Data Mining: Text Mining, Visualization and Social Media

Painting with Flickr

Cartogrammar has an interesting post describing using photographs tied to locations to interpolate average colours in a map. By positioning the pictures in space and analyzing them for colour distribution, then taking a function of the colours of pictures in the same area, some quality of the location as a function of photographs, emerges.

[HT to Gonzalo]

Zonetag: Geocoding Pictures in Flickr

You knew this day would come: you can now upload images to Flickr from a location enabled device and Flickr will take care of the geocoding. ZoneTag works by using cell tower information:

ZoneTag can automatically tag your photos with the location, based on the cell tower, in which they were taken. The location of the cell tower is not known until our user community updates the city, state, or zip code of their photos on Flickr. ZoneTag is then able to map the cell tower to the location.

on the following phones:

Currently, ZoneTag only works on Nokia Series 60 phones. ZoneTag is known to work on 6620, 6670, 6680, 6681, 6682, 7610 models, and it is likely to work on 3230, 6630, 6260 as well.

Note that you need to install an application to get all this geo-goodness to work. Via SEJ.

Some Novel Time Series

Matt Siegler pointed me to Information Aesthetics a while back (from which I have a number of posts in the pipeline). Information Aesthetics points to some interesting data visualization done by Jim Bumgardner (flickr set).

Here Jim has plotted images that contain the tags breakfast, lunch and dinner against the time of day at which the pictures were taken. I like this as an alternate view to the more standard multi-line time series and am thinking of ways in which it could be used for analysing my 24 Hours of Blogs data.

 

In this second image (for photos with the tag 'sunset'), the horizontal dimension represents the date the image was taken, the vertical represents the time of day.

Fun with Tags

In a recent post (August 5th) I finished off with:

The big win with tags is going to be the applications that are built on top of inferences made from them.

I think a link to Flickr's new tag clustering would have been appropriate (launched on August 1st). This is just what I am talking about (putting aside the argument that tags on photos are real meta-data and tags on text aren't). I've played with the usual tests (jaguar - it's a car and a cat, etc.) and haven't yet found results that I really didn't like. Some examples:

• Edinburgh: the city, the G8 protests, ...
• Golf: VW car, sport,...St Andrews
• Vacation: beach,..., Italy, Paris, Hawaii,...

With automated clustering, it is not too difficult to start doing searches and pulling things apart critically. For me, I found the system useful and fun.

Flickr geotagged at 21K

As of now, flickr's database contains 21, 563 geotagged photos.

Flickr geotagged photos nears 20K

I just checked on the geotagged tag and found 19, 437 results. I'll look at the blog trends later this week and see how things are going.

Trends in Flickr Geotagged Photos

When I first became interested in geocoding/geolocation/geotagging I came across a number of applications that use the Flickr API to present geolocated photos. At that time (a few months ago) there were about 1, 400 photos in Flickr with the tag geotagged. Recently, I have been reading about the 11, 000 geotagged images and have been wondering where this big leap came from.

Looking at trend graphs produced by blogpulse, it seems that the attention has a lot to do with the use of Google maps to provide geolocation information. The graph below suggests this:

Interestingly, the limitations of the geolocation service that Google provides gives a big bias to what parts of the world have geotagged photos. In addition, Google Map's less than stellar performance in the UK prompted Steeev to provide a lookup service via streetmap.co.uk (in addition to his most excellent work in providing the original Google script).  The site in question is www.geobloggers.com and the next graph strongly supports the conclusion that it has been responsible for the popularity of geotagging in Flickr:

Interestingly, since the Yahoo acquisition of Flickr, the percentage of mentions of Flickr in the blogosphere appears to have leveled out after a clear upward trend.