A case study on algorithms for group formation in collaborative environments applied to MEMENTOS system

• Grant number: 14/12002-0
• Support Opportunities: Scholarships abroad - Research Internship - Master's degree
• Start date: October 01, 2014
• End date: March 31, 2015
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computer Systems
• Principal Investigator: Seiji Isotani
• Grantee: Wilmax Marreiro Cruz
• Supervisor: Luís Manuel Pinto da Rocha Afonso Carriço
• Host Institution: Instituto de Ciências Matemáticas e de Computação (ICMC). Universidade de São Paulo (USP). São Carlos , SP, Brazil
• Institution abroad: Universidade de Lisboa, Portugal
• Associated to the scholarship: 13/13056-4 - A web environment for analysis and study of group formation algorithms in educational contexts, BP.MS

Abstract

In the literature, one can find several algorithms that work with group formation in learning environments, and which aims to maximize positive interactions that make the most effective and lasting learning. Such algorithms receive as input information of users (teachers and learners). And produce as possible output group formations. Some are based on the learning styles of learners, while others in restrictions set by the instructors. However, despite the proven algorithms produce positive results for metrics for this purpose, they are used by inappropriate or limited graphical interfaces, hindering its effective application in real learning scenarios. Furthermore, the use of group formation algorithms developed so far is limited to the system (prototype) that were initially implemented, making the comparison, analysis and reuse them. Thus, the aim of this project is to implement a tool to study algorithms form groups in order to facilitate the analysis and comparison of these algorithms in a real collaborative learning environment. To achieve this goal an integrated to an intelligent tutoring system (e.g. MeuTutor) that enables use different algorithms to form groups and generate a report on the data obtained by analyzing the interactions of students during group learning web system will be developed. The intended result is that the results of this project can help the community to compare and choose the most suitable way algorithms for training groups in the context of collaborative learning. (AU)