Our website uses cookies to provide you with a better online experience. Please select “Accept”.

Research of the Month: Automatic Team Recommendation for Collaborative Software Development

Mahidol University focuses on creating quality research and innovation which is beneficial to economic, social and human development. The Faculty of Information and Communication Technology (ICT) has various research groups, or clusters, such as the Machine Intelligence and Knowledge Engineering Research Cluster (MIKE), Software Engineering and Business Analytics Research Cluster (SEBA), Technology Enhanced Learning and Human Centered Computing Research Cluster (TEL-HuCC), Medical Informatics Research Cluster (MI), and Cyber Security and IoT Research Cluster (CSI).

Our research projects and innovations emphasize the application of information technology in response to challenging social problems. On this occasion, the Faculty of ICT would like to present one of our outstanding research projects, “Automatic Team Recommendation for Collaborative Software Development” by Assoc. Prof. Dr. Suppawong Tuarob, Head of the Machine Intelligence and Knowledge Engineering Research Cluster (MIKE), Mr. Noppadol Assavakamhaenghan, Miss Waralee Tanaphantaruk, Mr. Ponlakit Suwanworaboon, Associate Prof. Dr. Saeed UL Hassan, Information Technology University, Pakistan, and Dr. Morakot Choetkiertikul, ICT Mahidol instructor. This research project was published in the Empirical Software Engineering Journal.

In this research work, “Automatic Team Recommendation for Collaborative Software Development”, the researchers propose RECAST (RECommendation Algorithm for Software Teams), a software team recommendation method for large-scale collaborative software development. Machine learning and Behavioral Science are used in many aspects such as the necessary technical skills and teamwork compatibility, given task description and a task assignee for large-scale collaborative software development.

The prototype of RECAST has been developed by using Python, Scikit-Learn, MALLET, and Neo4J, where the software practitioners can input the details of their prospective software and members’ particular roles, such as Developer, Tester, Reviewer, and Integrator.

Then, the “RECAST” will automatically suggest software practitioners for a task merely targeting particular roles. The “Automatic Team Recommendation for Collaborative Software Development” system has been developed with the integration of Artificial Intelligence, Software Engineering, and Behavioral Science.

 “The common problem we often encounter during the software development process is selecting team members from a large group of software developers to accomplish a software development task. We have to consider not only the technical skills of each member, but also teamwork compatibility.

Our team intended to solve those problems by developing an algorithm for recommending software teams for a given task and its role requirements. The research, “Software Automatic Team Recommendation for Collaborative Software Development” presented RECAST, an intelligent recommendation system that suggests team configurations that satisfy not only the role requirements, but also the necessary technical skills and teamwork compatibility, given the task description and a task assignee.

This research originated from the senior project of ICT Mahidol undergraduate students. We are proud of our students’ potential both in academic aspects and in the ability in applying artificial intelligence technology to creatively solve social problems to respond to Mahidol University’s aspiration – Wisdom of the Land”, said Assoc. Prof. Dr. Suppawong Tuarob.

For those interested in the full research paper, it can be read at https://rdcu.be/ct5ES