Finding Key Concepts to Automatically Generate Pedagogically Valuable Questions for Learning Objectives

• In Event: Instructional Technology and Assessing Learning and Performance

Abstract

Answering questions is an essential part of learning in online courseware. However, generating questions requires a lot of effort. Although there are some methods for automatically generating questions, these technologies do not necessarily give questions that are useful for educational purposes. To fill this gap, we propose QUADL, a method for generating questions that are aligned with a given learning objective. The QUADL first identifies a key concept, if any, in a given sentence that has a strong connection with the given learning objective, and then converts the given sentence into a question. The results from the survey using Amazon Mechanical Turk suggest that the QUADL can be a step towards generating questions that effectively contribute to students’ learning.

Authors

• Machi Shimmei, North Carolina State University

• Noboru Matsuda, North Carolina State University