The Community for Technology Leaders
Green Image
Issue No. 01 - January/February (2003 vol. 18)
ISSN: 1541-1672
pp: 32-39
Kevin Knight , Information Sciences Institute, University of Southern California
Daniel Marcu , Information Sciences Institute, University of Southern California
Jill Burstein , ETS Technologies
<p>Automated essay-scoring applications are widely used from the elementary-school through university levels for large-scale assessment and classroom instruction. This goes hand in hand with the increase of essay writing on standardized tests. Writing teachers show growing excitement about the innovative automated-essay-evaluation software that helps students improve their writing. Integration of this software into the curriculum is also consistent with the drive toward individualized assessment and instruction. One kind of application developed for this purpose is an essay-based discourse analysis system. This software shows students the presence and absence of relevant essay-based discourse elements in their essays, including introductory material, thesis statements, main ideas, supporting ideas, and conclusions. This commercial software tool uses a voting algorithm based on decisions from three independent discourse analysis systems. The tool automatically labels discourse elements in student essays written on any topic, and across writing genres. This discourse analysis application is embedded in a larger application, Criterion writing analysis tools, and is a critical complement to other tools that provide feedback related to grammar, usage, mechanics, and style features in student essays.</p>
discourse analysis, discourse annotation, machine learning, text classification, automated essay evaluation, educational technology
Kevin Knight, Daniel Marcu, Jill Burstein, "Finding the WRITE Stuff: Automatic Identification of Discourse Structure in Student Essays", IEEE Intelligent Systems, vol. 18, no. , pp. 32-39, January/February 2003, doi:10.1109/MIS.2003.1179191
94 ms
(Ver 3.3 (11022016))