Tin Can: learner #analytics for the next #research frontier

What if you are looking for an easy, accessible learner analytics that does not only map access and timings, but actually allows trainers and teachers to take a more in-depth look into the actual learning? THAT is what I am looking for. As I am researching learner interactions in a mobile accessible open, online course – I can see that access pushes forward learner interactions, and even meaningful, constructive learner interactions (research snippets will be shared soon, still getting my thesis together). Looking at Tin Can will reveal a bit of the future of learner tracking and open opportunities for future educational research. The most essential challenge that emerged from my research (at this point) was the fact that meaningful mapping of learning was lacking due to a number of reasons. 

So this is where Tin Can enters (@tincanapi), and thanks to Danny De Witte (@paravolve ) for getting me back on this topic! Tin Can builds on SCORM, but takes learning/training data to the next level. What Tin Can does is enabling teachers/trainers and as such also researchers to see which type of learning appears within a learner community. Not only the formal learning (access to course content, etcetera), but also the informal learning, not only web-based but offline as well as online, and adding ubiquity to the analysis as well. So in a nutshell Tin Can wants to push learner analytics to the next level.

Tin Can is not yet in a version to provide a widely audience a userfriendly version, but … you should have a look at where they are heading (currently 1.95 version, so near public release). What Tin Can does is getting all the diversity of tools that all of us use to build brick-à-brack solution for learner analytics, and centralizing them so that it becomes more intuitive.

The problems tackled with Tin Can as it is developed:

• Mobile tracking – any device tracking: so allowing focus on the actual learning, no matter what device.
• Simulations: allowing to move away from the browser, into where the actual learning takes place.
• Educational (serious) games: gamification is a great way to learn, but it gives rise to a lot of learning challenges, let alone tracking. Currently a lot of serious games are being played by young children, which can actually show the actual learning going on (algebra, math, language…), but this (informal) learning does not seep through to the actual teacher/trainer… however, this could create a much more personalized and in-depth profile of the actual learning of a particular individual.
• Performance support: point-of-need, just-in-time learning is essential for learning. But the barrier with scorm was the actual ‘login, path….’ Which gave rise to a bit of demotivation. But Tin Can takes tracking outside of the LMS, as such it is much more directly accessible.
• Track real world activities: a webinar, training attendance… any tracking that is GPS enabled and such.
• Offline and long running content: spaced learning enhances all of our learning as we know, but this was tough to track, with Tin Can offline tracking will be enabled. Tin Can will not program spaced learning, but will provide data that will make it easier to develop spaced learning.
• Security and authentication: Tin Can will upgrade the security a bit: secure the security between a learning provider and the actual material. It will not be fully secure, but a bit more secure.

Deeper layers: multi-level tracking: in the cloud and on the device:

• Everything is learning: if we do something that increases our knowledge, this is essential to get an idea of learning: making a mistake, writing a blog, reading up on a specific topic …. The holistic learning environment.
• How it works: bookmarks are gathered (in Tin Can), book scanner (to add the books you read), tapestry api addition…. It is all about capturing learning events.
• Key enablers: tracking does not need to be done inside an LMS, it can be launched from anywhere. The asserter of the learning material, can be different from the learning event => as such everything on the web can be used as a learning object, and can be tracked for its learning, it does not be ‘scorm-enabled’.
• Free the data: LRS: this is a great concept, LRS is a Learning Record Store: the thing that accepts all the Tin Can data and enables other instruments to analyse the data. This is where specialized analysis comes in: improve content delivery, content analytics, point towards learning pathways…
• Training data portability: allow to take along training records.
• Personal data locker: that might give the learner herself/himself to learn more on their learning: ideal meta learning tool!

Major challenge: how can one filter out the signal to noise: what makes up relevant learning, what not?

And of course, if you look at Tin Can and put this next to MOOC’s and take socially intelligent agents into consideration, than you must agree that it will offer an amazing learning advancement for the next decennium. And the effect on educational research is ENORMOUS:

• How do people like to learn?
• Which learner profiles are there?
• Can you deduct a professional profile based on learner profiles?
• Can you filter out skills and consequent opportunities based on learning?
• Can you find topics that arise from learning … from what seems to be missing?

This will shed light on actual learning apart from neuroscience monitoring. Great!

If you want to learn more about Tin Can, have a look at their website here (http://tincanapi.com ), or get a broader idea watching this webinar.

#LAK11 the #semantic web and how the intelligent curriculum will enhance our learning

This week was rather busy, developing an online mobile course that will be open to all, following LAK the open course on learning analytics and finalizing a needs assessment, on top of regular work. But! The LAK content keeps intriguing. This week's content focused on the semantic web, linked data and intelligent curriculum.

Intelligent curriculum: or how data analysis will tailor content to the learner
The topic that struck me the most in this weeks LAK-topic was the idea of an intelligent curriculum. Just imagine that all the data that you - as a learner or knowledge worker - go to, examine, read, ... are analyzed and put against the content of the rest of the Web? And just think that an algorithm is put upon that data to see which content might be of use to you, but really of use to you... that would certainly enhance in-depth learning in your field of preference.

So the screening of data would result in immediate relevant content (which affects what needs to be learned, as old/new knowledge can change rapidly). Professional learners will be able to get to relevant up-to-date information much quicker.

The benefits for learning are enormous: it would not only provide me with personalized, tailored content that fits my current hunger for knowledge, it would also allow me to stay in close contact with those who provide that information and share it amongst those who have a similar interest (if an algorithm would keep track of who has similar interests, or who is close to the content I go to). This would have an effect on my (and others) professional networks, for the professional groups will shift from a more localized network to real global networks that learn through connectivity (well, most of us do this already, but professional groups that link up will become more important and most of all attainable).

Semantic course: the course wraps itself around the learner
We - as educators or trainers - might even be in the possibility of creating a course which redesigns itself depending on the prerequisites and skills of a particular learner, thus giving her/him a much smoother learning path, without leaving the learning objective itself.

Moving away from old-fashioned classrooms divided by age, going for skills and enthousiasm classes
This approach of semantic learning might even take us out of the artificially divided classrooms. If we could cater lessons to a variety of learners, they would not be put into classes depending their age, but depending their ability to grasp what is necessary, or depending on their eagerness into specific subject matter.

Creating research proposals in a jiffy
It will also facilitate research: just imagine, that you want to launch a new project in your scientific field? You need to write a proposal, and with an algorithm (AI friend) which searches in your scientific field (e.g.) scholar.google and cross-references this to the data bank of EU/WHO or B.& B. Gates foundation for funding that was granted... you could be on your way to get a funded post-doctorate or project going with much more ease.

Corporate intake: Bert De Coutere launches use cases based on learning analytics
Bert who works at IBM and comes up with great learning strategies and educational games, launched an interesting concept which fits learning analytics. This is what he proposed to enhance learning performance: OK, I'll try one again. Does anyone else feel comfortable adding some use cases as we go along in this course?

The use case:
A young manager quarterly runs a tool to picture his social network, as part of his continuous leadership development. Data mining has shown that successful leaders in his corporation typically have 1/3 of their network amongst subordinates, 1/3 with other managers on the same level, and 1/3 higher up the chain. The tool allows the young manager to see the evolution in his network and get some action points to move it to the desired state.

The semantic web
The semantic web is growing, and it effects all of us who search for content or other things in the vast amount of digital data that is on the web.

• Semantic Web: An Introduction: http://infomesh.net/2001/swintro/
• Welcome to the Metaweb http://www.youtube.com/watch?v=TJfrNo3Z-DU&feature=player_embed (Metaweb was purchased by Google in 2010, but this is still a nice resource on dealing with ambiguity of words/text)
  
• Ray, K (2009) Web 3.0 http://vimeo.com/11529540

As the web will become more semantic, all the data that is on it will be tagged, linked, analyzed... and this should increase our feeling of the 'living web'. Which ties the semantic web into Artificial Intelligence (AI) nicely.

For those interested of hearing more on semantic technologies in learning environments, have a look at the video lecture given by Dragan Gasevic available at http://bit.ly/gfXqEF (cool guy).

#LAK11 what about #privacy when using #data analytics to create #knowledge?

Learning Analytics: EDUCAUSE

View more presentations from gsiemens.

LAK11, the course on learning analytics and knowledge has started and immediately discussions touch a sensitive and complex issue: privacy. While talking about educational data mining, the issue of privacy was raised by many participants.

First a quick note on educational data mining: data mining, also called Knowledge Discovery in Databases (KDD), is the field of discovering novel and potentially useful information from large amounts of data. And with many social media apps gathering massive amounts of data, this field is of growing interests to companies as well as researchers. Educational data mining has a different aim, not to make money, but to map/increase/analyse educational knowledge creation and awareness. What makes educational data mining so interesting, is that it is increasingly using models drawn from the psychometrics literature in education.

The idea behind EDM is a great one: modeling student individual differences in these areas enables software to respond to those individual differences, significantly improving student learning for example. Another key area of application of EDM methods has been in studying pedagogical support (both in learning software, and in other domains, such as collaborative learning behaviors), towards discovering which types of pedagogical support are most effective, either overall or for different groups of students or in different situations. The only thing is, how do you cope with the privacy issues?

Privacy can be good or bad
Gathered data – just like anything else – can be used for the good or the bad. An early form of data gathering was getting all the Jews registered in Germany. Once that was done – for purely administrative purposes at first – it was a small step to gather the Jews themselves for … processing. There is also a recent initiative: in Nepal the third sex has been added to Nepal's next demographic surveys. This is a wonderful thing (I for one do not apply for many 'either/or' categories), but it makes abuse possible.

To me privacy is more relevant to minorities and vulnerable groups, then any other groups in society. If facebook sells gay related data to the Ugandan government, I would not like to be a gay person in Uganda, for you risk being seriously harassed if not killed (at this point in time). No matter when, privacy should be an option that is respected, disconnected from your own online identity, certainly you – as a user – should be able to use a ‘non-traceable’ account for certain reasons?

For instance by using disconnect(ere).

Out of the crowdsourcing cloud, out of the real world?
A way forward to keep your own data private is via: disconnect. But then if all of the people from a specific group use disconnect, their data will no longer be in the crowd, and as such 'non-existent', which makes vulnerable groups even more invisible and less catered to.

perspective of a LAK11 participant
Sarah Haavind, a participant of LAK11, mentions two interesting points on privacy as well:
First: the FB and twitter users no longer clutch to privacy (is this really true and has anyone researched this or the reasons behind it? I do mind and I adjust my privacy settings)
Secondly she adds to the privacy-commercial link: “What if the data-mining marketers know what I like? Isn't it a positive to be bombarded with ads for products I'm interested in rather than a random assortment, given their presence in our lives?”.
She has a point there, but… how can small, very targeted businesses come up through the data analytics that is available?
If I had to choose, I would also like smaller companies to be able to take part in this ad-data-world. I am not interested in starbucks, I am interested in the local coffeeshop burning its own coffee beans, just because I like a variety of tastes. If I go to Ethiopia, I want to listen to local contemporary music, I am not interested in the hashed music that can be found everywhere. So to that effect, I would like it better if I could choose localized data from my profile of ‘local business’ then the big mainstream stuff. But do I need to open up my private life to get access to such time-saving and potentially interesting stuff?

Having said this, gathering and mining educational data might help us a long way to get quick access to some sustainable outcomes (learner preferences, learner critical thinking skills…). But of course, like all data mining, the proof is in the algorithm. If the algorithm is based on a wrong hypothesis, will the results then still be useful? And if data is sold to the highest bidder, then the ethics of that highest bidder better be in sync with my interpretation of ethics.

Metaweb, the web of entities bringing us closer to Web3.0

While the concept of Web3.0 is gaining voices, the actor Metaweb, one of the pioneers in the field of organizing the Web in a more semantic sort of way has just joined Google.

This is quite thrilling news, for Metaweb goes beyond simple tagging and the ever growing problem of how tags are related to the thing they are describing. To get a clear idea, simply watch this very simple and clear movie:



If you are interested, you can join the freebase community that is part of Metaweb. Through Freebase users can add content to the open database, creating entities. Although I signed up as a member, the registering process had a glitch in Firefox at first, I could access it through Internet Explorer. When I tried a bit later, Firefox was working ok as well for accessing Freebase.

There is not much on education yet, so I made myself part of that group and started looking around. If Metaweb keeps growing, Google might be nearing the semantic web, very curious on how it will work out. At the moment it is very USA oriented, but it might catch on globally as Google has encapsulated them. Anyway it is an interesting idea.

Wonder wheel from google for learning

Back from an invigorating and wonderful vacation (while writing papers), aaaaahhhh super.

To start of my blogposts, I thought I would keep it simple. When writing for the Master course I am following (master in distance education), I started to use Google's wonder wheel, and what a wonderful search option this is.

Wonder wheel works easy, some quick steps:

• you type in a concept word ('eLearning', 'constructivist'...) in Google search engine;
• you click on the 'wonder wheel' option in the left menu bar;
• and the window gets a new look, with a wonder wheel that indicates related concepts on the left side of the screen and the traditional google text search results on the right side.
• when you click on one of the options in the wonder wheel, another wheel pops-up with again the concepts related to the link you have chosen. Additionally the search options also change in the traditional search text on the right side of the screen.
  

It works well when you want to explore a certain topic, for it gives some sort of overview of the possibilities and you can get a quick insight in the variations linked to the topic.

Why do I like it? It is a bit more semantic, it works with more visually organized links, simple and neat. If you have not tried it, give it a go.

My 8 learning predictions for 2010

In follow-up of the predictions I made in 2009, I take a go at predicting the learning evolutions for 2010 (oh, how I wish I had an oracle to advise me).

I also linked this post to the Big Question for January 2010 in a quest for plans or predictions, posted by Tony Karrer on the Learning Circuit blog.

Overall I feel that learning research in 2010 will favor pedagogy over technology as the prime focus, and ubiquitous learning will be the central goal. In a more elaborate sense, here are my 8 predictions for 2010:

Semantics: Learning will become the rave again. Web2.0, education2.0, mobile learning, eLearning, TELearning … we as learners will be focusing on Learning again for the simple reason that the learning is all around us, and done with every tool we have.

Ubiquitous learning: ubiquitous learning as a term becomes more common place, especially with net books and mobile devices still on the rise. Because ubiquitous learning is coming closer to our learning reality, and because it focuses more on the learning aspect and less on what type of technology is used, I think it will be one of the main educational foci in 2010.

Social media will become more streamlined, and all present: the last couple of year’s new social media applications sprung up. In 2010 I predict that it will become more streamlined, once people are used to certain software that serves a specific purpose; they tend to stay with it for a longer amount of time. Social media will become normal for any type of learning, because it favors networks and connections.

Pedagogy: for the last couple of years technology was at the center of innovative learning. In my opinion, now that these (social media) technologies have taken off, the focus will come back to the learner her/himself. Pedagogy will overtake technology as the main focus in new media learning research.

Cognitive factors: in 2008 and 2009 some new initiatives were taken to start using new technologies and resulting innovative pedagogies, e.g. Connectivism and Connective Knowledge course, Quest for learn. For 2010 I think the cognitive will be increasingly in the picture.

Low resource areas build more applications by themselves, and for themselves. Africa and other low resource areas are moving forward at a rapid pace. There is a growing number of African developers and activists that make a difference and enable citizens to participate in society, and engage in learning. This trend will increase, as more projects are developed or useful mash-ups are put together to get a message out to the world or boost their region and its people.

Augmented reality: as the applications for mobile devices grow, augmented reality is becoming a much more interesting area to explore. It allows all users to get a clearer view on topics that are of interest to them: is an engineering project on target? Which shops can I see from where I stand? What church is this? Just take a look at the Augmented Reality Team video’s.

Networking and connections gain even more ground: for any long term project that wants to take off, the strength will be in the network and the connections related to it. Building a strong and relevant personal network will be crucial for any work. But in order to be willing to build a network and exchange knowledge with all the connected people in it, trust will be crucial. Trust is a good characteristic for any type of living.

What are your predictions for 2010?

(Another great cartoon by Nick D Kim, nearingzero.net.)

the Horizon report 2009 from Educause

The Educause Horizon Report for 2009 has just been published. It makes predictions about the emerging technologies that are likely to have a significant impact on education. This year's predictions are: mobile devices, cloud computing, geo-everything, the personal web, semantic-aware applications, and smart objects (always linked with examples).

With its 36 pages it is a great report to read. Not always that surprising, but I bet you will be able to use some of the links to your benefit.

For more details see the full report