumentationAuthors: Francesca Toni and Paolo TorroniPublished at: First International Workshop on the Theory and Applications of Formal Argumentation 2011Abstract: Online social platforms, e-commerce sites and technical forasupport the unfolding of informal exchanges, e.g. debates or discussions,that may be topic-driven or serendipitous. We outline a methodology foranalysing these exchanges in computational argumentation terms, thusallowing a formal assessment of the dialectical validity of the positionsdebated in or emerging from the exchanges. Our methodology allowsusers to be engaged in this formal analysis and the assessment, within adynamic process where comments, opinions, objections, as well as linksconnecting them, can all be contributed by users.Link: http://www.doc.ic.ac.uk/~ft/PAPERS/tafaPT.pdf
What are the overall opinions?Is there any “knowledge” or consensus here?How can we analyse the conversation?
It has been often said that the Web 2.0 is a place for grassroots. Actually, this is exactly what happens here. New contributions and ideas are produced and shared in an exquisitely serendipitous, bottom-up approach. In general, debates in the social Web start with no clear purpose. If the one who posts the first comment has a purpose in mind, he or she does not usually state it. Different is the case of structured debates, or polls in which the objective is clear, for instance choosing one among three possible dates for a meeting. Here instead we are looking at chains of pseudo-random posts, like we find in Facebook, in Amazon or at the bottom of an online newspaper’s article. Sometimes such chains of posts converge to some topic, then again they may totally diverge and focus on some other topic. They may happen to never find a focus.Despite these features, we can still abstract away and recognize, within these exchanges, arguments. But, unlike arguments in the computational argumenta- tion literature, these arguments are not structured or relevant to any predefined topic, opinion or goal. They emerge, bottom-up, from the grassroots. From these arguments, a few mainstream opinions may emerge as the result of many com- ments, as if in a sort of “natural selection”.
These coherence parameters are then used as a grammar for defining relations in the merged KDA ontology, including relations between publications, between persons, and between arguments. The benefit of this approach is that rather than implement a multitude of inference rules for inferring positive association, only a limited set of parameterised inference rules need to be implemented. For example, Figure 2(i), which shows a parameterised rule for inferring a +ADDITIVE connection between some Y and some Z, covers typical positive association inferences such as when two arguments support a common third argument or when two publications cite a common third publication. Figure 2(ii), which also shows a parameterised rule, covers typical positive association inferences such as when two persons author a common publication or when two arguments are expressed by a common publication. Finally, Figure 2(iii) covers a typical ‘undercutting’ pattern in argument analysis which is a variation of the social network analysis adage that “the enemy of my enemy is my friend”.
http://jodischneider.com/jodi.html
The Viewpoints Web is my framework for…
Mixed-initiativeGenerate argument maps from conversations (Arvina, MAgtALO)Populate a knowledge baseMaybe change your views
They don’t say how they extracted these – but they say Someone makes statement (1)Someone else gives (4) as a reason/premise for (1)Someone else gives (3) as an additional reason for (1)(2) Is a counterproposal with a range of supporting reasons===Icons:http://findicons.com/icon/27954/girl_5?id=27964#http://findicons.com/icon/27930/boy_8?id=27939#http://findicons.com/icon/27955/girl_4?id=27965#