Employing Game theory and Multilevel Analysis to Predict the Factors that affect Collaborative Learning Outcomes: An Empirical Study

TL;DR

This study develops a predictive model using game theory and multilevel analysis to understand social and psychological factors influencing collaborative learning outcomes, validated on university students.

Contribution

It introduces a novel combination of cooperative game theory and multilevel analysis to predict individual learning outcomes in group settings.

Findings

Shapley values effectively predict individual learning outcomes.

Content engagement significantly impacts learning success.

Personality traits and learning styles have minimal influence.

Abstract

The purpose of this study is to propose a model that predicts the social and psychological factors that affect the individuals collaborative learning outcome in group projects. The model is established on the basis of two theories, namely, the multilevel analysis and the cooperative game theory (CGT). In CGT, a group of players form a coalition and a set of payoffs for each member in the coalition. Shapely values is one of the most important solution concepts in CGT. It represents a fair and efficient distribution of payoffs among members of a coalition. The proposed approach was applied on a sample that consisted of 78 freshman students, in their first semester, who were studying philosophical thinking course and instructed by the same professor. Tools for the data collection included self-assessments, peer assessments, quizzes and observations. The research concluded that learning outcome and contribution are best prophesied by the extent of engagement the content is purveying. Whereas personality traits, as well as, learning styles have the least impact on contribution. In addition, results show that Shapley values can be used as good vaticinators for individuals learning outcomes. These results indicate that CGT can be used as a good engine for analyzing interactions that recur in collaborative learning.