Asee peer logo

A Case Study of Early Performance Prediction and Intervention in a Computer Science Course

Download Paper |

Conference

2020 ASEE Virtual Annual Conference Content Access

Location

Virtual On line

Publication Date

June 22, 2020

Start Date

June 22, 2020

End Date

June 26, 2021

Conference Session

New Engineering Educators 1: Learning Aids

Tagged Division

New Engineering Educators

Page Count

14

DOI

10.18260/1-2--33977

Permanent URL

https://peer.asee.org/33977

Download Count

35

Request a correction

Paper Authors

biography

Mariana Silva University of Illinois at Urbana-Champaign

visit author page

Mariana Silva is a Teaching Assistant Professor in Computer Science at the University of Illinois at Urbana-Champaign. She has been involved in large-scale teaching innovation activities, such as the development of online course content and assessments for the mechanics course sequence in the Mechanical Science and Engineering Department and the numerical methods class in Computer Science. Silva is currently involved in two educational projects involving the development of online assessments for computer-based testing and creation of collaborative programming activities for computer science classes. She is also involved in a project that aims to create a software that facilitates collaborative problem-solving activities in classrooms, through which both the instructors and students learn more about collaboration skills. Silva is very passionate about teaching and improving the classroom experience for both students and instructors. She has been included in the List of Teachers Ranked as Excellent five times and has received the Engineering Council Outstanding Advisor Award every year since 2014.

visit author page

biography

Eric G. Shaffer University of Illinois at Urbana-Champaign

visit author page

Eric Shaffer is a Teaching Assistant Professor in the Department of Computer Science. He teaches a revolving set of courses including Virtual Reality, Computer Graphics, and Scientific Visualization. In addition to teaching, he has done research in the areas of scientific computing, computer graphics and visualization. He has served as a PI or co-PI on grants from a variety of sponsors, including Exxon-Mobil, the Boeing Company, Caterpillar, and the US Department of Energy. He holds an MS in Computer Science from the University of Minnesota Twin Cities and a BS and PhD in Computer Science from the University of Illinois at Urbana-Champaign.

visit author page

biography

Nicolas Nytko University of Illinois at Urbana-Champaign

visit author page

Nicolas Nytko is a M.S. student in the department of Computer Science at the University of Illinois at Urbana-Champaign. His current research interests are in computer science education and scientific computing.

visit author page

biography

Jennifer R. Amos University of Illinois at Urbana-Champaign

visit author page

Dr Amos joined the Bioengineering Department at the University of Illinois in 2009 and is currently a Teaching Associate Professor in Bioengineering and an Adjunct Associate Professor in Educational Psychology. She received her B.S. in Chemical Engineering at Texas Tech and Ph.D. in Chemical Engineering from University of South Carolina. She completed a Fulbright Program at Ecole Centrale de Lille in France to benchmark and help create a new hybrid masters program combining medicine and engineering and also has led multiple curricular initiative in Bioengineering and the College of Engineering on several NSF funded projects.

visit author page

Download Paper |

Abstract

This work presents the results of an intervention study performed in an upper-division undergraduate computer science (CS) course with 348 students, designed to offer additional resources to students that were identified as “at-risk” of low performance after completing graded assessments during the first two weeks of the semester. The course uses Python as the required programming language, however not every student that takes the class has prior experience with Python. Moreover, the overall programming experience is not uniform among the students, which can be partially explained due to the large diversity of majors in the class (44% CS, 19% CS + X, 19% Engineering and 18% other majors). This disparity in programming skills can greatly affect the overall student’s experience in the classroom and potentially their overall course performance. Other studies have shown how prerequisite grades are used to predict a student's performance in a course. For example, Liao et al [1] determined that prerequisite grades are the most predictive data for upper-division courses. However, for introductory programming courses, in-class short quiz questions are the most predictive data for student performance. In this study, we used data collected during the first two weeks of the semester to predict if a student was at risk of low performance. The available data consisted of two quizzes and two homework assignments covering linear algebra (course prerequisite) and basic Python programming. We used equivalent data from previous semesters to train a model using machine learning algorithms to predict students that were at risk of lower performance, here defined as a final grade less than 80% (roughly representing 30% of the class). Students that were identified as “at-risk” received an invitation to join a 6-week course, which was created to give students an additional opportunity to work on programming activities using Python. Out of the 60 students that received the invitation, 24 accepted and joined the short course that started on week 3 of the semester. The class met once a week for 80 minutes, and was held in an active learning classroom, where each group table had a large computer monitor and a white board. Students were split into groups of 5 and given a programming problem that required the entire group to collaborate. The tasks involved real world examples, designed in a structured way to allow students to complete the solution on their own, without a lot of guidance from the instructors. Focus groups were conducted along with a survey to capture student perceptions of the course. [1] Liao et al, “Exploring the Value of Different Data Sources for Predicting Student Performance in Multiple CS Courses”, SIGCSE '19.

Silva, M., & Shaffer, E. G., & Nytko, N., & Amos, J. R. (2020, June), A Case Study of Early Performance Prediction and Intervention in a Computer Science Course Paper presented at 2020 ASEE Virtual Annual Conference Content Access, Virtual On line . 10.18260/1-2--33977

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: © 2020 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