In our latest episode, the penultimate in the pilot series, we explore the topics that are likely to be moving up the curve of the hype cycle this year—adaptive learning and learning analytics. Like many of the topics in the pilot series, we could have made an entire series about this one. (And maybe we will at some point.) But since the first adaptive learning product faculty will run into is most likely to be from a textbook publisher, we interviewed McGraw Hill’s Al Essa and Pearson’s Jason Jordan about their respective takes on what this trend is all about.
Tag: analytics
-
Digging into the Purdue Course Signals Results
Update: Mike has written another post clarifying the intuitions behind his math.
The spectacular Mike Caulfield casts a skeptical eye on the Course Signals data:
Only a portion of Purdue’s classes are Course Signals classes, so the chance any course a freshman takes is a Course Signals course can be expressed as a percentage, say 25%. In an overly dramatic simplification of this model, a freshman who takes four classes the first semester and drops out has a has about a 16% chance of having taken two Course Signals courses (as always, beware my math here, but I think I’m right). Meanwhile they have a 74% chance of having taken 1 or fewer, and a 42% chance of having taken exactly one.
What about about a student who does *not* drop out first semester, and takes a full load of five courses each semester? Well, the chance of that student having two or more Course Signals courses is 75%. That’s right — just by taking a full load of classes and not dropping out first semester you’re likely to be tagged as a CS 2+ student.
In other words, each class you take is like an additional coin flip. A lot of what Course Signals “analysis” is measuring is how many classes students are taking.
Are there predictions this model makes that we can test? Absolutely. As we saw in the above example, at a 25% CS adoption rate, the median dropout has a 42% chance of having taken exactly one CS course. So it’s quite normal for a dropout to have had a CS course. But early on in the program the adoption rate would have much lower. What are the odds of a first semester dropout having a CS course in those early pilots? For the sake of argument let’s say adoption at that point was 5%. In that case, the chance our 4-course semester drop out would have exactly one CS course drops from 42% to 17%. In other words, as adoption grows having had one course in CS will cease to be a useful predictor of first to second-year persistence.
Is that what we see? Assuming adoption grew between 2007 and 2009, that’s *exactly* what we see.
I’d like to see somebody at Purdue (or Ellucian) respond to the questions that Mike raises. Matt Pistilli, are you listening?
-
LoudCloud Systems Announces Adaptive LMS General Release
One of the trends that I’ve been tracking in the LMS market is a move away from the monolithic, all-things-to-everyone enterprise LMS solution. There are several different approaches challenging this model, but the general theme is that the ed tech market needs more flexible, targeted approaches to directly support teaching and learning needs.
The news today is that LoudCloud Systems is officially announcing their LMS solution’s entry into the general higher education and K-12 markets as described in a Campus Technology article. In this announcement, LoudCloud promises what they describe as the “first fully adaptive and configurable Learning Management Systems for Higher Education and K12”. While I cannot judge yet how successful this vendor will be with their strategy, I think the announcement is significant for the LMS market for two reasons.
- LoudCloud appears to be providing the first disaggregated LMS on the commercial market; and
- The system has an integrated analytics engine that supports personalized content delivery.
-
Breaking Up the LMS: K-12 District Selects Part of LoudCloud Systems’ LMS
This is a guest post by Phil Hill from Delta Initiative, follow on Twitter @PhilOnEdTech or his blog
It’s been a busy week for LMS announcements, and I expect more announcements leading up to EDUCAUSE. First, the Hawaii Virtual Learning Network (for K-12) is moving from Moodle to Blackboard, which as Michael Feldstein points out, is a new development to watch. Then Brown University announced they are moving from Blackboard to Instructure’s Canvas as their LMS. This morning, Jefferson County school district, the largest district in Colorado, announced that they have chosen a module from LoudCloud Systems’ LMS as the basis for their Instructional Improvement System.
That’s right – they purchased a module from the overall LMS. Normally I cover higher ed more than K-12, but this announcement is worth watching since it shows how the New Mentality in LMS Market is or will be changing our expectations on what an LMS can provide.
-
Moodle, Wave, and Widgets (Oh my!)
Scott Wilson , Paul Sharples, Dai Griffiths and Kris Popat have an article up on their work embedding Wave-enabled widgets into Moodle using Wookie. (Try saying that ten times fast.) What they envision is very similar in a lot of ways to what my former SUNY colleagues and I were thinking about when we proposed a Learning Management Operating System. Of course, that was 2005, so we were thinking about portlets rather than widgets. The lower barrier to entry and client-side nature of widgets are game changers.
Anyway, it’s a very good piece, well worth reading. A couple of points jumped out at me. First:
Rather than just being a like-for-like replacement, the Widgets update in real-time without any page refresh, and this affects user behavior. Rather than clicking links to launch tools or to view content, the Widgets encourage more of a “monitoring” mode of operation, with users navigating to a course page, then leaving it open in the background, occasionally bringing it into focus to see if any new conversations were happening in the chat widget, or the voting results had changed.
If this finding bears out with further research, it could be a fairly big deal. For one thing, it has the potential of making the learning environment a lot stickier and more Facebook-like (in a good way). At the same time, it should force some pretty substantial refactoring of core LMS tools, which simply aren’t designed for monitoring. The two models are likely to clash.
Here’s another interesting—and problematic—bit:
Another consequence of Widgets is that far less tracking information is available at a micro-level, as interactions with Widgets are not made available to the VLE. This implies that a new model for tracking will need to be developed for such systems; this may be a useful opportunity to reconsider tracking in more sophisticated terms than page views and hits. For example, it may be useful to separate out measures of attention, using something like APML[12], and measures of user effort, using something like User Labor Markup Language (ULML[13]).
The thing is, we’re just now beginning to develop models where we can identify at-risk students and, more importantly, help them self-identify and self-remediate based on the data from the learning environment. The fact that this trend is in direct tension with the whole Web-2.0-in-the-learning-environment trend is underappreciated. We need to solve this problem.
-
Thoughts on "Analytics" and Privacy
Last week at the IMS conference, the LTAC (Learning Technology Advisory Council) had an interesting and, I think, fruitful discussion about “analytics.” In this context, the term umbrella term covers various types of data analysis that would be useful in helping ensure that more students learn more and better. One example that came up a couple of times in the discussion was some work done by John Campbell at Purdue University showing that analysis of some basic stats out the LMS (e.g., how recently and frequently a student has logged on) will predict the likelihood that the student will persist in the class and pass it with a very high degree of accuracy. The idea is that if you could get an early warning that a student is at risk, you can intervene and hopefully help that student get through a rough spot.
Of course, developing this kind of tool raises all sorts of interesting problems, not the least of which is privacy.