IEEE Systems, Man and Cybernetics Magazine - April 2023 - 6

Universal
Optimization
Framework
Leader-Centered Learning Team
Formation Based on Fuzzy Evaluations
of Learners and E-CARGO
by Hua Ma , Jingze Li , Yuqi Tang, Haibin Zhu ,
Zhuoxuan Huang , and Wensheng Tang
B
6
uilding the right learning teams is a key to the
success of collaborative learning in online
and offline learning environments. However,
existing research on learning team formation
(LTF) ignores the uncertainty of learners'
abilities and lacks a common problem modeling and optimization
approach. Aiming at the characteristics of two
typical types of leader-centered (LC) LTF problems, a universal
optimization framework of LC-LTF is proposed by
introducing role-based collaboration (RBC) theory. This
framework evaluates the comprehensive ability of learners
via a fuzzy description mechanism; applies the environments-classes,
agents, roles, groups, and objects (E-CARGO)
model to formulate the LC-LTF problem; and employs an
optimization platform to obtain an optimal solution. A
case study demonstrates the effectiveness and feasibility
of the proposed framework.
Introduction
From an educator's perspective, teachers always want all
learners to complete their learning tasks and achieve
the best possible results after a course cycle. Existing
research [1], [2] indicates that dividing learners into
groups for collaborative learning is beneficial to learners.
Digital Object Identifier 10.1109/MSMC.2022.3231698
Date of current version: 25 April 2023
IEEE SYSTEMS, MAN, & CYBERNETICS MAGAZINE April 2023
Collaborative learning can significantly improve the overall
learning effectiveness of learners. Compared with individual
learning, collaborative learning allows learners to
get more help from group members and gain higher academic
achievement [3].
The key to the success of collaborative learning is forming
appropriate learning teams. Previous research on LTF can be
divided into two categories, i.e., leaderless LTF (LL-LTF)
methods [4], [5] and LC-LTF methods [6]-[9]. LL-LTF methods
assign learners to heterogeneous and homogeneous
teams according to their cognitive ability, learning style,
personal willingness, and so on. In every team, no leader
organizes learning activities, and all members communicate
with one another freely. Compared with LL-LTF,
LC-LTF methods have more advantages [10], [11]. In a team
with a leader, the leader plays a central role in the collaborative
learning process. For example, the leader could organize
and coordinate members to participate in learning
with a clearer goal, more quickly respond to queries and
resolve problems, and communicate with teachers to get
necessary support. Thus, this article mainly discusses the
LC-LTF method.
It is a challenging problem to divide tens and even hundreds
of learners into teams and guarantee the optimal
overall collaborative learning performance at the same
time. To solve it, it is necessary to evaluate the learners'
ability in an objective and accurate manner according to
2333-942X/23©2023IEEE

https://orcid.org/0000-0002-1980-4709 https://orcid.org/0000-0003-1922-1631 https://orcid.org/0000-0003-1924-2870 https://orcid.org/0000-0002-9617-4341 https://orcid.org/0000-0003-1137-1758

IEEE Systems, Man and Cybernetics Magazine - April 2023

Table of Contents for the Digital Edition of IEEE Systems, Man and Cybernetics Magazine - April 2023