Using cortical learning algorithm to arrange sporadic online conversation groups according to personality traits

© Springer International Publishing Switzerland 2016. Online conversation spaces are becoming an increasingly popular tool for language learning. Various portals on the Internet offer technological platform where groups of students can meet native teachers and arrange conversation sessions in convenient dates and times. The students’ satisfaction is very important in this context because potential new users pay much attention to the comments and ratings provided by others in the past. Therefore, the portals implement simple mechanisms for the students to rate their experiences, and use the feedback so gathered to promote the teachers who get the best evaluations. Notwithstanding, the current online conversation portals do not implement any means to proactively supervise the formation of the sporadic groups of students, aiming to ensure that the conversations will be balanced, engaging and pleasant to everyone. In this paper we look at the question of whether social data mining and machine learning technologies can be used to maximise the chances that the people put into the same group will get on well together. Specifically, we present one approach based on mining personality traits and using Cortical Learning Algorithm to aid in the planning of the sessions.