The automatic assessment of knowledge integration processes in project teams

Automatic assessment of group processes in collaborative groups is one of the holy grails of the computer supported collaborative learning community. The conversation in collaborative work provides an important window into the inner workings of a group. In this paper we present work towards detecting where students are displaying “reasoning” in conversational speech and how others are building upon those expressions of reasoning (“transactivity”). Such technology would add to the body of work in educational data mining another means of monitoring student work as well as contributing to the area of automatic collaborative process analysis. We begin by discussing our operationalization of targeted group processes, namely reasoning and transactivity. We then discuss the level of success we are able to achieve applying machine learning technology to replicate this human analysis using simple audio signal processing techniques. We end with a road map towards improving upon this baseline technology.