Automatic Extraction of Conceptual Maps From Design Team Documents

Abstract

Most engineering project classes expect teams of students to collaborate and to build on existing knowledge to accomplish their project goals. As the project evolves, the team is expected to develop a shared understanding. However, students often become overwhelmed by the amount of information available and lose sight of the big picture. Instructors may also find it difficult to keep track of individual and team activities and are often forced to evaluate the product instead of the learning process. This paper presents preliminary results from a tool that supports effective knowledge management for engineering design projects. This framework, called DesignWebs, automatically extracts conceptual maps from the team’s evolving set of documents and discussions about an engineering artifact. It uses Latent Dirichlet Allocation, hierarchical clustering, and other machine learning techniques to generate a navigable web-based graph. Both instructors and students can browse this graph interactively to explore the concepts embedded inside design team documents and the connections between them. An experiment performed on documents obtained from a project course shows the effectiveness of DesignWebs in synthesizing the design knowledge from multiple sources of information in engineering project teams.