Automated feedback has the potential to provide significant assistance to student game creators. We present a system for generating automated, critique-like feedback for students creating games in the StudyCrafter platform. We implemented a system that builds a personalized feedback report for students based on a templated format. This critique uses automated analysis of structural and interactive aspects of the game narrative and recommends alternate games for students to examine as inspiration. We investigate the impact of automatically-generated formative assessment on students' design process and educational experience. We present the results of two studies conducted in different University classrooms where students were tasked with creating virtual experiments using a narrative game creation tool with different learning goals in both cases. The first study involved providing automated feedback to 10 student groups for the narrative-based games they developed as a part of a psychology class to learn about research methods. The second study was conducted across two course sections, in which one course section received automated feedback for their games' narrative design, and the other section did not. Our results reveal that students who received AI-generated feedback actively engaged with the feedback system. We further find that their projects developed more over time in regard to their narrative design.

Creator

• Mahajan, Shruti P.

Colaboradores

• Harrison, Lane T.
• Smith, Gillian Margaret

Degree

• MS

Unit

• Computer Science

Publisher

• Worcester Polytechnic Institute

Identifier

• etd-4996

Advisor

• Smith, Gillian Margaret

Defense date

• 2020-12-08

Year

• 2020

Date created

• 2020-12-11

Resource type

• Thesis

Rights statement

• In Copyright

Última modificación

• 2021-02-03