Learning Analytics

Here we've got a classmate PC demo that shows off Richard Beckwith shows off Classmate Assist which supports users seated or standing at the desk or table. This is an example of context aware computing. There are visual sensors that recognize the items on the table and instruct and walk the students through a series of educational tasks. The goal is to support existing curriculum and practices of teachers.

I've been following developments in intelligent tutoring systems for a while,  and find it interesting to see how researchers are combining artificial intelligence, learning theory, affective computing, and sensor networks to create applications that might prove to be useful and effective.

In the first commercial application of CeNSE technology, HP and Shell will build a wireless sensing system to acquire high-resolution seismic data. By vastly improving the quality of seismic imaging, the new system will allow Shell to more easily and cost-effectively explore difficult oil and gas reservoirs.

We thought it would be useful to propose one possible taxonomy - we call it the Snice* taxonomy - of what a data scientist does, in roughly chronological order: Obtain, Scrub, Explore, Model, and iNterpret (or, if you like, OSEMN, which rhymes with possum).

20 years ago, Tim Berners-Lee invented the World Wide Web. For his next project, he's building a web for open, linked data that could do for numbers what the Web did for words, pictures, video: unlock our data and reframe the way we use it together.

Learning analytics is the use of intelligent data, learner-produced data, and analysis models to discover information and social connections, and to predict and advise on learning. EDUCAUSE's Next Generation learning initiative offers a slightly different definition "the use of data and models to predict student progress and performance, and the ability to act on that information". Their definition is cleaner than the one I offer, but, as I'll detail below, is intended to work within the existing educational system, rather than to modify it. I'm interested in how learning analytics can restructure the process of teaching, learning, and administration.

A short introduction to the semantic web

The comments to the video are also interesting.

Social network analysis [SNA] is the mapping and measuring of relationships and flows between people, groups, organizations, computers, URLs, and other connected information/knowledge entities. The nodes in the network are the people and groups while the links show relationships or flows between the nodes. SNA provides both a visual and a mathematical analysis of human relationships. Management consultants use this methodology with their business clients and call it Organizational Network Analysis [ONA].

A way of using massive amounts of data for medicine and forensics (16 minute video)

The British universities, Oxford and Cambridge included, are under siege from a system of state control that is undermining the one thing upon which their worldwide reputation depends: the caliber of their scholarship. The theories and practices that are driving this assault are mostly American in origin, conceived in American business schools and management consulting firms. They are frequently embedded in intensive management systems that make use of information technology (IT) marketed by corporations such as IBM, Oracle, and SAP. They are then sold to clients such as the UK government and its bureaucracies, including the universities. This alliance between the public and private sector has become a threat to academic freedom in the UK, and a warning to the American academy about how its own freedoms can be threatened.

LAK course website.

A data analysis service for the learning science community

Hilary Mason presents the history of machine learning covering some of the most significant developments taking place over the last two decades, especially the fundamental math and algorithmic tools employed. She also exemplifies how machine learning is used by bit.ly to discover various statistical information about users.

Needlebase allows you to view web pages through a virtual browser, point and click to train it in understanding what fields on that page are of interest to you and how those fields relate to each other. Then the program goes and scrapes the data from all of those fields, publishes them into a table, list or map, and recommends merges of cells that appear to be mistakenly separate. It's very cool and it lets non-technical people do things with data quickly and easily that we used to require the assistance of someone more technical to do.

Also, "liking" itself is a very limited way of expressing your thoughts on something. You might like pizza, but no anchovis. If you dislike a Pizza Anchovis, what does the system store? On the other hand, some interesting analogies and recommendations can be done with relatively simple like/dislike statements and multiple choice answers.\n\nHunch should incorporate serendipity.

For the past several years, EDUCAUSE publications have described the emergence of two complementary forces: (1) the growth of "academic analytics" in higher education and the knowledge services needed to support seamless sharing and leveraging of contextualized data/information; and (2) the escalating accountability demands that are driving performance measurement and improvement initiatives. These forces converged in the July/August 2007 issue of EDUCAUSE Review, which showcased their potentially transformative impacts on higher education

"This study analyzes the outcomes at more than 380 higher education institutions. It looks at what the chosen strategies have accomplished, in what ways institutions use the data they collect, whether institutions are investing more resources in tools that enable them to collect and manipulate management information, and the degree to which information and analysis are being used to support institutional decision making."