Summary Street: An Intelligent Tutoring System for Improving Student Writing through the use of Latent Semantic Analysis
David J. Steinhart, Written David J. Steinhart, Walter Kintsch, David J. (ph. D · 2001
Steinhart, David J. (Ph.D., Psychology) Summary Street: An Intelligent Tutoring System for Improving Student Writing through the use of Latent Semantic Analysis Thesis directed by Professor Walter Kintsch This dissertation describes the design, evolution, and testing of Summary Street, an intelligent tutoring system which uses Latent Semantic Analysis (LSA) to support writing and revision activities. Summary Street provides various kinds of automatic feedback, primarily whether a summary adequately covers important source content and fulfills other requirements, such as length. The feedback allows students to engage in extensive, independent practice in writing and revising without placing excessive demands on teachers for feedback. The efficacy of this system was examined in three classroom studies in a Boulder County school. In the first study, students read texts about three Mesoamerican civilizations and then composed summaries of those texts. One