Using Educational Data Mining to Identify Correlations Between Homework Effort and Performance

James Herold; Thomas Stahovich; Kevin Rawson

Download Paper | Permalink

Conference: 2013 ASEE Annual Conference & Exposition
Location: Atlanta, Georgia
Publication Date: June 23, 2013
Start Date: June 23, 2013
End Date: June 26, 2013
ISSN: 2153-5965
Conference Session: Assessment of Student Learning 1
Tagged Division: Educational Research and Methods
Page Count: 14
Page Numbers: 23.1311.1 - 23.1311.14
DOI: 10.18260/1-2--22697
Permanent URL: https://peer.asee.org/22697
Download Count: 526

Paper Authors

biography

James Herold University of California, Riverside

visit author page

James Herold earned his B.S. in computer science at California Polytechnic State University, Pomona in
2004. He is currently a Ph.D. student in computer science at the University of California, Riverside where he is researching applications of Data Mining in Educational Research Methods.

visit author page

biography

Thomas Stahovich University of California, Riverside

visit author page

Dr. Stahovich received his B.S in Mechanical Engineering from UC Berkeley in 1988. He received his S.M. and Ph.D. from MIT in 1990 and 1995 respectively. He conducted his doctoral research at the MIT Artiﬁcial Intelligence Lab. After serving as an Assistant and Associate Professor of Mechanical Engineering at Carnegie Mellon University in Pittsburgh, PA, Dr. Stahovich joined the Mechanical Engineering Department at UC Riverside in 2003 where he is currently a Professor and Chair. His research interests include pen-based computing, educational technology, design automation, and design rationale management.

visit author page

biography

Kevin Rawson University of California, Riverside

visit author page

Mr. Rawson received his B.S.E. in Mechanical Engineering and B.S. in Mathematics from Walla Walla University in 2001. He received his M.S. in Mechanical Engineering from UC Riverside in 2005, where he currently is working towards his Ph.D.

Research interests include sketch understanding, machine learning, pen-based computing, and educational informatics.

visit author page

Download Paper | Permalink

Abstract

Knowledge Discovery and Pattern Finding in Students’ Solution SequencesIn this paper we apply machine learning techniques to automatically identifypatterns in the way in which students solve problems in an undergraduateMechanical Engineering course. Such patterns can provide valuable insight intostudents’ cognitive processes and, when correlated with performance in the class,can provide insight as to which behaviors may contribute to or impede success inthe classroom.We provided 150 students enrolled in a Mechanical Engineering statics course withLivescribe digital pens with which they completed all of their coursework. Thesepens serve the same purpose as traditional ink pens, but additionally digitize theink, producing a digital, time-stamped copy of the students’ coursework.This digital representation of student work provides an unprecedented view intothe sequence of steps students take to solve problems. For example, using thetiming information, we can answer the question, “How often do students completeall their free body diagrams before beginning to solve equations?” While manuallyinspecting this data set for interesting patterns of problem-solving behaviors isprohibitively time consuming, a digital corpus of student work allows us to usedata mining techniques to automatically identify such patterns.We encode a student’s solution to an assignment as a sequence of characters, usingan alphabet in which each letter represents a specific kind of action taken by thestudent. For example, a simple alphabet might contain two letters, “A”, indicatingthat a student drew a free body diagram, and “B”, indicating that a student wrote anequation. Using this alphabet, the sequence “ABA” would indicate that a particularstudent began by drawing a free body diagram, then wrote equations, and thenrevisited his/her free body diagram. We consider several different alphabetsdescribing a range of problem-solving activities. We then mine the resultingcharacter sequences using several popular data mining methods, e.g., FisherKernels and motif discovery. Through these methods, we identify commonpatterns of problem-solving behavior which correlate with both successful andunsuccessful course performance.

Citation
Format

Herold, J., & Stahovich, T., & Rawson, K. (2013, June), Using Educational Data Mining to Identify Correlations Between Homework Effort and Performance Paper presented at 2013 ASEE Annual Conference & Exposition, Atlanta, Georgia. 10.18260/1-2--22697

TY  - CPAPER
AB  -  Knowledge Discovery and Pattern Finding in Students’ Solution SequencesIn this paper we apply machine learning techniques to automatically identifypatterns in the way in which students solve problems in an undergraduateMechanical Engineering course. Such patterns can provide valuable insight intostudents’ cognitive processes and, when correlated with performance in the class,can provide insight as to which behaviors may contribute to or impede success inthe classroom.We provided 150 students enrolled in a Mechanical Engineering statics course withLivescribe digital pens with which they completed all of their coursework. Thesepens serve the same purpose as traditional ink pens, but additionally digitize theink, producing a digital, time-stamped copy of the students’ coursework.This digital representation of student work provides an unprecedented view intothe sequence of steps students take to solve problems. For example, using thetiming information, we can answer the question, “How often do students completeall their free body diagrams before beginning to solve equations?” While manuallyinspecting this data set for interesting patterns of problem-solving behaviors isprohibitively time consuming, a digital corpus of student work allows us to usedata mining techniques to automatically identify such patterns.We encode a student’s solution to an assignment as a sequence of characters, usingan alphabet in which each letter represents a specific kind of action taken by thestudent. For example, a simple alphabet might contain two letters, “A”, indicatingthat a student drew a free body diagram, and “B”, indicating that a student wrote anequation. Using this alphabet, the sequence “ABA” would indicate that a particularstudent began by drawing a free body diagram, then wrote equations, and thenrevisited his/her free body diagram. We consider several different alphabetsdescribing a range of problem-solving activities. We then mine the resultingcharacter sequences using several popular data mining methods, e.g., FisherKernels and motif discovery. Through these methods, we identify commonpatterns of problem-solving behavior which correlate with both successful andunsuccessful course performance.
AU  - James Herold
AU  - Thomas Stahovich
AU  - Kevin Rawson
CY  - Atlanta, Georgia
DA  - 2013/06/23
PB  - ASEE Conferences
TI  - Using Educational Data Mining to Identify Correlations Between Homework Effort and Performance
UR  - https://peer.asee.org/22697
DO  - 10.18260/1-2--22697
ER  -