To accomplish larger scale facilitation, there are two important aspects to consider. One is identify markers of both collaborative activities and disciplinary content and/or practices. Some of these might include indicators such as making contributions, asking responding to questions, social network analysis, or indicators of transactivity. Learning analytics (LA) techniques are important to be able to accomplish this [4; 5]. The markers of disciplinary content and practices may be more difficult to measure. The second aspect is acting on what is learned through LA. A first step might be a dashboard that might alert instructors as to where they might need to intervene as well as suggesting appropriate strategies.
Research on these massive networked communities should build on research on best practices in CSCL and problem-based learning (PBL; e.g., [3; 6-10]). This research suggests that certain instructional goals can support productive collaboration, and that there are particular cognitive, metacognitive, and social strategies that can best serve particular kinds of goals. For example, in some groups such as a PBL group, goals might include:
Educational Goals for students:
For TA’s or any kind of automated agents to use these strategies, it will be important to have indicators so that whatever the facilitation strategy needed, there is some way to first indicate that attention is needed in a group. Some of this might be timed-for example, having a group summarize where they are could be done at intervals based on the ebb and flow of course assignments and content difficulty. Some of the social prompts could be based on shallow indicators like participation and length of posts. Others would need more semantically oriented indicators. For example, the first time that someone mentions or proposes some complex idea, it would be reasonable to ask the group if they understand. Semantic indicators could compare what is being discussed with key course objectives and past discussion. To the extent that these indicators can be identified, these are other places where simple intervention might be quite productive. An area ripe for research is identifying these indicators, understanding what kinds of strategies might be generally useful and the extent to which these indicators are amenable to computational solutions.
In our computational work, we have been developing
techniques for extracting indicators within messages that tell us
something about a student’s orientation at a time point (i.e., a
week of participation within the course) towards the course, which
will enable us to make a prediction about how likely it is that the
student will drop out of the course on the next time point. The
relevant levels of analysis are post, week, and trajectory within the
course. First, we extract indicators from individual
messages. Then we aggregate messages within a week in order to
construct an indicator for a week. We then use a survival analysis
to model the probability that the student with drop out on the next
time point given the value of the variable. In this way, we can
identify risk factors that instructors should be aware of so that
they can focus their efforts to support those students. Indicators
we have explored include social network analysis measures such
as authority and hub scores [
Recent research in the learning sciences has begun to address how to use LA productively [15]. At the same time, MOOCs can provide transformative opportunities for learners if we can identify and support learning communities within the larger communities. Bringing the LA and learning sciences communities together for discussion and joint efforts can provide opportunities to better understand how to facilitate learning communities in this frontier.