Asee peer logo

Data Mining An Online Homework System

Download Paper |

Conference

2007 Annual Conference & Exposition

Location

Honolulu, Hawaii

Publication Date

June 24, 2007

Start Date

June 24, 2007

End Date

June 27, 2007

ISSN

2153-5965

Conference Session

NSF Grantees Poster Session

Page Count

12

Page Numbers

12.440.1 - 12.440.12

Permanent URL

https://peer.asee.org/2440

Download Count

33

Request a correction

Paper Authors

author page

Andrew Bennett Kansas State University

author page

Eric Lawrence Kansas State University

author page

Genevra Neumann Northern Iowa University

author page

Elena Verbych Kansas State University

author page

Steve Warren Kansas State University

Download Paper |

Abstract
NOTE: The first page of text has been automatically extracted and included below in lieu of an abstract

Data-Mining an Online Homework System

Abstract

Online homework systems are becoming increasingly popular since (when they work) they are convenient for both faculty and students. Systems that rely on mechanical grading are naturally best adapted to more mechanical types of problems, raising issues of whether an increasing reliance on such systems will privilege the assessment of procedural knowledge over the assessment of conceptual knowledge. However, online systems naturally and efficiently capture large amounts of data about student work and data-mining techniques can be applied to evaluate conceptual understanding as well as procedural understanding, even though the prompts are all procedural. In this paper, we discuss how to use detailed analysis of procedural results captured by a locally designed online homework system (tuned for the purpose of assessing conceptual understanding) to recognize conceptual growth in classes in mathematics and the likelihood of successful transfer of this understanding to later engineering classes. Patterns that demonstrate students are wrestling with new concepts and techniques for disentangling correlations in different subjects caused by successful transfer from correlations caused by general skills are developed. While the analysis is based on our local system, the general approach and tools can be applied to other systems as long as they allow multiple attempts and retain information about unsuccessful attempts prior to the final submission.

Introduction

Online homework is becoming a common tool in college mathematics courses, as well as other science and engineering courses. One product, WebAssign, has a list of over 300 U.S. Colleges and Universities using their system1, and most publishers now offer online homework systems as an option with many of their texts. The popularity of online homework systems is easy to understand. For the faculty, an online homework system reduces the amount of effort spent on grading and can also reduce management issues relating to collecting, recording, and returning student papers. For the students, online homework systems allow them to work on their own schedule and receive immediate feedback on what they have done correctly and incorrectly. In addition, some systems allow students multiple attempts and extra practice compared to courses with traditional homework only. Given the practical advantages, the shift to online homework seems very likely to continue. Therefore, it is important to study how this shift may alter instruction and learning, and how teachers can best assess student learning in an online world.

Using an online homework system can influence the types of assignments that are made. Online homework problems must be of a format that can be graded by machine. This can lead to more procedurally oriented problems that have well-defined answers and for which systems can be easily generate multiple variations by simply adjusting the numbers. More conceptual problems are more likely to require open-ended solutions and are usually much more difficult to implement with such systems. Thus the shift to more online homework raises the possibility that it will be accompanied by a shift toward more

Bennett, A., & Lawrence, E., & Neumann, G., & Verbych, E., & Warren, S. (2007, June), Data Mining An Online Homework System Paper presented at 2007 Annual Conference & Exposition, Honolulu, Hawaii. https://peer.asee.org/2440

ASEE holds the copyright on this document. It may be read by the public free of charge. Authors may archive their work on personal websites or in institutional repositories with the following citation: © 2007 American Society for Engineering Education. Other scholars may excerpt or quote from these materials with the same citation. When excerpting or quoting from Conference Proceedings, authors should, in addition to noting the ASEE copyright, list all the original authors and their institutions and name the host city of the conference. - Last updated April 1, 2015