First Impressions on Supporting Students with a Course-Aligned, AI-powered Virtual Teaching Assistant (TA), Oliver

We show in this paper that an LLM-based tutor with a simple, web-based interface is readily used by students to answer natural language queries without specific training. Through analysis of the log data of nearly 3000 separate interactions, we find that students tend to use the tutor to clarify concepts and explain sticking points in laboratory assignments. Results indicate that the chatbot was used throughout the course at times outside of regular help-seeking hours, indicating that the tutor provides personalized support to students who are in need of help even when it is not available. Finally, through analysis of the log data, we can generate useful insights into student learning throughout the course.

Authors

Institutions

Publication Details

Journal
Proceedings of the Canadian Engineering Education Association (CEEA)
Published
2024-12-20
DOI
https://doi.org/10.24908/pceea.2024.18548
Citations
2
Primary Topic
Artificial Intelligence in Education
Type
article
Field-Weighted Citation Impact
1.14
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

First Impressions on Supporting Students with a Course-Aligned, AI-powered Virtual Teaching Assistant (TA), Oliver

Michael Cooper-Stachowsky, Zille Huma Kamal
2 citations
Proceedings of the Canadian Engineering Education Association (CEEA)
Artificial Intelligence in Education
1.14
article

First Impressions on Supporting Students with a Course-Aligned, AI-powered Virtual Teaching Assistant (TA), Oliver

Michael Cooper-Stachowsky, Zille Huma Kamal
article en
2 citations

Abstract

We show in this paper that an LLM-based tutor with a simple, web-based interface is readily used by students to answer natural language queries without specific training. Through analysis of the log data of nearly 3000 separate interactions, we find that students tend to use the tutor to clarify concepts and explain sticking points in laboratory assignments. Results indicate that the chatbot was used throughout the course at times outside of regular help-seeking hours, indicating that the tutor provides personalized support to students who are in need of help even when it is not available. Finally, through analysis of the log data, we can generate useful insights into student learning throughout the course.

Proceedings of the Canadian Engineering Education Association (CEEA)
University of Waterloo (CA)
Quality Education
Openalex Percentile: Top 16%
Artificial Intelligence in Education
1.14
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.