A novel metaheuristic approach for collaborative learning group formation

Abstract

In this paper, a new approach for the formation of four-member collaborative learning groups is presented. Group formation is presented by the mathematical optimization problem. Based on the proposed approach and the variable neighbourhood search (VNS) algorithm, the application that solves the presented problem and provides the appropriate division into groups is created. The proposed approach considers the scores of a pretest, interpersonal relationships, and prosocial behaviour/openness skill of students. In order to validate our approach, an experiment was designed with 108first-year university students of Belgrade Business School-Higher Educational Institution for Applied Studies. Experimental and control groups were divided into fourmember groups. The experimental group was divided by using the proposed method and the control group by student selection and random selection. Multilevel analysis is used to determine whether there is a significant difference in learning outcomes between the two groups. The experimental results showed that students from the experimental group achieved significantly higher success than the students from the control group. In addition, computational results obtained with the proposed VNS algorithms are compared and verified with the results obtained by random (Monte Carlo) method.

A hybrid approach for composing groups in collaborative learning contexts

“…(2010) PSO N = 61, K = 4, actual data (not available) Intel Core 2 Duo 2.66 GHz processor and 2 GB RAM memory 0.83 Lin et al. (2016) GA N = 100, k = 5, random data (not available) Intel Core i7 2.1 GHz processor and 4 GB RAM memory 1.35 Sadeghi and Kardan (2015) BIP N = 100, k = 4, random data (not available) Intel Core i7 2.20 GHz processor and 8 GB RAM memory 14591.4 Lambić et al. (2018) Other heuristic N = 108, k = 4, actual data (not available) AMD FD-7500 2.10 GHz processor and 8GB RAM memory 11.33 Zheng et al.…”

“…(2019) states that intra-heterogeneity enhances the success of a group by empowering the differences and complementary roles of its members according to their prequalified characteristics whereas inter-homogeneity ensures that all groups are equally built and therefore have the same chance of achieving such success. From the 33 analyzed works, most choose either intra-heterogeneity or inter-homogeneity, whereas a few choose the mixed alternative ( Henry, 2013a ; 2013b ; Hubscher, 2010 ; Lambić et al., 2018 ) and even fewer adapt themselves to several alternatives ( Abnar et al., 2012 ; Sadeghi and Kardan, 2015 ).…”

The role of team processes in innovation development to sustain learning organizations

“…While theoretical frameworks vary, learning organization research in industry and HE settings often pulls from similar perspectives such as experiential learning, as well as theories of organizational learning and change (Applebaum et al, 2012;Bui and Baruch, 2012;Cierna et al, 2016). Within HE, theories of social and emotional learning are also common (Huang and Lin, 2017;Lambi c et al, 2018;Watzek et al, 2019). This study was framed by five areas of literatureexperiential learning theory, action learning theory, organizational learning theory, change theory and design thinking.…”

An Optimization Model for Group Formation in Project-based Learning

“…The evaluation of the model indicates that the proposed model is useful in order to ensure the quality of the education. Furthermore, Lambić et al [12] use a mathematical optimization model in order to assign students to project groups containing four members each. In a comparison, their results indicate that optimization based assignment leads to significantly better study results than student chosen, or random, assignment.…”