Affiliations: 363 Psychology-Math Building, Northern Illinois
University, DeKalb, Il 60115, USA. [email protected] | School of Computer Science, Telecommunications, and
Information Systems, DePaul University, 243 S. Wabash, Chicago, IL 60604,
USA | 363 Psychology-Math Building, Northern Illinois
University, deKalb, Il 60115, USA | Learning Research & Development Center, University
of Pittsburgh, Pittsburgh, PA 15260, USA
Abstract: Learning and reasoning from multiple documents requires students to
employ the skills of sourcing (i.e., attending to and citing sources) and
information integration (i.e., making connections among content from different
sources). Sourcer's Apprentice Intelligent Feedback mechanism (SAIF) is a
tool for providing students with automatic and immediate feedback on their use
of these skills during the writing process. SAIF uses Latent Semantic Analysis
(LSA), a string-matching technique and a pattern-matching algorithm to identify
problems in students' essays. These problems include plagiarism, uncited
quotation, lack of citations, and limited content integration. SAIF provides
feedback and constructs examples to demonstrate explicit citations to help
students improve their essays. In addition to describing SAIF, we also present
the results of two experiments. In the first experiment, SAIF was found to
detect source identification and integration problems in student essays at a
comparable level to human raters. The second experiment tested the
effectiveness of SAIF in helping students write better essays. Students given
SAIF feedback included more explicit citations in their essays than students
given sourcing-reminder instructions or a simple prompt to revise.
