home - login - register

Conference Proceedings Detail Page

Using natural language processing to predict student problem solving performance
written by Jeremy Munsell, N. Sanjay Rebello, and Carina M. Rebello
In this work we report on a pilot study where we used machine learning to predict whether students will correctly solve the classic "ballistic pendulum" problem based on an essay written by students elucidating their approach to solving the problem. Specifically, students were asked to describe the "principles, assumptions, and approximations" they used to solve the problem. Student essays were codified using the practices of natural language processing. Essays from two non-consecutive semesters were used for training/validation (N = 1441) and testing (N=1480). The final model used to make predictions was an ensemble classification scheme using random forest, eXtreme Gradient Boosting classifier (XGBoost), and logistic regression as estimators. Our accuracy in predicting students' correctness was around 80% with slightly higher accuracy in identifying students who incorrectly solved the problem and slightly lower in predicting student who correctly solved the problem.
Physics Education Research Conference 2021
Part of the PER Conference series
Virtual Conference: August 4-5, 2021
Pages 295-300
Subjects Levels Resource Types
Education - Applied Research
- Technology
Education - Basic Research
- Assessment
= Methods
- Communication
= Writing
- Problem Solving
- Lower Undergraduate
- Reference Material
= Research study
PER-Central Type Intended Users Ratings
- PER Literature
- Researchers
  • Currently 0.0/5

Want to rate this material?
Login here!


Format:
application/pdf
Mirror:
https://doi.org/10.1119/perc.2021…
Access Rights:
Free access
License:
This material is released under a Creative Commons Attribution 4.0 license. Further distribution of this work must maintain attribution to the published article's author(s), title, proceedings citation, and DOI.
Rights Holder:
American Association of Physics Teachers
DOI:
10.1119/perc.2021.pr.Munsell
NSF Number:
1712201
Keyword:
PERC 2021
Record Creator:
Metadata instance created October 1, 2021 by Lyle Barbato
Record Updated:
October 1, 2021 by Lyle Barbato
Last Update
when Cataloged:
October 10, 2021
ComPADRE is beta testing Citation Styles!

Record Link
AIP Format
J. Munsell, N. Rebello, and C. Rebello, presented at the Physics Education Research Conference 2021, Virtual Conference, 2021, WWW Document, (https://www.compadre.org/Repository/document/ServeFile.cfm?ID=15767&DocID=5499).
AJP/PRST-PER
J. Munsell, N. Rebello, and C. Rebello, Using natural language processing to predict student problem solving performance, presented at the Physics Education Research Conference 2021, Virtual Conference, 2021, <https://www.compadre.org/Repository/document/ServeFile.cfm?ID=15767&DocID=5499>.
APA Format
Munsell, J., Rebello, N., & Rebello, C. (2021, August 4-5). Using natural language processing to predict student problem solving performance. Paper presented at Physics Education Research Conference 2021, Virtual Conference. Retrieved July 5, 2022, from https://www.compadre.org/Repository/document/ServeFile.cfm?ID=15767&DocID=5499
Chicago Format
Munsell, J, N. Rebello, and C. Rebello. "Using natural language processing to predict student problem solving performance." Paper presented at the Physics Education Research Conference 2021, Virtual Conference, August 4-5, 2021. https://www.compadre.org/Repository/document/ServeFile.cfm?ID=15767&DocID=5499 (accessed 5 July 2022).
MLA Format
Munsell, Jeremy, N. Sanjay Rebello, and Carina Rebello. "Using natural language processing to predict student problem solving performance." Physics Education Research Conference 2021. Virtual Conference: 2021. 295-300 of PER Conference. 5 July 2022 <https://www.compadre.org/Repository/document/ServeFile.cfm?ID=15767&DocID=5499>.
BibTeX Export Format
@inproceedings{ Author = "Jeremy Munsell and N. Sanjay Rebello and Carina Rebello", Title = {Using natural language processing to predict student problem solving performance}, BookTitle = {Physics Education Research Conference 2021}, Pages = {295-300}, Address = {Virtual Conference}, Series = {PER Conference}, Month = {August 4-5}, Year = {2021} }
Refer Export Format

%A Jeremy Munsell %A N. Sanjay Rebello %A Carina Rebello %T Using natural language processing to predict student problem solving performance %S PER Conference %D August 4-5 2021 %P 295-300 %C Virtual Conference %U https://www.compadre.org/Repository/document/ServeFile.cfm?ID=15767&DocID=5499 %O Physics Education Research Conference 2021 %O August 4-5 %O application/pdf

EndNote Export Format

%0 Conference Proceedings %A Munsell, Jeremy %A Rebello, N. Sanjay %A Rebello, Carina %D August 4-5 2021 %T Using natural language processing to predict student problem solving performance %B Physics Education Research Conference 2021 %C Virtual Conference %P 295-300 %S PER Conference %8 August 4-5 %U https://www.compadre.org/Repository/document/ServeFile.cfm?ID=15767&DocID=5499


Disclaimer: ComPADRE offers citation styles as a guide only. We cannot offer interpretations about citations as this is an automated procedure. Please refer to the style manuals in the Citation Source Information area for clarifications.

Citation Source Information

The AIP Style presented is based on information from the AIP Style Manual.

The AJP/PRST-PER presented is based on the AIP Style with the addition of journal article titles and conference proceeding article titles.

The APA Style presented is based on information from APA Style.org: Electronic References.

The Chicago Style presented is based on information from Examples of Chicago-Style Documentation.

The MLA Style presented is based on information from the MLA FAQ.

Using natural language processing to predict student problem solving performance:


Know of another related resource? Login to relate this resource to it.
Save to my folders

Contribute

Related Materials

Similar Materials