Originally Published In
Exploring the Material Conditions of Learning: The Computer Supported Collaborative Learning (CSCL) Conference 2015, Volume 2. Gothenburg, Sweden: The International Society of the Learning Sciences. ISBN: 978-0-9903550-7-6
Using online knowledge communities (OKCs) from the Internet as studentcentered, open learning environments (SCOLEs) poses the question how likely these communities will be to integrate learners as new members. This premise of learning in SCOLEs is analyzed in the current study. Based on the approaches of voices interanimation and polyphony, a natural language processing tool was employed for dialog analysis in integrative vs. non-integrative blog-based OKCs. Three dialog dimensions were identified: participants’ individual content-oriented contribution, social contribution, and their position within the social network. Hierarchical clusters built upon these dimensions reflect sociocognitive structures including central, regular and peripheral OKC members. OKCs with a stronger layer of regular members appear more likely to integrate new members, whereas OKCs with a stronger layer of peripheral members appear less likely to do so. Consequently, the study suggests an automated prediction method of OKC integrativity that may sustain the educational use of OKCs.