• DocumentCode
    1146563
  • Title

    Finding the WRITE stuff: automatic identification of discourse structure in student essays

  • Author

    Burstein, Jill ; Marcu, Daniel ; Knight, Kevin

  • Author_Institution
    ETS Technol., Princeton, NJ, USA
  • Volume
    18
  • Issue
    1
  • fYear
    2003
  • Firstpage
    32
  • Lastpage
    39
  • Abstract
    An essay-based discourse analysis system can help students improve their writing by identifying relevant essay-based discourse elements in their essays. Our discourse analysis software, which is embedded in Criterion, an online essay evaluation application, uses machine learning to identify discourse elements in student essays. The system makes decisions that exemplify how teachers perform this task. For instance, when grading student essays, teachers comment on the discourse structure. Teachers might explicitly state that the essay lacks a thesis statement or that an essay´s single main idea has insufficient support. Training the systems to model this behavior requires human judges to annotate a data sample of student essays. The annotation schema reflects the highly structured discourse of genres such as persuasive writing. Our discourse analysis system uses a voting algorithm that takes into account the discourse labeling decisions of three independent systems.
  • Keywords
    intelligent tutoring systems; learning (artificial intelligence); linguistics; natural languages; Criterion; annotation schema; essay-based discourse analysis system; intelligent tutor; machine learning; online essay evaluation application; student essays; voting algorithm; writing; Algorithm design and analysis; Application software; Feedback; Humans; Large-scale systems; Machine learning; Protocols; Testing; Voting; Writing;
  • fLanguage
    English
  • Journal_Title
    Intelligent Systems, IEEE
  • Publisher
    ieee
  • ISSN
    1541-1672
  • Type

    jour

  • DOI
    10.1109/MIS.2003.1179191
  • Filename
    1179191