Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
167 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
42 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Synergistic Team Composition: A Computational Approach to Foster Diversity in Teams (1909.11994v1)

Published 26 Sep 2019 in cs.AI

Abstract: Co-operative learning in heterogeneous teams refers to learning methods in which teams are organised both to accomplish academic tasks and for individuals to gain knowledge. Competencies, personality and the gender of team members are key factors that influence team performance. Here, we introduce a team composition problem, the so-called synergistic team composition problem (STCP), which incorporates such key factors when arranging teams. Thus, the goal of the STCP is to partition a set of individuals into a set of synergistic teams: teams that are diverse in personality and gender and whose members cover all required competencies to complete a task. Furthermore, the STCP requires that all teams are balanced in that they are expected to exhibit similar performances when completing the task. We propose two efficient algorithms to solve the STCP. Our first algorithm is based on a linear programming formulation and is appropriate to solve small instances of the problem. Our second algorithm is an anytime heuristic that is effective for large instances of the STCP. Finally, we thoroughly study the computational properties of both algorithms in an educational context when grouping students in a classroom into teams using actual-world data.

Citations (26)

Summary

  • The paper introduces two algorithms that optimize team balance by integrating competencies, personality, and gender using a linear programming approach and an anytime heuristic.
  • It demonstrates that the linear programming-based method excels in small instances while the heuristic achieves 75%-95% efficiency in larger, computationally challenging scenarios.
  • Empirical evaluation on real-world data validates the models and supports their practical application via tools like EduTeams for effective educational team formation.

Introduction

In the field of cooperative learning, the formation of diverse and balanced teams is crucial for both academic accomplishments and individual knowledge acquisition. The strategies involving the assembly of efficient teams must account for the intricate interplay among competences, personality traits, and gender. This document explores the synergistic team composition problem (STCP), which seeks to create partitions wherein each team is not only balanced according to these factors but also capable of performing allocated tasks. To address the STCP, two distinct algorithms are introduced: a linear programming-based algorithm suitable for small instances and an anytime heuristic tailored for larger instances.

Related Work

Research in organizational psychology historically focuses on factors contributing to team success, lacking comprehensive computational models employed in classrooms. Although multiagent systems concentrate on agent competencies within teams, they tend to oversimplify skill representation. Furthermore, existing literature has not holistically considered all three factors simultaneously: competencies, personality, and gender when forming teams.

Synergistic Team Composition Model

The proposed model for STCP incorporates three dimensions of diversity: gender, personality, and competencies. In this context, the personality is measured using Post-Jungian methodology, while competencies are evaluated on a gradient, allowing for a fine-grained representation of individual skill levels. A task type within this framework defines the competencies required, their respective levels, and importance. The STCP aims to partition a classroom into teams such that each team maintains an even distribution of competencies, personalities, and gender, thus forming "synergistic" teams.

Algorithms to Solve STCP

Two algorithms are proposed for the STCP: STCPSolver utilizes integer linear programming (ILP) to generate an optimal solution by leveraging off-the-shelf ILP solvers. The SynTeam algorithm, designed as an anytime heuristic, offers quality solutions within constrained computational time frames which can be desirable for larger team sizes or when ILP-based approaches are computationally prohibitive. Comparative computational trials revealed that while STCPSolver is recommended for smaller team sizes due to its efficiency, SynTeam provides a noteworthy alternative for larger instances, striking a balance between solution quality and computational feasibility.

Empirical Evaluation and Application

An extensive empirical comparison of the proposed algorithms was conducted using real-world data. For smaller instances, STCPSolver's performance is commendable, but it incurs a prohibitively increasing runtime with larger team sizes and an increasing number of students. SynTeam, on the contrary, manages larger instances effectively, yielding approximate solutions with relative quality ranging from 75% to 95% of an optimal solution's value. The research also details a web application, EduTeams, which allows educators to apply the concepts of the STCP algorithmically for team composition in educational settings.

Conclusion and Future Directions

The STCP instigates fresh avenues for advanced and comprehensive models to accurately articulate varying determinants of team performance. Future endeavors may include dimensions like explicit expert preferences, consideration for multiple task types, and avenues for leveraging parallelism in algorithms to optimize performance. These paths reflect an evolution in forming teams that not only perform tasks with homogeneity but also enhance the collaborative learning experience.