Posts made by Tanya Elias

Hi everyone,

After our look at the semantic web and future possibilities, week 4 of LAK11 takes a turns back practical application of analytics in current learning environments.

I've started compiling a list of tools and their potential uses in the LAK Tools wiki and encourage everyone to add tools and suggestions for their use to the wiki.

If you have ideas for the application of LAK but are unaware of a tool that can make it happen, add that as well. Maybe someone else will be able to point you to a tool that can help.

You might also try using some of the tools and add comments about what you liked/ didn't like about them. (Or write out some instructions for using some of these tools, for the technologically challenged in the group wink)


Hi Irwin,

I especially like the question "How will the answers be used?" I did read a good quote somewhere (maybe in the work on action analytics??) that if what is gathered and learned is not applied to improving the system we are not engaging in analytics at all, but rather simply mining data.

At my work, someone came up with the idea of inserting a short evaluation tool at the end of each online training session. It is both an excellent idea and doable. The questions that have not yet been answered (or asked actually as so far they've only lived in my head) are "who is going to look at that information", and "how will use it to ensure the development of better courses?"

(And I'm very open to any potential answers out there smile.)
Hi Viplav,

I couldn't agree more. In order for learning analytics to be of use (both in the corporate world and academics) we need to be looking beyond the learning side of things to find out what people are actually doing (as well as needing/wanting to know) in the real world.
Use case:

Developing training for Customer Care representatives.
Level 1: Baseline performance stats are gathered: New curriculum is developed, agents train, are tested and begin working - same stats are again compared to see how much the new training improved performance. Gives an overall picture of whether new training was effective for the curriculm development team.

Level 2: Baseline stats are gathered. Parts of training and assessments question performance and types of assessment and tied to specific baselline stats. Same stats are remeasured. Gives a more detailed picture of which parts of training were effective for the currciulum development team (i.e., Did learners who scored well on the written assessment questions perform better on the job? or even If learners scored well on question one, did that help them do better on the job?)

Level 3: bits tied together in such a way that at the end of each shift, agent performance is measured and their areas of strengths and weaknesses that day are presented to them. Based on these measures, specific training bits are suggested directly to the agent. Once completed their performance is again measured an presented to them. Curriculum development team gets a report of which lessons are most improving agent performance which they can then use to determine which aspects of lesson design are most important.

I listened to Dragon Gasevic's talk with interest and then I tried to follow George, Dave and Jon's conversation as they discussed it on Friday.

And then I tried really hard to get through some of the course readings and videos on the idea.

One of the examples was Fido. Using the semantic web, you would code "Fido" as a dog and then a dog as a type of animal, which would eventually help computers sort out the difference between references to "Fido the dog" from "Fido the phone" (if they are even still out there).

So here are the things I just don't get:

1. Who puts all of that information in there?

Me? If I write the sentence "Fido barked." I know I'm talking about a dog (and hopefully so will anyone reading it.) Will I really take the time to add the info to code for the semantic web? I'm time challenged already, and if I'm mostly writing for myself and people who know me, why would I spend my time to tag it?

My computer? If my computer can guess for me, then it is often going to get it wrong and what's the point?

2. What if I want to write something with multiple meanings? If I'm complaining about my cell phone that would stop ringing and, "I wish Fido would just quit barking." Again I know I'm comparing my phone to a dog (hopefully the people I'm writing for will to), but my computer? not so sure it'll "get" the reference without a lot of effort and work. And again, why bother?

Whenever we start talking about "teaching computers," I start to get confused. I love the way computers enable us to connect with one another, they are excellent tools. In terms of analytics, Computers do some things very well: gather data, remember stuff, calculate and crunch data - Syntax-related stuff.

People tend to do other things well: thinking, analyzing, sorting and determining - sematics-related stuff.

I may simply be out in left field, but it seems to me that people spending a whole lot of time and effort developing a syntax that enables people to code semantics in a simple enough way for a computer to understand really has both the people and the machines playing to their weaknesses - in my experience not usually a recipe for a successful outcome.

I'd love to hear from people who diagree... Maybe that'll help me "get it"!