Mapping Google News

CousinLarry writes "A neat project called Buzztracker.org has been mining Google News for over a year and keeping track of relationships between geographic locations mentioned in articles. The results are some really cool maps that actually seem to reflect the "buzz" of the day - check out the Vatican clusters from earlier this month, or the global New Year's chatter. You can also dig down into the articles from which the maps were generated."

Comments

Re:MetaWeb

[winkydink]

SEMANTIC WEB!

Thank you Tim (Berners-Lee) Didn't know you were a /. reader. The question remains, while it's very interesting (and cool), what does one do with the aggregated data?

thats old news..

[ShaniaTwain]

..no, literally. its made up of old news..

This gives me a great idea...

[MisterLawyer]

I should start a website, beertracker.org, to keep track of my daily buzz.

Nelson Mandela != Nelson town

[Anonymous Coward]

It looks like the code needs a bit more tuning. http://www.buzztracker.org/index.html lists Nelson, NZ, as one of the hot spots. Clicking on that lists a bunch of articles about apartheid. I think the site code misinterpreted a reference to Nelson Mandela in one of the articles.

Does Google mind?

[IBeatUpNerds]

I remember about a year ago or so, there was a guy who was mining google news to produce an RSS feed. IIRC, google politely demanded that individual stop offering this to people. I can't find the article to cite this, maybe someone can help? At any rate, I wonder how google will feel about this.

New Business Plan!

[Fyz]

1. Map out the world in x and y coordinates.
2. Feed google buzz data into huge neural network.
3. Predict location and magnitude of future events.
4. ???
5. Profit!

Re:New Business Plan!

[Ingolfke]

I actually spent the last 3 months of my life writing something very similar to this for my PhD thesis. My work was slightly different then what you explained though. Basically I take the Google data, use it to prime the network, and then feed in historical data from a particular news site into the neural network. The app processes the data, and predicts which news events the news site will report on in the coming days. I've run this application against Slashdot, since such a wide range of topics are reported on here, and have found that the application can guess 7 stories from the next day 87% of the time. I didn't have nearly this much success with other news sites, so I decided to figure out why I was so successful. I found that the nueral network was simply reporting on news events that happened more than 3 weeks ago, contained words like 'Star Wars', would search for anything about Google and then would add the question "Are they becoming evil?", would take all Microsoft and EFF press releases, and somehow managed to pull every 17th email from Linus Torvald's inbox, would repost every 19th article, and would occasionally take a story about someone being prosecuted and insert "Your right online" in front of the original news source's title. Unfortunately for me, the nueral network seemed to learn too much from Google and now requires that I become a member of its club before I can see any more future stories.

Re:Definitely on the Nifty List

[FuturePastNow]

This site has another list, of the sources Google News uses (something Google refuse to publish). Also an interesting use of data mining.

This is pretty nifty

[aftk2]

While mapping the news activity over the whole world is certainly cool, I can see this having an even greater effect when applied to a smaller area. For example, if you're moving somewhere, you could easily see crime news applied to the particular region. It doesn't have all have to be depressing news, either: you could use such a "buzz" indication to find out information like the following:

• find where there are lots of new jobs being generated
• view up-and-coming areas by their positive "buzz" (new creative hot spots, architecture, etc...)
• find areas of town with great new restaurants

I think this is where it starts to get exciting (and more useful). Mapping Google news? Meh. Mapping the northwest, and giving that information to Citysearch? You betcha.

Re:Can't say I'm surprised.

[alphan]

Well when you think about it aren't those the exact places you'd expect to be hotspots?

It is good that you could expect that. For me, there are a lot of different factors that add to complexity. Neutrality of Google being one, the fact that Google News is in English being another.

Really cool but suffers from a common problem...

[terraformer]

That being one level of hierarchy to display complex data. China (Top with .09%) is top dog because all international press refer to china as a whole and fails to reference individual places in china (ie; Guangdong Province) despite the sheer size of the country. Therefore, China is over represented when looking at news. However, in the case of Gaza (the second highest at .08%), the exact opposite occurs where Gaza steals all of the thunder from the larger Palestinian issue (Gaza is one of two territories in question and is not in Palestine, the place where all of the problems in the middle east originates from).

If, they represented this in hierarchical format, the middle east would dominate by picking up points from children Gaza, West Bank and Palestine (not to mention Iraq). Baghdad is probably a good example here. How much actually happens in areas outside of Baghdad proper but gets labled baghdad anyhow.

Re:Can't say I'm surprised.

[jonno317]

Well, actually if you look at the bottom of google news you'll notice that it's in 21 languages other than English (counting Canadian English, Australian English, and the like as separate languages...so maybe a few less than that technically). But I'd say that Google is in enough other major languages to not be considered biased (at least as far as languages are concerned). If buzztracker.org is biased toward English, then I would say it's because of their choices and no fault of Google.

Nov 3rd? Dec 26?

[mzieg]

I have to question the results a bit. Look at the archive for November 2004, especially around Nov 3rd . Anyone remember any "buzz" about Ohio? Maybe a Florida 2000 reprisal? "Battleground States," anyone? That was a hugely geographic news event, and it doesn't even register on their chart. Likewise, Sumatra barely merits a blip on Dec 26. I'm not sure I'm buying this.

What we have here is one computer algorithm aggregating another computer algorithm's assessment of "newsworthy," with no provision for hindsight or fluff-vs-historical weighting. It's a neat idea, and the graphics are pretty slick, but I don't see any real value here.