Welcome to the CSCL2009 dialog blog!

It is our great pleasure to welcome you on the CSCL2009 pre-conference dialogue blog!

The purpose of the blog is to facilitate the dialogue between the authors and other participants of the conference, before, during and after CSCL 2009 conference. There is a post –containing the abstract along with a link to the full text- for every paper that will be presented at the conference. You can view the abstract of a paper, read the full text, post your comments and/or questions, exchange ideas…

Tags associated with the types of the papers have been assigned to the relative posts so that you have the choice of filtering the content you want to read. Just click on a tag and all posts concerning the papers of the corresponding category will be displayed on the main blog’s page. You can then scroll through the posts of this certain category until you find the one(s) you are interested in. All tags are displayed in the tags block on the right column of the blog’s page.

The meanings of the tags are described here below:

(a) Regarding the paper category:

  • ΑF (full papers)
  • AFI (full papers that will be presented in interactive format)
  • API (short papers that will be presented in interactive format)
  • AS (short papers)
  • ASP (posters)

(b) Regarding award nominees:

  • BPN (Best Paper Nominee)
  • BSPN (Best Student Paper Nominee)
  • BTDN (Best Technology Design Nominee)

(c) Regarding the conference sessions:

  • PS_1: Analyzing Group Cognition in CSCL Practises
  • PS_2: Scripts & Scaffolds
  • PS_3: Argumentation & Problem Based Learning
  • PS_4: Tabletops and tangibles
  • PS_5: Teacher Professional Development & Communities of Practice
  • PS_6: Discussion & Conflict Resolution
  • PS_7: Approaches to Analyzing Interaction
  • PS_8: Games and Simulations
  • PS_9: Evaluating Computer-Mediated Learning
  • PS_10: Knowledge Building & Virtual Learning Environments
  • PS_11: Science Education & Problem Based Learning
  • PS_12: Learning Processes & Games
  • PS_13: Handhelds & mCSCL
  • PS_14: Scripts & Adaptation
  • PS_15: Mathematics & Science Education
  • PS_16: Case studies in Higher Education
  • PS_17: Data Mining and Process Analysis
  • PS_18: Shared displays & workspaces
  • PS_19: Social Software/wikis
  • PS_20: Professional Development
  • PS_21: : Peer Awareness for Assessment, Coaching & Coordination
  • PS_22: Web 2.0, Wikis & Knowledge building
  • PS_23: Awareness & Self regulation
  • PS_24: Knowledge Construction & Gaming Practices

Alternatively, you could also search for a paper arbitrarily, by entering a part of its title, or the author/s name in the search box provided at the top of the blog’s page.

Posting of comments is allowed for registered users only. You will therefore be prompted to give an e-mail address each time you post a comment.

Use RSS or Atom Syndication to get the newer comments immediately for the full blog, or a specific tag, or a specific post-paper :

Comments-only feed

Atom 1.0: http://cscl2009.blogspot.com/feeds/comments/default

RSS 2.0: http://cscl2009.blogspot.com/feeds/comments/default?alt=rss

Label-specific site feed:

Atom 1.0: http://cscl2009.blogspot.com/posts/comments/default/-/labelname
RSS 2.0: http://cscl2009.blogspot.com/feeds/posts/default?alt=rss/-/labelname


Individual post comment feed:

Atom 1.0: http://cscl2009.blogspot.com/feeds/postId/comments/default
RSS 2.0: http://cscl2009.blogspot.com/feeds/postId/comments/default?alt=rss

Hoping you will enjoy the blog …




    Collaboration and abstract representations: towards predictive models based on raw speech and eye-tracking data

    • Marc-Antoine Nüssli , Ecole Polytechnique Fédérale de Lausanne
    • Patrick Jermann , Ecole Polytechnique Fédérale de Lausanne
    • Mirweis Sangin , Ecole Polytechnique Fédérale de Lausanne
    • Pierre Dillenbourg , Ecole Polytechnique Fédérale de Lausanne
    This study aims to explore the possibility of using machine learning techniques to build predictive models of performance in collaborative induction tasks. More specifically, we explored how signal-level data, like eye-gaze data and raw speech may be used to build such models. The results show that such low level features have effectively some potential to predict performance in such tasks. Implications for future applications design are shortly discussed.
    Full text in PDF

    No comments:

    Post a Comment