Data Mining: Text Mining, Visualization and Social Media

Thumbtack from Live Labs

Yesterday, Live Labs launched a project called Thumtack. The project is an exploration of a collection metaphor for information objects found on the web. It supports the grouping and analysis of objects and the sharing and collaboration of these collections with different communities. Steve Drucker, whose voice you will hear on the Thumbtack video, has been working in this area for a while as a principal scientist hear at Live Labs specializing in the area of HCI and UX/UI.

For me, in addition to the social aspects of the project, the most exciting thing about this area in general is the fundamental change in how it views information presented on the web: from a collection of pages linked by hyperlinks to an underlying space of information articulated via online resources (including web pages). The revolution, when it comes, will be a result of this shift in how we think about web published data and any project (Live Labs or otherwise) that starts behavioural change is well worth the investment.

672 Obama Headlines

Vertigo has a great demo of Silverlight’s deep zoom capabilities (a product of Live Labs). I hesitate in calling it a demo as I believe that deep zoom is going to be a horizontal new UX element and that this is a valid application of it. It can take you from this:

to this:

via a very quick, slick spin of the mouse wheel. And you can keep going…

[thanks to Kevin for the tip]

Photosynth Receives Award

Photosynth is a winner of the PC Magazine’s Annual Technical Excellence Award for software.

The hints about the Photosynth technology from Microsoft Live Labs tantalized for months, and the release of Photosynth this summer did not disappoint. It takes your collection of photographs, identifies the features in each, compares all of them for overlap, and links those spots to create a three-dimensional position. What you end up with is a single 3D-esque shot compiled from all the smaller shots. You can even use it to generate a "synth" of an object. Photosynth uses Seadragon technology, which is neat in its own right: Seadragon innovates on "zoom" relationships. It's how you keep drilling in smoothly to ever more detailed visual information in WorldWide Telescope.—EG

Congrats to the team.

[PC Magazine might like to check up on the progeny of our technology though – WWT doesn’t use Seadragon as Jonathan Fey explains in this interview.]

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.

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!

Let the TechFest Begin!

It is almost exactly a year ago that I joined Microsoft. I was lucky enough with my timing that my first week here coincided with TechFest. TechFest is an expo put on by Microsoft Research to showcase new and ongoing innovation internally. What I remember most about that first week was how impressed I was at the diversity of work being carried out by MSR. While this event is an internal one, there is also a press day which takes some of these research projects and demonstrates them to the media. This year's press day was yesterday.

The work that we've been doing in the social media space here at Live Labs is not yet ready for the outside world. However, one of the projects that builds on our work - done by a group of colleagues at MSR - was on display at yesterday's press event.

BLEWS (blogs and news) is an application that sits at the intersection between social media (in this case, weblogs) and main stream media (textual news). The project web site best sums up the goals:

While typical news-aggregation sites do a good job of clustering news stories according to topic, they leave the reader without information about which stories figure prominently in political discourse. BLEWS uses political blogs to categorize news stories according to their reception in the conservative and liberal blogospheres. It visualizes information about which stories are linked to from conservative and liberal blogs, and it indicates the level of emotional charge in the discussion of the news story or topic at hand in both political camps. BLEWS also offers a “see the view from the other side” functionality, enabling a reader to compare different views on the same story from different sides of the political spectrum. BLEWS achieves this goal by digesting and analyzing a real-time feed of political-blog posts provided by the Live Labs Social Media platform, adding both link analysis and text analysis of the blog posts.

Here is a close up:

The application has had a reasonable amount of press coverage:

• Microsoft's cutting edge on display at TechFest
• Gushing over Microsoft Research at TechFest 2008
• TechFest takes a World View
• One big science fair for hundreds of Ph.D.s

Congratulations to the BLEWS team: Michael Gamon, Sumit Basu, Dmitriy Blenko, Danyel Fisher and Christian Konig.

Note also that we have a paper on the system to be presented at ICWSM in a few weeks.

Geeking with Greg

Exciting news: Greg Linden is going to be joining us here at Live Labs next week. Congratulations to Greg!

Listas: Live Labs Technical Preview

Live Labs recently announced a tech preview of a new social content platform names Listas. From the Live Labs blog:

Listas is a tool for the creation, management and sharing of lists, notes, favorites, and more. It allows you to quickly and easily edit lists, share them with others for reading or wiki-style editing, and discover the public lists of other users.

Listas has one fundamental data structure - the list. The list allows for indenting - effectively the creation of hierarchical lists, or sub-lists. In addition to wiki-like editing of list data, Listas comes with another key component: a toolbar. With the toolbar installed, users can - upon encountering something they would like to store in a list - push data to their account on Listas. The toolbar page explains:

Quickly navigate to Listas web site.

One click to add a link to your current page to a list.

Select page content and click once to add it to a list.

Highlight web page "clippings" and add them to a list

Listas also offers a community aspect which allows for the sharing and joint editing of lists.

PhotoSynth on PBS | Wired Science

As written about on the PhotoSynth site.

NASA/Live Labs PhotoSynth

Adam writes about some more great demos of PhotoSynth, this time in collaboration with NASA.