Posts Tagged 'Tracking Trends'

M.Sc. thesis and job hunting

Well it’s been a long time since I last posted! about 12 weeks which has mostly been working on my M.Sc. thesis and finding a job for when I finish in Edinburgh at the end of August. Both are done now so I’ve got a bit more free time again (which will be mostly enjoying the Edinburgh festivals for a week!).

The thesis changed slightly from influenza tracking to trying to forecast the belief of the population about the recent swine flu outbreak. This ended up looking at ways of extracting and aggregating information from Twitter and blog posts then trying to forecast the value of a prediction market. Prediction markets along with text mining are both very interesting so I’ve learned a lot and enjoyed the whole project. I’m going to post about the work and what I found from it in a post soon, summarising the interesting bits from 70 pages!

On the job hunting front I have a job at Mendeley down in London starting mid September which I’ll hopefully blog about when I start there. The work they do is very interesting trying to bring science up to speed on the web, they describe themselves as “Last.fm for research” which kinda gives the scope of their goals. So I’m leaving academia finally but not quite, as the work I am doing will be very much helping many people doing research around the world.

Advertisements

Ad hoc trend tracking (or where’s it snowing?)

The heavy snow falls last week in the UK have caused quite a lot of chaos, a lot of which is due to not knowing how bad off different areas were. Ben Marsh created a mashup of a snowmap last Sunday, before snow had fallen over much of the UK, which plotted posts on twitter with the #snowuk tag against a photo and report of the snow level. This shows how quickly it is possible to directly track things over the internet using an ad hoc organised system over services like Twitter.

Contrasting to my last post, where the trend was tracked indirectly, this is directly tracking on outbreak of snow with tags from people. This is tending towards ideas from the semantic web by making information more machine readable, and twitter is encouraging this with the internet population. This is not done in a semantically strict way though but using ad hoc tags and meaning decided by people as they are needed, as we have learnt from the past with the web.  This is probably more the way people would want to interact with the semantic web, but it does remove some of the key ideas of interoperability and data linking.

Mashups like this won’t be able to accurately or reliably predict anything but they do have a very fast reaction time. This makes them very useful to people, which is what matters, so how can we start using systems like this on a more global scale?


About Me

I'm a student at Edinburgh University studying Artificial Intelligence. Find out more about me and my projects on my website

Twitter Updates

Advertisements