Predicting Student Performance Using Discussion Forums' Participation Data

Mac Joseph Gray; Rabih Younes

Download Paper | Permalink

Conference: 2024 ASEE Annual Conference & Exposition
Location: Portland, Oregon
Publication Date: June 23, 2024
Start Date: June 23, 2024
End Date: June 26, 2024
Conference Session: Educational Research and Methods Division (ERM) Technical Session 7
Tagged Division: Educational Research and Methods Division (ERM)
Page Count: 16
DOI: 10.18260/1-2--47858
Permanent URL: https://peer.asee.org/47858
Download Count: 97

Paper Authors

biography

Mac Joseph Gray Duke University

visit author page

Mac Gray is currently a second-year Master of Science student in Electrical and Computer Engineering at Duke University. With an interest in the intersection of machine learning and software engineering. Mac is specifically passionate about advancing natural language processing (NLP) technologies.

visit author page

biography

Rabih Younes Duke University orcid.org/0000-0002-5720-8553

visit author page

Rabih Younes is an Assistant Professor of the Practice in the Department of Electrical and Computer Engineering at Duke University. He received his PhD in Computer Engineering from Virginia Tech in 2018 after receiving his BE and MSE in Computer Engineering from the Lebanese American University in 2011 and 2013, respectively. Rabih speaks nine languages (fluent in three) and holds a number of certificates in education, networking, IT, and skydiving. He is also a member of several honor societies, including Tau Beta Pi, Eta Kappa Nu, Phi Kappa Phi, and Golden Key.
Rabih has a passion for both teaching and research; he has been teaching since he was a teenager, and his research interests include wearable computing, activity recognition, context awareness, machine learning, engineering education, and Middle Eastern politics. As a professor, Rabih is committed to helping his students achieve their goals and providing them with opportunities to realize that. He also focuses on their personal development and on improving their abilities to be critical thinkers, better communicators, and active members of their community and the world.
More information can be found on his personal website: www.rabihyounes.com.

visit author page

Download Paper | Permalink

Abstract

A significant gap in education lies in the need for mechanisms that enable early detection of potentially at-risk students. Through access to an earlier prediction of student performance, instructors are given ample time to meet with and assist under-achieving students. As with any prediction modeling problem, there are many predictors to choose from when formulating a model. Previous related works have shown limited success in predicting course performance using students’ personal and socioeconomic traits. Students learn by asking clarifying questions. Therefore, discussion boards have been a staple of learning at the university level for years. This paper aims to utilize participation in discussion forums to predict final student performance. Using students’ course grades at roughly the halfway point in the term and various discussion forum predictors, our model predicts the students’ final percentage score. Using the model’s prediction, instructors can speak with at-risk students and discuss ways to improve. The student grades and discussion board participation datasets are gathered from a graduate-level Electrical and Computer Engineering (ECE) course at Duke University. Various classical machine learning models are explored, with random forest yielding the highest accuracy. This random forest model, trained on discussion forum participation data, surpasses other similarly trained state-of-the-art models. Furthermore, related research attempts the classification problem of predicting what discrete letter grade a student will earn. This is not an accurate representation of a student’s performance, and therefore, we attempt the regression problem of predicting the exact percentage a student will earn. A significant finding of this paper is that our random forest model can predict student performance with an average error of approximately 2.3%. Additionally, our random forest model can generalize to a different graduate-level course and make performance predictions with an average error of 3.3%. The final important finding is that a model including discussion board predictors outperforms another whose sole predictor is the students’ halfway point grade. This indicates that discussion forums hold significant value in determining final performance. We envision that the knowledge from our findings and our optimal random forest model can enable instructors to identify and support potentially at-risk students preemptively.

Citation
Format

Gray, M. J., & Younes, R. (2024, June), Predicting Student Performance Using Discussion Forums' Participation Data Paper presented at 2024 ASEE Annual Conference & Exposition, Portland, Oregon. 10.18260/1-2--47858

TY  - CPAPER
AB  - A significant gap in education lies in the need for mechanisms that enable early
detection of potentially at-risk students. Through access to an earlier prediction of
student performance, instructors are given ample time to meet with and assist
under-achieving students. As with any prediction modeling problem, there are many
predictors to choose from when formulating a model. Previous related works have
shown limited success in predicting course performance using students’ personal and
socioeconomic traits. Students learn by asking clarifying questions. Therefore,
discussion boards have been a staple of learning at the university level for years. This
paper aims to utilize participation in discussion forums to predict final student
performance. Using students’ course grades at roughly the halfway point in the term
and various discussion forum predictors, our model predicts the students’ final
percentage score. Using the model’s prediction, instructors can speak with at-risk
students and discuss ways to improve. The student grades and discussion board
participation datasets are gathered from a graduate-level Electrical and Computer
Engineering (ECE) course at Duke University. Various classical machine learning
models are explored, with random forest yielding the highest accuracy. This random
forest model, trained on discussion forum participation data, surpasses other similarly
trained state-of-the-art models. Furthermore, related research attempts the
classification problem of predicting what discrete letter grade a student will earn.
This is not an accurate representation of a student’s performance, and therefore, we
attempt the regression problem of predicting the exact percentage a student will earn.
A significant finding of this paper is that our random forest model can predict student
performance with an average error of approximately 2.3%. Additionally, our random
forest model can generalize to a different graduate-level course and make
performance predictions with an average error of 3.3%. The final important finding is
that a model including discussion board predictors outperforms another whose sole
predictor is the students’ halfway point grade. This indicates that discussion forums
hold significant value in determining final performance. We envision that the
knowledge from our findings and our optimal random forest model can enable
instructors to identify and support potentially at-risk students preemptively.

AU  - Mac Joseph Gray
AU  - Rabih Younes
CY  - Portland, Oregon
DA  - 2024/06/23
PB  - ASEE Conferences
TI  - Predicting Student Performance Using Discussion Forums' Participation Data
UR  - https://peer.asee.org/47858
DO  - 10.18260/1-2--47858
ER  -