Open Collections

UBC Undergraduate Research

Building a System for Automated Question Generation and Evaluation to Assist Students Learning UML Database Design Urazova, Tatiana

Abstract

With the increase of online learning, the importance of online systems that support continuous learning and provide immediate feedback has grown. Building database diagrams is a key concept taught in computer science courses; however, those questions are time-consuming for instructors to develop, mark and provide feedback. The AutoER system supports automatic generation and marking of database design questions for student practice and course assessments. The unique approach of students interacting with question text directly and building the diagram iteratively guarantees unambiguous marking and helps students recognize and learn key database design concepts. Adding submission restrictions to AutoER proves to be an effective strategy to prevent system exploitation and undesired user behaviour. The analysis of student performance on the course examinations under submission restrictions revealed that although students demonstrate some undesired behaviour under regression penalty, the distribution within student behaviour profiles shows a major improvement compared to student performance under no submission restrictions.

Item Metadata

Title
Building a System for Automated Question Generation and Evaluation to Assist Students Learning UML Database Design
Creator
Urazova, Tatiana
Date Issued
2022-04
Description
With the increase of online learning, the importance of online systems that support continuous learning and provide immediate feedback has grown. Building database diagrams is a key concept taught in computer science courses; however, those questions are time-consuming for instructors to develop, mark and provide feedback. The AutoER system supports automatic generation and marking of database design questions for student practice and course assessments. The unique approach of students interacting with question text directly and building the diagram iteratively guarantees unambiguous marking and helps students recognize and learn key database design concepts. Adding submission restrictions to AutoER proves to be an effective strategy to prevent system exploitation and undesired user behaviour. The analysis of student performance on the course examinations under submission restrictions revealed that although students demonstrate some undesired behaviour under regression penalty, the distribution within student behaviour profiles shows a major improvement compared to student performance under no submission restrictions.
Genre
Graduating Project
Type
Text
Language
eng
Series
University of British Columbia. COSC 449
Date Available
2022-05-20
Provider
Vancouver : University of British Columbia Library
Rights
Attribution-NonCommercial-NoDerivatives 4.0 International
DOI
10.14288/1.0413656
URI
http://hdl.handle.net/2429/81605
Affiliation
Science, Irving K. Barber Faculty of (Okanagan); Computer Science, Mathematics, Physics and Statistics, Department of (Okanagan)
Peer Review Status
Unreviewed
Scholarly Level
Undergraduate
Rights URI
http://creativecommons.org/licenses/by-nc-nd/4.0/
Aggregated Source Repository
DSpace

Item Media

Item Citations and Data

Rights

Attribution-NonCommercial-NoDerivatives 4.0 International