Why did they post that argument? Communicative intentions of web 2-0 arguments SINTELNET-arguing on the web 2-0-at-ISSA--2014-06-30

  • 189 views
Uploaded on

Paper here: …

Paper here:
http://jodischneider.com/pubs/issaargweb2014.pdf

Talk for Arguing on the Web 2.0, SINTELNET workshop collocated with the 8th ISSA Conference on Argumentation, Amsterdam, June 30, 2014
http://www.sintelnet.eu/content/arguing-web-20-0

Jodi Schneider, Serena Villata, Elena Cabrio.
"Why did they post that argument? Communicative intentions of Web 2.0 arguments."

More in: Technology
  • Full Name Full Name Comment goes here.
    Are you sure you want to
    Your message goes here
    Be the first to comment
    Be the first to like this
No Downloads

Views

Total Views
189
On Slideshare
0
From Embeds
0
Number of Embeds
2

Actions

Shares
Downloads
0
Comments
0
Likes
0

Embeds 0

No embeds

Report content

Flagged as inappropriate Flag as inappropriate
Flag as inappropriate

Select your reason for flagging this presentation as inappropriate.

Cancel
    No notes for slide
  • http://www.sintelnet.eu/content/arguing-web-20-0

    15:50-16:10: 15 min + 5 min for questions

    Full paper online at:
    http://jodischneider.com/pubs/issaargweb2014.pdf

    Abstract:
    The Web is an open platform where users are free to publish their own opinions, to discuss the latest news, to write reviews about a service or product. Given the growing number of online platforms allowing such interactions, it is becoming more and more important to support users in understanding the meaning of such conversations by identifying the context of the discourse, and the evidence and background knowledge required to evaluate the proposed arguments. In this paper, we suggest recording the rough context with communicative intentions to help classify arguments on the Web. We describe five communicative intentions: recreation, information, instruction, discussion, and recommendation. We suggest that this classification can help identify and analyze messages for the Argument Web. In particular, we discuss the suitable combinations of natural language processing techniques and argumentation-based reasoning to support users in understanding the discussions.
  • seeks
    “to encourage debate,
    to facilitate good argument, and
    to promote a new online critical literacy”


  • Every day billions of people add texts, photos, and videos on a wide range of topics like potholes, Rihanna’s fashion choices, and the Ukraine crisis. Some of these messages argue a point of view.
  • Every day billions of people add texts, photos, and videos on a wide range of topics like potholes, Rihanna’s fashion choices, and the Ukraine crisis. Some of these messages argue a point of view.
  • Reviewing our examples (Figure 1 and Figure 2) against this typology, they do not fit: they are not persuasion, negotiation, deliberation, information-seeking, inquiry, discovery, or eristic dialogues. There is no appropriate positioning within these choices. Figure 1 is a humorous argument concluding that chocolate is salad.
  • Reviewing our examples (Figure 1 and Figure 2) against this typology, they do not fit: they are not persuasion, negotiation, deliberation, information-seeking, inquiry, discovery, or eristic dialogues. There is no appropriate positioning within these choices. Figure 1 is a humorous argument concluding that chocolate is salad.
  • purely informational message that conveys an argument from a scientific study.
  • And anyway, social media is someplace between writing and talking – monologue and dialogue
  • Reviewing our examples (Figure 1 and Figure 2) against this typology, they do not fit: they are not persuasion, negotiation, deliberation, information-seeking, inquiry, discovery, or eristic dialogues. There is no appropriate positioning within these choices. Figure 1 is a humorous argument concluding that chocolate is salad.
  • purely informational message that conveys an argument from a scientific study.
  • In future work we plan to test whether communicative intention impacts the choice of natural language processing algorithms. We expect that considering the communicative intention will make it easier to accurately identify and reconstruct arguments with natural language processing.

    Further, we will test whether other aspects of messages should be taken into consideration for the Argument Web. Herring suggested that the best way to handle the fast-changing pace of computer-mediated communication was use a faceted classification [9]. Communicative intention, form, and dialogue type are among the relevant facets for argumentation in social media, but further study is needed to develop a full faceted genre description of social media appropriate for the Argument Web.

Transcript

  • 1. Jodi Schneider, Serena Villata, and Elena Cabrio INRIA, France Arguing on the Web 2.0, collocated with ISSA 2014 University of Amsterdam 2014-06-30
  • 2. Encourage debate Facilitate good argument Promote online critical literacy
  • 3. "A MESSAGE ON THE WEB"
  • 4. NOT ALL MESSAGES ARE THE SAME
  • 5. Comparing our 2 messages Similarities • Platform (Twitter) • Length • Use symbols • Attention from others – Marked as a favorite – Retweeted Differences • Topics • Authors • Whether they use hashtags • Whether they have replies • Communicative Intent
  • 6. Comparing our 2 messages Similarities • Platform (Twitter) • Length • Use symbols • Attention from others – Marked as a favorite – Retweeted Differences • Topics • Authors • Whether they use hashtags • Whether they have replies • Communicative Intent
  • 7. Walton/Krabbe typology of dialogue Initial Situation Participant's goal Goal of dialogue Type of dialogue Conflict of opinion Persuade other Resolve or clarify issue Persuasion Conflict of interests Get what want Reasonable settlement Negotiation Dilemma or practical choice Coordinate goals & actions Decide course of action Deliberation Need information Acquire or give info Exchange information Information-seeking Find & verify evidence Prove/disprove hypothesis Proof Inquiry Explain facts Find and defend hypothesis Choose hypothesis for testing Discovery Personal conflict Verbally hit out at opponent Reveal deeper basis of conflict Eristic Based on Walton COMMA 2010; see also Walton & Krabbe 1995.
  • 8. Humorous
  • 9. Informational: reporting an argument from a scientific study
  • 10. These do not fit the typology we have • Persuasion • Negotiation • Deliberation • Information-seeking • Inquiry • Discovery • Eristic dialogue
  • 11. Communicative Intentions for Web texts • Recreation • Information • Instruction • Discussion • Recommendation Sharoff 2011. In the garden and in the jungle. In Genres on the Web (Springer)
  • 12. Recreation
  • 13. Information
  • 14. Instruction
  • 15. Discussion
  • 16. Recommendation
  • 17. Processing communicative intention • Recreation slang, metaphors, puns – Named entity recognition and normalization of texts • Information news-like, scientific discussions – Recognizing textual entailment, opinion mining • Instruction informational messages – Question-answering, question interpretation • Discussion everyday language – Discourse analysis, recognizing textual entailment • Recommendation persuasive intent – Sentiment analysis
  • 18. Processing communicative intention • Recreation slang, metaphors, puns – Named entity recognition and normalization of texts • Information news-like, scientific discussions – Recognizing textual entailment, opinion mining • Instruction informational messages – Question-answering, question interpretation • Discussion everyday language – Discourse analysis, recognizing textual entailment • Recommendation persuasive intent – Sentiment analysis
  • 19. Processing communicative intention • Recreation slang, metaphors, puns – Named entity recognition and normalization of texts • Information news-like, scientific discussions – Recognizing textual entailment, opinion mining • Instruction informational messages – Question-answering, question interpretation • Discussion everyday language – Discourse analysis, recognizing textual entailment • Recommendation persuasive intent – Sentiment analysis
  • 20. Processing communicative intention • Recreation slang, metaphors, puns – Named entity recognition and normalization of texts • Information news-like, scientific discussions – Recognizing textual entailment, opinion mining • Instruction informational messages – Question-answering, question interpretation • Discussion everyday language – Discourse analysis, recognizing textual entailment • Recommendation persuasive intent – Sentiment analysis
  • 21. Processing communicative intention • Recreation slang, metaphors, puns – Named entity recognition and normalization of texts • Information news-like, scientific discussions – Recognizing textual entailment, opinion mining • Instruction informational messages – Question-answering, question interpretation • Discussion everyday language – Discourse analysis, recognizing textual entailment • Recommendation persuasive intent – Sentiment analysis
  • 22. Future work • Use Communicative Intentions to focus NLP • Identify aspects of messages to consider for the Argument Web: – Communicative intention – Form/platform – Dialogue type – … • Define challenge tasks for the Argument Web: – application areas, corpora, …