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..

Can't say I'm surprised.

[CSMastermind]

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

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.

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.

That's cool

[Red Moose]

That is finally some news for nerds. About fucking time.

What a cool site, and it works very quickly and is not overflowing with advertising crap?

This gives me a great idea...

[MisterLawyer]

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

virtual sightseeing

[tedtimmons]

not news (pun intended), but here is a compilation of neat google maps I've been collecting:

http://perljam.net/notes/interesting-google-satell ite-maps/

-ted

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.

BuzzTracker?

[Storlek]

Apparently they didn't Google their own name, or else they would've noticed the name was already in use for a fairly popular music composition program.

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.

Animations

[Doctor O]

Now, take the data and put up some nice animations, archive the first 100 articles or so and put it into some nice database to mine for interesting stuff. Should not be too hard to script together the data gathering, you can already start fetching stuff while developing the functionality and frontend.

Someone wanna join? This cries 'distributed database'... ;)

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.

Through With Buzz

[Doc Ruby]

The big circle in the US is called "Washington", which is rated at 03%. It obscures "New York" in the GUI. Boston is available, and the only other US buzz is Grand Rapids, apparently on the strength of a local paper's report 2 days ago of a resident killed in Cairo. I find all that hard to believe, or at least to make into any sense. The GUI is unusable, and the mapping of data to "reality" defies sensibility. I think the buzz has gone to their heads, and they should put the pipe down quick.

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.

Why do we need this?

[A Sea and Cake]

Why do we need this?

A map that showed where the stories getting the least attention that contained certain keywords - famine, Schiavo, wobbegong, whatever - came from would strike me as more interesting.

We already know where the stories indicated by this map are coming from, because they're taking up ridiculous amounts of space on the front pages of newspapers everywhere.

Chasing the Pack (and running from it)

[doom]

What I like about google news is that it's an incredibly easy way of keeping an eye on what has been called the "pack journalism" problem. Just as an example, trying doing a google news search on "Count Every Vote Act": that's consistently turned up less than 100 hits since it was announced. Is there some reason it's not newsworthy? Similarly, when the Ohio recount thing was going down last year, it took *forever* for it to punch through as a top-level story. Evidentally the pattern is something like a story is dead until the AP Wire runs it, and then a thousand other news "sources" pick it up.

I've had the thought that it might be cool to implement an anti-news site that would do something like show you links to New York Times stories that have never been referenced by the top page of Google News.

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.

Re:Nov 3rd? Dec 26?

[Random Chaos]

I understand your point, however I think it is partially based on a false premise: In reguard to Nov 3rd. The site tracks cities, not states.

After checking Dec 26, 27, 28, and 29th they do have Indonesia, but it doesn't show up until the 28th (and then under Jakarta only). I would guess this is due to them not having Sumatra or Banda Aceh in their keyword search system.

I also notice that most cities in the US other then Washington and New York seem to almost never show up - could it be that their "selection of articles" is a bit limited (refering to the above's 2nd paragraph)?