The COVID pandemic hit heavily on all areas of industries, especially on education. Professor Neil Heffernan, also the founder of ASSISTments, enlisted our help to recoup the loss that occurred during the pandemic. ASSISTmentsis a tool for both teachers and students to use and improve their efficiency. Teachers can easily assign homework and analyze students' performance or learning experience, where students can have an easier time understanding the topic by getting prompt feedback from ASSESSments. Our team aims to make this process even more efficient on the teacher's side by providing a tool to predict the score of a student’s answer and give suggestions for comments. We worked on the training of NLP models that would be deployed into classrooms closely after the end of this project. The NLP model aims to give better and more accurate scores and comments suggestions to teachers. The Bert transformer method is used in this NLP model. We also looked into methods of data parsing and other model ensembles to compare with the models we plan to deploy

• 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

• Li, Shundong
• Gong, Fan

Subject

• Well-Being
• Learning
• Innovation
• Community
• Project-Based Learning

Publisher

• Worcester Polytechnic Institute

Identifier

• 41446
• E-project-111621-094953

Palavra-chave

• ASSISTment
• BERT
• regression
• NLP
• regex

Advisor

• Heffernan, Neil
• Shaw, Stacy

Year

• 2021

UN Sustainable Development Goals

• 4 - Quality Education
• 8 - Decent Work and Economic Growth
• 10 - Reducing Inequality

Date created

• 2021-11-16

Resource type

• Interactive Qualifying Project

Rights statement

• In Copyright

Última modificação

• 2022-04-01