An Interactive Platform for Team-based Learning Using Machine Learning Approach

Tony Maricic; Nisha Ramanna; Alison Reed; Rui Li; Jack Yang

Download Paper | Permalink

Conference: 2024 ASEE Annual Conference & Exposition
Location: Portland, Oregon
Publication Date: June 23, 2024
Start Date: June 23, 2024
End Date: July 12, 2024
Conference Session: DSA Technical Session 7
Tagged Topic: Data Science & Analytics Constituent Committee (DSA)
Page Count: 11
DOI: 10.18260/1-2--46563
Permanent URL: https://strategy.asee.org/46563
Download Count: 17

Nisha Ramanna is a student at New York University, pursuing her Bachelor's and Master's in Computer Science with a concentration in Machine Learning and Artificial Intelligence. She is passionate about all areas of Machine Learning, including Natural Language Processing.

visit author page

author page

Alison Reed New York University Tandon School of Engineering

biography

Rui Li New York University

visit author page

Dr. Li earned his master's degree in Chemical Engineering in 2009 from the Imperial College of London and his doctoral degree in 2020 from the University of Georgia, College of Engineering.

visit author page

author page

Jack Yang New York University Tandon School of Engineering

Download Paper | Permalink

Abstract

This evidence-based complete paper explores the feasibility of developing an interactive platform with chatbot feature to facilitate project-based learning. Teamwork pedagogy is widely used in engineering courses, particularly in first year (cornerstone) and senior-year (capstone) design courses, but also across the curriculum. Faculty have several aims for teaching in teams, one of which is to improve students' collaborative abilities. Engineering expertise, as well as pedagogical goals such as greater learning and motivation, are under consideration when building an effective team pedagogy. CATME, and other platforms have long been used to facilitate the process of monitoring team performance. The comprehensive data that the platform provided has enabled faculty members to analyze the problems in detail. Also, it is very helpful when documenting the team performance from year to year. In the large private institution located in the Northeast Region of the US, 700 students are taking a fundamental engineering course on an annual basis. The students are asked to form project teams after the first two weeks and work on a semester-long project on a weekly basis. Overall, there are 50-60 teams each semester. CATME has been implemented to monitor the team’s progress. It has been reported by the faculty members that it took time to evaluate the students’ peer comments and ratings as there are 2000 - 3000 comments each semester. Human errors can also occur when reviewing those comments. To reduce the workload of faculty members for analyzing the student comments and taking actions accordingly, an interactive team-monitoring platform is built to serve the purpose. This platform consists of two major components, which is built on React and Fast API. The platform can potentially be integrated with CATME or other team-monitoring software. A group of CATME users were asked to try out the platform and fill in a user experience survey. The survey results gave some constructive feedback for the developers. Overall, the project can deliver a feasible solution for course instructors to handle many student project teams. In the future, a generative AI feature - CHATME will also be available on the front end to help the user check the status of each student group, which is built using NLTK and TensorFlow. Moreover, if a team issue arises, the platform will alert the users, and provide constructive suggestions on how to improve the group performance.

Citation
Format

Maricic, T., & Ramanna, N., & Reed, A., & Li, R., & Yang, J. (2024, June), An Interactive Platform for Team-based Learning Using Machine Learning Approach Paper presented at 2024 ASEE Annual Conference & Exposition, Portland, Oregon. 10.18260/1-2--46563

TY - CPAPER
AB - This evidence-based complete paper explores the feasibility of developing an interactive platform with chatbot feature to facilitate project-based learning. Teamwork pedagogy is widely used in engineering courses, particularly in first year (cornerstone) and senior-year (capstone) design courses, but also across the curriculum. Faculty have several aims for teaching in teams, one of which is to improve students&#39; collaborative abilities. Engineering expertise, as well as pedagogical goals such as greater learning and motivation, are under consideration when building an effective team pedagogy. CATME, and other platforms have long been used to facilitate the process of monitoring team performance. The comprehensive data that the platform provided has enabled faculty members to analyze the problems in detail. Also, it is very helpful when documenting the team performance from year to year. In the large private institution located in the Northeast Region of the US, 700 students are taking a fundamental engineering course on an annual basis. The students are asked to form project teams after the first two weeks and work on a semester-long project on a weekly basis. Overall, there are 50-60 teams each semester. CATME has been implemented to monitor the team’s progress. It has been reported by the faculty members that it took time to evaluate the students’ peer comments and ratings as there are 2000 - 3000 comments each semester. Human errors can also occur when reviewing those comments. To reduce the workload of faculty members for analyzing the student comments and taking actions accordingly, an interactive team-monitoring platform is built to serve the purpose. This platform consists of two major components, which is built on React and Fast API. The platform can potentially be integrated with CATME or other team-monitoring software. A group of CATME users were asked to try out the platform and fill in a user experience survey. The survey results gave some constructive feedback for the developers. Overall, the project can deliver a feasible solution for course instructors to handle many student project teams. In the future, a generative AI feature - CHATME will also be available on the front end to help the user check the status of each student group, which is built using NLTK and TensorFlow. Moreover, if a team issue arises, the platform will alert the users, and provide constructive suggestions on how to improve the group performance.

AU - Tony Maricic
AU - Nisha Ramanna
AU - Alison Reed
AU - Rui Li
AU - Jack Yang
CY - Portland, Oregon
DA - 2024/06/23
PB - ASEE Conferences
TI - An Interactive Platform for Team-based Learning Using Machine Learning Approach
UR - https://strategy.asee.org/46563
DO - 10.18260/1-2--46563
ER -