Proficient Valuation and Estimation of Human Performance in Collective Learning Environments using Machine Learning

Abstract

Novel organic single Machine learning has fascinated more and more attention in the past few decades. In this paper, we have proposed machine learning-based system architecture and algorithms to find patterns of learning, interaction, and relationship and effective valuation for a complex system involving massive data that could be obtained from a proposed collective learning environment (CLE). Collective learning may take place among larger team members to find solutions for real-time events or problems, and to discuss concepts or interactions during situational judgment tasks (SJT). Modelling a collective, networked system that involves multimodal data presents many challenges. This paper focuses on proposing a Machine Learning - (ML)-based system architecture to promote understanding of the behaviours, group dynamics, and interactions in the CLE. The designed framework integrates techniques from computational psychometrics (CP) and deep learning models that include the utilization of convolution neural networks (CNNs) for feature extraction, skill identification, and pattern recognition. The proposed framework also identifies the behavioral components at a micro level, and can help us model behaviors of a group involved in learning.