New ways to identify students in need of assistance are imperative to the evolution of online tutoring platforms. Currently implemented models to identify struggling students use costly and tedious classroom observation paired with student's platform usage, and are often suitable for only a subset of students. With the recent influx of new students to online tutoring platforms due to COVID-19, a simple method to quickly identify struggling students could help facilitate effective remote learning. To this end, we created an anomaly detection algorithm that models the normal behavior of students during remote learning and recognizes when students deviate from this behavior. We demonstrated how anomalous behavior not only revealed which students needed additional assistance, but also helped predict student learning outcomes and reduced the confidence intervals in research experiments performed within the online tutoring platform.

Creator

• Prihar, Ethan B.

Contributors

• Harrison, Lane T.
• Heffernan, Neil

Degree

• MS

Unit

• Data Science

Publisher

• Worcester Polytechnic Institute

Identifier

• etd-5496

Keyword

• Outlier Detection
• Online Learning
• Unsupervised Learning
• Tutoring
• Anomaly Detection

Advisor

• Heffernan, Neil

Defense date

• 2021-04-27

Year

• 2021

Date created

• 2021-03-02

Resource type

• Thesis

Rights statement

• In Copyright

License

• Creative Commons BY-NC Attribution-NonCommercial 4.0 International

Last modified

• 2023-09-20