This document summarizes a paper on semi-automated argumentation analysis of online product reviews. The paper describes extracting argument fragments from reviews, evaluating them using formal tools, and providing semi-automated support to speed up analysts' work. The goal is to extract distributed arguments across corpora and instantiate argumentation schemes to identify pros, cons, and relationships between arguments.
What's New in Teams Calling, Meetings and Devices March 2024
Semi-automated argumentation analysis of online product reviews--COMMA 2012-09-11
1. Semi-Automated Argumentation
Analysis of Online Product Reviews
Adam Wyner1, Jodi Schneider2, Katie Atkinson1,
and Trevor Bench-Capon1
1 - Department of Computer Science, University of Liverpool
2 – Digital Enterprise Research Institute, National University of Ireland
September 11, 2012
COMMA 2012
Vienna University of Technology
5. Output extensions
Preferred Extension (using ASPARTIX)
September 11, 2012 Wyner et al., COMMA 2012 5
6. Goals
• Extract arguments distributed across a corpora and
evaluate them with formal, automated tools.
• Speed the work of human analysts.
• Provide semi-automatic support.
• Use aspects of NLP to incrementally address a range
of problems (ambiguity, structure, contrasts,....)
September 11, 2012 Wyner et al., COMMA 2012 6
7. Consumer argumentation scheme
Variables in schemes as targets for extraction.
Premises:
• Camera X has property P.
• Property P promotes value V for agent A.
Conclusion:
• Agent A should Action Camera X.
September 11, 2012 Wyner et al., COMMA 2012 7
8. Analyst’s goal: instantiate
Premises:
• The Canon SX220 has good video quality.
• Good video quality promotes image quality for
casual photographers.
Conclusion:
• Casual photographers should buy the Canon SX220.
September 11, 2012 Wyner et al., COMMA 2012 8
9. Identifying and extracting text
• Annotate text:
– Simple or complex annotations.
– Highlight annotations with
– Search for and extract text by annotation.
• GATE “General Architecture for Text Engineering”.
– Works with large corpora of text.
– Rule-based or machine-learning approaches.
September 11, 2012 Wyner et al., COMMA 2012 9
10. To find argument passages
• Use:
– Indicators of
after, as, because, for, since, when, ....
– Indicators of
therefore, in conclusion, consequently, ....
September 11, 2012 Wyner et al., COMMA 2012 10
12. To find what is being discussed
• Use :
– Has a flash
– Number of megapixels
– Scope of the zoom
– Lens size
– The warranty
September 11, 2012 Wyner et al., COMMA 2012 12
14. To find attacks between arguments
• Use contrast terminology:
– Indicators
but, except, not, never, no, ....
– Sentiment
The flash worked .
The flash worked .
September 11, 2012 Wyner et al., COMMA 2012 14
18. An argument for buying the camera
Premises:
The pictures are perfectly exposed.
The pictures are well-focused.
No camera shake.
Good video quality.
Each of these properties promotes image quality.
Conclusion:
(You, the reader,) should buy the CanonSX220.
September 11, 2012 Wyner et al., COMMA 2012 18
19. An argument for NOT buying the
camera
Premises:
The colour is poor when using the flash.
The images are not crisp when using the flash.
The flash causes a shadow.
Each of these properties demotes image quality.
Conclusion:
(You, the reader,) should not buy the CanonSX220.
September 11, 2012 Wyner et al., COMMA 2012 19
20. Counterarguments to the premises of
“Don’t buy”
The colour is poor when using the flash.
For good colour, use the colour setting, not the flash.
The images are not crisp when using the flash.
No need to use flash even in low light.
The flash causes a shadow.
There is a corrective video about the flash shadow.
September 11, 2012 Wyner et al., COMMA 2012 20
21. Future work
• Tool refinement.
• Add ontology modules to the tool.
• User models.
• Richer query patterns.
• More extensive argument 'chains'.
• Incrementally analyse ambiguity, e.g. when, because,....
• Argumentation schemes for other aspects of text.
• Further work on contrariness.
September 11, 2012 Wyner et al., COMMA 2012 21
22. Related Papers
• Schneider, Davis, and Wyner (2012). ''Dimensions of
argumentation in social media'', Knowledge Engineering and
Knowledge Management (EKAW).
• Wyner and Schneider (2012). ''Arguing from a point of
view'', Agreement Technologies.
• Schneider and Wyner (2012). ''Identifying consumers'
arguments in text'', Workshop on Semantic Web and
Information Extraction (SWAIE at EKAW).
September 11, 2012 Wyner et al., COMMA 2012 22
23. Acknowledgements
• FP7-ICT-2009-4 Programme, IMPACT Project, Grant
Agreement Number 247228.
• Science Foundation Ireland Grant No. SFI/08/CE/I1380 (Líon-
2)
• Short-term Scientific Mission grant from COST Action IC0801
on Agreement Technologies
September 11, 2012 Wyner et al., COMMA 2012 23
24. Thanks for your attention!
• Questions?
• Contacts:
– Adam Wyner adam@wyner.info
– Jodi Schneider jschneider@pobox.com
September 11, 2012 Wyner et al., COMMA 2012 24
Notas del editor
Tuesday, September 11, 2012
Why is opinion or sentiment analysis **not** sufficient? Because:It provides no explanation or justification for the opinion, broadly construed.We can count the numbers of participants who hold an opinion, but one well-made 'counter-argument' may lead individuals to retract their opinion.Knowledge in the text is implicitly structured and many-layered. How can we extract that structured information?
Colors represent annotations in the text. We can then search for a large body of text
Screenshot from GATE, in which we have built components of a toolPurple: conclusionOrange: premiseLots of ambiguity – different meanings of the words*DOES* draw attention to relevant places. Can turn on & off particular things that we’re looking for. Helps with the search problem.
binary values (such as has a flash), properties with ranges (such as the number of megapixels, scope of the zoom, or lens size), and multi-slotted properties (e.g. the warranty).
Drawn from vast lists of terminology, given sentiment valence: positive vs. negative +5 to 0 to -5Can look for various levels or homogenize – this is homogenized
Leave camera implicit in the examples for brevity.
We have an argument for buying the camera, an argument for not buying the camera. They rebut each other.We have attacks on the premises for “don’t buy the camera”. The argument for not buying the camera is defeated; the argument for buying the camera stands. So you should buy the camera.