TeamUp: Semantic Project Matching and Team Formation for Learning at Scale

2026-05-04

AI Summary

This study addresses the challenges of accurately matching students to appropriately challenging projects and forming cognitively diverse teams in large-scale project-based learning, where conventional approaches often exacerbate educational inequities. The authors propose a hybrid ranking algorithm that integrates semantic embeddings from pretrained language models with pedagogical constraints to deliver personalized project recommendations. For the first time, cognitive diversity in team formation is modeled through embedding variance to capture skill complementarity, enabling automatic construction of heterogeneous teams. Experimental results demonstrate that the method significantly improves matching quality (average cosine similarity of 0.74 versus 0.43), assigns difficulty-appropriate projects to 83% of students (compared to 34%), and ensures 82% of teams span three or more technical domains (versus 41%). The system achieves sub-second recommendation latency per query and costs less than $0.10 per student.

Abstract

Project-based learning improves student engagement and learning outcomes, yet allocating students to appropriately challenging projects while forming cognitively diverse teams remains difficult at scale. Traditional allocation methods (manual spreadsheets, preference surveys) can't construct the cognitively diverse teams that that collaborate cognitively. This mismatch perpetuates equity issues: high-performing students self-select visible projects while under-represented students face reduced access to opportunity. We propose TeamUp, a lightweight, embedding-based team-forming system designed to improve learning outcomes and equity in large-scale project-based courses. TeamUp uses semantic embeddings from pretrained language models to match students to projects aligned with their skill level. The system employs a hybrid ranking algorithm combining cosine similarity with pedagogical constraints (difficulty alignment, domain preferences, and demand balancing) to generate personalised and transparent recommendations. Beyond individual matching, TeamUp constructs cognitively diverse teams by modelling skill complementarity through embedding variance, ensuring teams possess well-distributed capabilities rather than homogeneous strengths. We evaluated TeamUp through a virtual experiment using 250 student profiles and 60 project descriptions. Results show: (1) substantially higher match quality (mean cosine similarity of 0.74 vs. 0.43); (2) better difficulty alignment (83% placed within one level vs. 34%); (3) more diverse teams (82% covering three or more technical areas vs. 41%); and (4) sub-second recommendation latency at operational costs under $0.10 per student.

Problem

• project-based learning
• team formation
• cognitive diversity
• equity
• student-project matching

Innovation

• semantic embeddings
• team formation
• project-based learning
• cognitive diversity
• hybrid ranking algorithm