QUICK-Comments uses machine learning models to give teachers automatic suggestions of scores and feedback for student responses to open-ended questions on ASSISTments, an online education platform. However, up until now, the data being passed through the QUICK-Comments API has not been logged, limiting the ability to research it. Additionally, the machine learning models being used have needed to be retrained manually when new data is available. In this paper, we design and implement a solution to both of these problems to prepare for the launch of an extended research platform built on QUICK-Comments.

• This report represents the work of one or more WPI undergraduate students submitted to the faculty as evidence of completion of a degree requirement. WPI routinely publishes these reports on its website without editorial or peer review.

Creator

• Goto, Kendall

Subject

• Project-Based Learning
• Innovation
• Computing
• Learning

Publisher

• Worcester Polytechnic Institute

Identifier

• 65456
• E-project-042822-135533

Keyword

• Model Training
• Education
• Machine Learning
• Logging

Advisor

• Heffernan, Neil

Year

• 2022

Sponsor

• ASSISTments

UN Sustainable Development Goals

• 4 - Quality Education

Date created

• 2022-04-28

Resource type

• Interactive Qualifying Project

Rights statement

• In Copyright