As a pedagogical strategy, Writing-to-Learn uses writing to improve students’ understanding of course content, but most existing writing feedback systems focus on improving students’ writing skills rather than their conceptual development. In this article, we propose an automatic approach to generate individualized feedback based on comparing knowledge representations extracted from lecture slides and individual students’ writing assignments. The novelty of our approach lies in the feedback generation: to help students assimilate new knowledge into their existing knowledge better, their current knowledge is modeled as a set of matching concepts, and suggested concepts and concept relationships for inclusion are generated as feedback by combing two factors: importance and relevance of feedback candidates to the matching concepts in the domain knowledge. A total of 88 students were recruited to participate in a repeated measures study. Results show that most participants felt the feedback they received was relevant (78.4%), easy to understand (82.9%), accurate (76.1%) and useful (79.5%); they also felt that the proposed system made it easier to study course concepts (80.7%) and was useful in learning course concepts (77.3%). Analyses of students’ submitted assignments reveal that more course concepts and concept relationships were included when they used the proposed system.
All Science Journal Classification (ASJC) codes
- Computer Science Applications
- Automated formative feedback
- Concept maps
- Meaningful learning