Thursday, March 6

GeoLife Microsoft Research Project

More coverage of Microsoft Techfest in the Seattle Times.

GeoLife, a project from Microsoft's lab in Beijing, uses mobile devices and cameras enabled with global positioning systems to automatically create a log and multimedia presentation chronicling a person's travels through a city. The log is displayed on a map that could be shared with a friend.

A tourist in Beijing, for example, could select an area of the city on the map and search for information. Other people's travel logs from that area could be returned as results.

See the homepages of Yu Zheng and Xing Xie for details.


Initially, I thought of the Reality Mining project at MIT, but the two are pretty different. The Reality Mining project is more simply data mining over communication and location based activity data.

Microsoft Research Demos SearchTogether and CoSearch Collaborative Search Projects

Microsoft TechFest, a giant research science fair for geeks, is happening this week.

The Seattle Pi has an article covering a few of the search related projects:
One, SearchTogether, is an Internet Explorer plugin that puts a sidebar into the browser. It's meant for collaborating on multiple computers, possibly in different locations. In the sidebar, each person can see and follow the Web searches that a friend or co-worker has conducted related to their project or common interest. It uses a Windows Live ID login.

The other, CoSearch, is designed for collaborative searching on a single computer. For example, a person using a mobile phone in the room can control a cursor on the computer screen to click on a link and transfer the result to the phone, even as the people using the PC follow a different link.
Researcher Meredith Morris has more details available on her page devoted to collaborative search.

Other non-search highlights of the the event included the WorldWide Telescope and the Singularity research operating system for academics and researchers. In other news, the IE8 beta was released and there is a lot of buzz about that, watch the Channel 10 introduction video.

Why [search log] data matters by Hal Varian

Hal Varian posted about user data and privacy on the Google Blog.

What I found interesting from the article"
Over the years, Google has continued to invest in making search better. Our information retrieval experts have added more than 200 additional signals to the algorithms that determine the relevance of websites to a user's query.

So where did those other 200 signals come from? What's the next stage of search, and what do we need to do to find even more relevant information online?

We're constantly experimenting with our algorithm, tuning and tweaking on a weekly basis to come up with more relevant and useful results for our users.

But in order to come up with new ranking techniques and evaluate if users find them useful, we have to store and analyze search logs. (Watch our videos to see exactly what data we store in our logs.) What results do people click on? How does their behavior change when we change aspects of our algorithm? Using data in the logs, we can compare how well we're doing now at finding useful information for you to how we did a year ago. If we don't keep a history, we have no good way to evaluate our progress and make improvements.
...
Storing and analyzing logs of user searches is how Google's algorithm learns to give you more useful results. Just as data availability has driven progress of search in the past, the data in our search logs will certainly be a critical component of future breakthroughs.
Google and the other major search engine are constantly using search log data to improve the quality of their results, it's good to hear some details emerging.