Initial Assessment and Creation of a Fluid Mechanics Chatbot as an Additional Learning Resource
- Conference
- Location
-
Las Vegas, Nevada
- Publication Date
-
April 18, 2024
- Start Date
-
April 18, 2024
- End Date
-
April 20, 2024
- DOI
-
10.18260/1-2--46047
- Permanent URL
-
https://peer.asee.org/46047
Paper Authors
Daniel Skeldon California State Polytechnic University, Pomona
Yitong Zhao California State Polytechnic University, Pomona
Dr. Yitong Zhao is an Associated Professor at the Mechanical Engineering Department of Cal Poly Pomona (California State Polytechnic University Pomona). She received her B.S degree majored in Micro-Electrical-Mechanical System (MEMS) from Tsinghua University in China. She received her Ph.D. degree in Bioengineering from UCLA under the guidance of Dr. Chih-Ming Ho. Since joining Cal Poly Pomona, she has been focusing on STEM education with the assistance of technology to tackle the challenge of the new age of education. Her current focus is in utilizing virtual reality (VR)/augmented reality (AR) and mixed reality (MR) technology to improve the effectiveness of engineering education. Her other interests include autonomous vehicle and data science.
Carolyn Dougherty California State Polytechnic University, Pomona
Abstract
(Poster only) In the engineering curriculum, certain classes, such as Fluid Mechanics, serve as a foundation to higher level courses. When these classes have a high repetition rate, they become a bottleneck that impedes students’ progress through the curriculum. To improve the number of students succeeding in these key classes, additional tools to complement existing learning resources should be investigated. With recent improvements in artificial intelligence (AI), large language models (LLM) emerge as a compelling solution due to their ability to engage with students’ queries outside of a scripted dialogue.
Utilizing the LLM’s generative technology, our team implemented a web based conversational tool, called the “Fluids Chatbot”, for students taking Fluid Mechanics, where students could ask questions and receive immediate responses about course material. By sourcing information from a rich knowledge base of transcribed course lectures and illustrated solutions, the chatbot was able to ensure accurate and comprehensive responses to students’ questions. While guiding students through problems with a Socratic probing method, the chatbot helped reveal misconceptions or flawed premises in a student’s approach, thus reducing the negative reinforcement that usually occurred during missteps in self-study as well as aid students in assessing which topics required more attention.
To gauge the chatbot’s potential as a learning resource, relationships between time usage, course material studied, and helpfulness of a given response were observed. Additionally, we conducted a survey of the Fluid Chatbot, which included numerically rated helpfulness, perceived usability, and written feedback regarding potential future improvements.
Skeldon, D., & Zhao, Y., & Dougherty, C. (2024, April), Initial Assessment and Creation of a Fluid Mechanics Chatbot as an Additional Learning Resource Paper presented at 2024 ASEE PSW Conference, Las Vegas, Nevada. 10.18260/1-2--46047
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: © 2024 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