Data Mining: Text Mining, Visualization and Social Media

Veep Attention

After McCain’s strategic (one should say maverick?) choice of vice president, it is informative to look at how the news translated into attention. Certainly, according to BlogPulse, McCain’s choice got more attention than Obama’s.

However, it didn’t manage to pierce the Obama attention ceiling (3.478 versus 3.275).

ICWSM 2009 – San Francisco Bay Area

ICWSM 2009 is going to be held in the Bay Area. We are moments away from publishing the CFP, so stay tuned!

WWW Social Networks Track

The CFP is up for the WWW track on Social Networks and Web 2.0.

Nice Synth (nicesynth)

This is an example of something like a Photosynth art form - a synth still life (still synth?). With this type of synth, I like the way that you can essentially view the subject from angles that were not in the original set of images by manipulating the view of the point cloud.

Photosynth 2 from matthew hurst on Vimeo.

I've been tagging interesting synths in delicious with the tag nicesynth.

Second Beach Synth

We just got back from a great trip around the Olympic Peninsula. Here’s a synth of Second Beach.

Photosynth Launches

Today, Live Labs launched one of our flagship projects: Photosynth. Photosynth is departure from nearly all approaches to sharing and browsing photographs. It takes a collection of pictures of a scene or object and computes points in the 3d space which represent points on the surface of the objects depicted. This point cloud then provides an immersive geometry which the user can navigate – a reconstruction of the scene – to view the images.

The videos below demonstrate how this point cloud describes the scene and how images are located in this inferred space.

Photosynth 1 from matthew hurst on Vimeo.

Here is the synth used in the above video. To create it, I took several pictures of the Kamakura Daibutsu and simply dropped them into Photosynth! Once you have Photosynth installed, have fun with the synth below. Hit ‘p’ to toggle between different modes (photos and/or point cloud) or use the control key. +/- provide zooming, and there are even Doom-style controls for another approach to navigation. When the halo appears – you can grab it to rotate the scene around its centre.

Congratulations to everyone involved with Photosynth. This is a huge, visionary project, and personally one of the reasons why I joined Live Labs.

Using Google Insights to Track Linguistic Communities

There are many fun things you can do with Google Insights. Putting in a term in a specific language, one can get a picture of where in the world people speaking that language live. Here are some examples (I used the fish for most translations).

Russian: пицца (pizza)

Japanese: 寿司 (sushi)

Korean: 피자 (pizza)

Dutch: bioskoop (cinema)

etc.

Wanted: Social Media Scientists

Live Labs is looking for researchers in the field of social media analysis. We are interested in all computational aspects of this discipline, including:

• Text and data mining
• Visualization
• Applications
• Theory of social media
• Content aggregation
• Computational Linguistics (especially subjectivity)

In addition to being leaders in their fields, Live Labs scientists are passionate about building systems and applications; having their contributions used in many products and having a real impact.

Please contact me if this sounds like fun!

The Unintentional Revolution

I’ve recently finished reading Clay Shirky's excellent book ‘Here Comes Everybody’. Even if you are knee deep in this field, it is still worth the read due to the quality of the writing and thoughtful structure. Essentially, Shirky says: certain web technologies have lowered the cost of organizing groups and these newly enabled communities, and the infrastructure that supports them, can change the world in ways both new and old.

Much of the revolutionary speak around the current technologies and applications found on the web focuses on the network: what happens when we can create and organize in networks that focus on our electronic identities. But is there a revolutionary line around our ability to aggregate all of the data that these networks and these technologies create?

To answer this question, we must recognize what is different about this data, how it is created and where it exists. How are weblogs different from the pre-social web? A description of these differences will include people (not documents) being the centre; non-html publication and distribution; the intentionally subjective nature of the content; the temporal qualities of the content; etc.

While I don’t yet have a thorough statement describing the data miners revolution due to the growth of social data, I do believe that a big part of it is the fact that we can create analytics that mirror intentional statements in the networked world. For example, digg is an intentional site where contributors digg or bury online objects. Something similar can be done via counting links found in any type of social media. Another example is in the area of market or product research. The intentional model is to directly ask people questions about brands, products, etc. With a large enough data set, we can turn the opinions found in social media into an unintentional focus group.

Google Insights

I’ve not yet done a deep dive on Google’s latest expansion of their Trends tool: Insights for Search. But, take a look at this post from Pingdom which uses the tool to evaluate the popularity of social networks globally. Below is a sample for Friendster.

This tool deserves attention no just for the analytical and visualization aspects, but also for the strategic importance of commoditization in this space.

[Via ebiquity]