Forgot your password?
typodupeerror

Software Tracks Blogosphere Mood Swings 149

Posted by CowboyNeal
from the manic-depressive dept.
holy_calamity writes "Dutch researchers have figured out a way to measure the mood swings of the blogosphere. It can pick up peaks of flirtiness from bloggers around Valentine's Day and drunkenness at weekends, the plan is to create a search engine that returns the prevailing mood in the blogosphere about a topic. Companies are already interested in using it to track consumer confidence. What's the mood of Slashdot on this one?"
This discussion has been archived. No new comments can be posted.

Software Tracks Blogosphere Mood Swings

Comments Filter:
  • by XorNand (517466) * on Thursday April 20, 2006 @07:28PM (#15169395)

    This is old news. Just blogs? Bah! Color me unimpressed. I've already harnessed the power of the Internet to track the mood of the entire planet: http://www.howisyourday.com/ [howisyourday.com]
    • by Umbral Blot (737704) on Thursday April 20, 2006 @07:33PM (#15169424) Homepage
      Are you trying to be funny? Getting a small group of people who speak english to and are willing to put up with voting / verification is in no way a representitive sample. Now if you went into their blog and determined their mood from the text, that might be cool.
    • by JordanL (886154) <jordan.ledouxNO@SPAMgmail.com> on Thursday April 20, 2006 @07:33PM (#15169427) Homepage
      FTA: On Valentine's Day, there is spike in the numbers of bloggers who use the labels "loved" or "flirty", but also an increase in the number who report feeling "lonely".

      So let me get this straight... all this to discover that people either think about their relationships or lack or relationships on Valentines Day...

      This is the ultimate geek software. "What is this strange thing... emotion... I'll build a software program to explain it to me."
    • Not to mention, TFA doesn't explain how this is accomplished from a technological point of view. Makes me suspect that all they are doing is just a frequency analysis painted with Kinkaid colors and various insane words from the "blogospheric" vocabulary.
      • by daviddennis (10926) <david@amazing.com> on Thursday April 20, 2006 @08:51PM (#15169817) Homepage
        Actually, the article was pretty clear on how it worked, but I'll explain it a little better since I guess (from your post) it was confusing.

        When you write a blog entry in LiveJournal, you're give an opportunity to select a "mood" from a dropdown list of moods. So you can say you're

        happy
        sad
        loved
        excited
        lonely
        (etc)

        by just picking the appropriate word.

        Now, as you know, emotional data taken from a dropdown list at the end of writing a blog post might not be worth taking all that seriously, but it's data, and you can try to analyze it.

        Now, some people are laughing at this by saying that it should of course be obvious that people are likely to be feeling loved or lonely around Valentines' day. But actually this is an important observation, since it says that what people pick in the dropdown can be related to real events. Of course we know people are loved/lonely on Valentines' day; what we didn't know is if what they picked on the dropdown was meaningful. Now we know it is, and so (in theory) we can use this to predict events or people's behaviour based on what they say.

        The Harry Potter example showed that this could in fact be done, and this means that further reasearch might be promising. For example, let's say there was a "suicidal" mood in the list. It would be interesting to track whether actual suciides were predictable or at least more likely after showing those moods, so that an early warning system for such behavior could be created.

        On paper, it seems possible that lives could be saved that way, which makes this a non-trivial application indeed. To support my theory, note the previous news reports we've seen here that note that suicidal behavior was often predictable in hindsight from what people wrote on their Myspace profiles. If this could be determined from moods, which are trivial to check automatically, it might be a very interesting result indeed.

        Hope that helped people's understanding.

        D
        • Meh, its easy to say suicidal behavior is easy to predict in hindsight, but how many people match all the criteria that people apply to the suicides who are not going to commit suicide?

          All automated flagging will do is annoy a lot of people and discourage them from posting anything honest about how they feel. What they really need is someone personally noticing and taking action, not some automated spider ran by someone who could give a fuck about you. Its the same reason guidance councelers don't really he
          • That's a very good point, if the Chinese government (or even our own governments) got hold of something like this, and started locking you away whenever you selected a drop box option of 'suicidal', or said 'rubber chickens', then we're well on the way to having our own Big Brother.
        • by bnf (16861)
          So if there is a corelation between mood and blog posts how about using this data set to "prime the pump" of a Bayesian filter which would analyse blog posts on other sites and determine how likely it is that the blog post is one of these moods.
    • That's pretty cool, actually. Would be neat if you could localize it more, I know there are days when my town just feels angry =P
  • Blogosphere Mood (Score:5, Insightful)

    by NitsujTPU (19263) on Thursday April 20, 2006 @07:29PM (#15169399)
    My mood always turns sour when people refer to the "Blogosphere."

    I'll take a few fewer buzzwords a day, and call my Dr. next week to see if the situation improves.
    • by Anonymous Coward
      Better not blog that too bodly in your blog or the blogerati are going to get a coupla of pipe-hitting bloggers to get blog evil on your ass. Blog.
      • every time you want to say "blog", just go ahead and say it. but afterwards add: "crying out loud". like this: "blog crying out loud". you won't notice when you start saying "for crying out loud" instead.
    • It sounds like they're doing interesting work, as long as nobody takes it too seriously or starts, like, trying to make money off of it (in which case you'll see some form of astroturfing zombie army emerge to tweak the bogosphere's Mood Indices.) What happens to LiveJournal moods in September, or graduation time, or Christmas break, or release-date-for-some-popular-game?
    • Livejournal's mood setting, or imood.com has been using tagging to do what they say for a while now.
    • What is this "special relativity"? I hate buzzwords. Just call it the ether like everyone else. I mean they're close enough...and nobody's gonna need to use "special relativity" in calculations anyway, it's just hypothetical.
    • We could refer to it as the noosphere if that would make you happier.
    • Well, imagine it as the terrain that was partially demolished to make way for the Information Superhighway.
  • Reservation...as with most topics that involve personal tracking, and large corporations having access to personal information (and yes, I consider my mood personal information when it's being used to a company's advantage).
    • Sounds like "Dutch researchers" have selected and invented a group of buzzwords to get them on the homepage of Slashdot. Impressive.
    • Re:Reservation... (Score:2, Insightful)

      by Gyga (873992)
      I hope whatever they use listens to robots.txt
    • Re:Reservation... (Score:4, Interesting)

      by shawb (16347) on Thursday April 20, 2006 @08:01PM (#15169586)
      I understand your concerns, but information that you yourself put on a webpage should not be considered private. If you don't want personal information to get out, don't post it in a public forum. Besides, it doesn't sound like this particular piece of software is really collecting personal information; all it does is look for spikes in a particular mood tag, and then parses through the text in the publically readable text to find unusual words. If this helps companies figure out what products actually excite people, then they will come out with products that people actually like (if used properly.)

      As a company (and especially as an investor) I would, however, take any information gathered through such a technique with a grain of salt or two. It seems that it would be close to trivial for a company game the system and set up enough accounts or bribe enough bloggers to tip the scales one way or the other, essentially creating inter-corporate astroturphing.
    • A very simple lesson in life. If you don't want something listened to, don't shout it in public(that's essentially what a blog is). If you don't want people to see what you're doing don't do it in public. You don't have that level of privacy in public. You can copyright your works to stop people from copying them, but if you stick it on a blog you're giving everyone license to read it and everyone includes marketing types.
    • Don't post your mood in a public place if you want it to remain private. Ta da!

      For my next trick, I'll teach you how to keep strangers from seeing your bare genitalia.

  • by koweja (922288) on Thursday April 20, 2006 @07:29PM (#15169401)
    From whiney to really pissed off?
  • So... (Score:5, Funny)

    by TechnoGuyRob (926031) on Thursday April 20, 2006 @07:31PM (#15169414) Homepage
    The blogosphere is female? Oh wait, we're on our way to understanding it. Nevermind then.
  • by TheDarkener (198348) on Thursday April 20, 2006 @07:32PM (#15169415)
    +1 Smart ass
    +1 Pro Linux
    -1 Corporatism
    -1 Proprietarism (is that a word? Happy 4:20..sorry)

    And...of course

    +1 CowboyNeal

    Disregarding the above blabber, this software sounds so flippin' cool. I've always thought about the overall mood of people, and if there's relation between it and a certain period of time. Like a website that simply asks "Are you happy right now?" or "Are you sad right now?" Very useful information! *gazes up at sky*
    • Like a website that simply asks "Are you happy right now?" or "Are you sad right now?"

      Nah... noone would ever bother to set up such a website. [howisyourday.com]
    • I've always thought about the overall mood of people, and if there's relation between it and a certain period of time.

      Not just that, but you could attempt to track the mood in relation to data. If a popular news item was making the rounds, what was the overall mood of those passing it. Did the information affect the mood and how?

      Scary stuff.
  • skeptical (Score:2, Redundant)

    I am highly skeptical about this. Opinion extraction in general is a difficult area of data mining with enough problems in areas as (relatively) well defined as Amazon reviews, etc. To try to measure the general mood of the "blogosphere" with any measure of accuracy is useless at best. And just how are you supposed to even roughly verify the "mood" for arbitrary ideas?? Random human sampling and verification just won't cut it...

    Companies might be better off using a magic 8 ball...

    • Re:skeptical (Score:3, Informative)

      by TechnoGuyRob (926031)
      Erm...I don't know if you read the article, but they extract the moods from LifeJournal posts, not analyze the text or anything like that.

      Assuming that people are honest about their moods (and why wouldn't they be?), I don't see why this wouldn't be accurate.

      Apparently, your mood right now is ignorant.
      • Yeah but that kind of average is too unspecific. Even in the TFA they seemed to try to sell it as something more larger than that. I totally got the impression that their reported mood was supposed to reflect on specific recent events. It's either that or a fun crawler toy you can make in less than an hour. Which one is it?
        • Yeah but that kind of average is too unspecific. Even in the TFA they seemed to try to sell it as something more larger than that. I totally got the impression that their reported mood was supposed to reflect on specific recent events. It's either that or a fun crawler toy you can make in less than an hour. Which one is it?

          A bit of both. From what I understood, first, they crawl all the pages and figure out what the general mood profile is. Then, they try to identify unusual mood settings. If they fin
  • by cno3 (197688) on Thursday April 20, 2006 @07:33PM (#15169421) Homepage
    The software, called MoodViews, was created by Gilad Mishne and colleagues at Amsterdam University, The Netherlands. It tracks about 10 million blogs hosted by the US service LiveJournal.

    Monday - Mood: Emo
    Tuesday - Mood: Emo
    Wednesday - Mood: Emo ...
  • userMood=random(3); switch(userMood) { case 1: user="Depressed"; break; case 2: user="Drunk"; break; case 3: user="Happy" break; } return 0; On another note, I thought most companies didn't like their users blogging.
  • by JoeCommodore (567479) <larry@portcommodore.com> on Thursday April 20, 2006 @07:34PM (#15169429) Homepage
    Was a yellow-green now looks like its changing to a deep purple.
  • by anomalous cohort (704239) on Thursday April 20, 2006 @07:35PM (#15169436) Homepage Journal

    The Blogosphere (a collective term encompassing all weblogs) isn't really addressable so how can it be measurable? It's not like there is a URL to "the blogosphere" and how would you know if you have successfully polled all blogs on the Internet? This appears to be a subtle commercial for LiveJournal.

    • right. it's a BETA.
    • The Blogosphere (a collective term encompassing all weblogs) isn't really addressable so how can it be measurable? It's not like there is a URL to "the blogosphere" and how would you know if you have successfully polled all blogs on the Internet? This appears to be a subtle commercial for LiveJournal.

      Find as many things that seem to be blogs and take the mood of them. See what people are on about.

      Blogs occur on private web-sites, a whole boat load of blogging services, and everything in between.

      I don't see

  • And? (Score:2, Insightful)

    by Jayjay75 (468973)
    What would this tell us, exactly? That people are more inclined to get drunk on weekends and are grouchier on Mondays than on other days? This is something we don't already know?
  • Mixed Signals (Score:4, Interesting)

    by _Sprocket_ (42527) on Thursday April 20, 2006 @07:40PM (#15169467)
    Great. Humans already have trouble [wired.com] interpreting the tone of electronic messages. On top of that, let's have some algorithm tack on the subtle clues so necessary for proper interpretation of human communication. After all, computers have already shown a bang-up track record [wikipedia.org] dealing with Human languages.

    Cool project though. Hilarity will undoubtedly ensue.
    • Subtle cues? It's tracking what mood LiveJournal users pick from a drop-down menu. It's not that hard to come up with an algorithm to determine what someone's mood is when they explicitly tell you what their mood is.
    • Re:Mixed Signals (Score:3, Informative)

      by patio11 (857072)
      I could see this working. Is it any harder to tell if a message is, say, depressed than it is to determine if a message is a commercial pitch?* Because pure-"Bayesian" analysis of spam routinely gets 95%+ accuracy, which if we're not talking about the content of any specific message but are trying to measure trends between time periods is plenty good enough. Lets take a particular application: Apple wants to know if their iPods are still the hottest thing on the planet. Simple process: have a team of hu
      • Because pure-"Bayesian" analysis of spam routinely gets 95%+ accuracy, which if we're not talking about the content of any specific message but are trying to measure trends between time periods is plenty good enough.

        Yes - I'm sure mood can easily be interpreted with Bayesian analysis. Human communication isn't much more complex than spam, after all.

        Quick exercise to the reader - was that earnest or sarcasm?

        Cool idea though. I'm sure there is some degree of analysis that can be done. It'd be interesting

    • Large. The human ones have already the trouble to interpret the dial
      tone of the electronic mails. On this, leave have a certain point of
      algorithm to us on the indices subtle if necessary for the suitable
      translation of human transmission. After all, the computers already
      showed a formidable professional experiment treating human languages.

      Refreshing the plant nevertheless. Laughter that follows without the
      doubt.
  • Slashdot mood? (Score:5, Insightful)

    by TechnoGuyRob (926031) on Thursday April 20, 2006 @07:43PM (#15169485) Homepage
    There's almost 30 posts and only one of them has been modded up (once, to funny no less)? I think I can predict the mood of Slashdot about this:

    Indifferent

    Or as a LiveJournalist would say:

    like i don care man
    • I think it's because these sorts of things fall under the following catch-all that a more technically proficient crowd innately understands, even if not sure of the exact reason (which I put in another post):

      Your invention/analysis uses science/technology in an unscientific/non-technical/inappropriate way to prove something trivial/meaningless/completely wrong.

      People use the keyword 'love' more around Valentine's Day? Brilliant! Of course they do. Valentine's day comes with huge amounts of social programm
  • zerg (Score:3, Interesting)

    by Lord Omlette (124579) on Thursday April 20, 2006 @07:48PM (#15169514) Homepage
    They did this for Livejournal. It would always, without fail, return "tired".
  • One word: (Score:3, Funny)

    by Xaroth (67516) on Thursday April 20, 2006 @07:53PM (#15169547) Homepage
    "Sardonic."
  • The ability to automate the aggregation of all this information and display it is pretty cool, and the target for this data mining is the general population is pretty cool.

    Of course things like trends will skew it so its not really what people are thinking, but rather what theier online personality wants other people to think they are thinking.... but still, very interesting!
  • by StressGuy (472374) on Thursday April 20, 2006 @08:02PM (#15169589)
    "Geeky"

    There I go pissing karma away again....

  • by Gothmolly (148874) on Thursday April 20, 2006 @08:03PM (#15169595)
    Just as useless, and as unprovable. Next, specialized computer technology to detect the color underwear most bloggers wear?
  • Amusing, but fairly pointless unless the thundering herd of sheeple that live their lives by what's hot/popular go for it - at which time it'll become profitable in a limited way for a limited number of people.

    Otherwise? yawn

  • Website still up? (Score:5, Informative)

    by Chris_Jefferson (581445) on Thursday April 20, 2006 @08:18PM (#15169662) Homepage
    This can't be right.. the website is still up. Perhaps that is because no-one can find the link To the actual moodviews website [science.uva.nl].

    I can't decide if I should feel guilty for posting this..
  • Does this mean we all have to start tagging?

    That's great...brilliant idea...[/sarcasm]
  • So according to the mood measurement graph, the mood of bloggers becomes more "sleepy" late at night at around the time when a large number of the population generally go to bed.

    That's an amazing demonstration of how technology can reveal insightful and as yet unknown facts about humanity that we never would have been able to predict without this fantastic new tool.

    I can't believe how cool.... oh wait... Doh!

  • by jigjigga (903943)
    Whats next? podcastosphere? TrendytechwordO'sphere?
  • by syrinx (106469) on Thursday April 20, 2006 @08:42PM (#15169774) Homepage
    I've found thier top-secret code:

    Mood of LiveJournal: angsty

  • The article focuses on the moodview, which analyzes the tags that bloggers use. While this may lead to some interesting data manipulation procedures, I think that Mood Teller [science.uva.nl] is more interesting, it actually scans the text, and makes a guess on the mood. Then it compares its guess to the actual data that was gathered using the blogger tags.
    • While individual applications can vary in how good they are, or are not, the general area of research is an interesting one. Yeah, OK we can spot Emo kids angsting on LJ, but couple Mood Teller with some context and you start building something like what Neal Stepheson describes in Interface.For example, what it the mood of people when they are thinking (writing) about Iran? How about Apple's Boot Camp software?

      Of course there are a few non-trivial issues to solve like biase (people are more likely to blog
  • by Quantam (870027)
    This is just another weapon for Bushitler's arsenal against civil liberties and free thought!
  • by spezz (150943)
    What's there to track? Just leave it set to "pissy" and you'll be fine.

  • and the mood on 4/20 (Score:3, Interesting)

    by SecureTheNet (915798) on Thursday April 20, 2006 @09:10PM (#15169892) Homepage
    According to their page, under "Which moods are hot?" they list "high"

    http://ilps.science.uva.nl/MoodViews/Moodgrapher/? high [science.uva.nl]

    Notice the sudden spike in the "high" mood on 4/20? I thought that was interesting.
  • All these pop-AI things come down to one thing: keyword search counts. Create a bag of keywords, count the number of times they show up in some arbitrary (usually Web these days) search, and make an arbitrary determination of what each bag of keywords means. Then pass it off as some sort of special intelligent sensor or machine intelligence, add in some buzzword references to biological brain structures or psychological processes, and pretend you are some genius.

    But guess what? It's just a set of arbitrar
  • by bennomatic (691188) on Friday April 21, 2006 @12:03AM (#15170664) Homepage
    Why didn't this story just point directly towards the Mood Tap [moodtap.com] web site?

  • Shoot all marketing arseholes. Is that opinionated enough for you?
  • Thats interesting.. it shows a spike for 'horny' followed a few hours later by a spike for 'depressed' which I presume means all those horny people didn't get laid again..
  • Now, I don't have MPD, but I do have very different blogs for very different occasions. And I guess I'm not the only one who tries to spin here. Corps use the tool of a blog by far more aggressively than me, and they create moods rather than displaying one.

    So tracking those would not track the mood bloggers have, but the mood they'd like to create.
  • Moodgrapher (Score:3, Interesting)

    by themusicgod1 (241799) <themusicgod1.zworg@com> on Friday April 21, 2006 @05:11AM (#15171513) Homepage Journal
    what, like Moodgrapher? [science.uva.nl] I don't understand what's so new?
  • There's a little gadget that skims the XML version of livejournal and examines the standard moods from all public posts. (You can type whatever you want into the mood box, but it disregards these custom moods.)

    Here [brainporn.org] it is, for which it's author will be eternally grateful for me posting, I'm sure.

    Anyway, I realize that it's not the same thing, but in my small deluded brain, I can dream that something I knew about was the inspiration.
  • It's because of the blogosphere (as much as I hate that word). It's the fact that you can get an overview of the current thoughts and emotions of the entire human population (or at least a huge chunk of it, certainly well above the boundaries of "statistically significant").
  • and apparently the Internet is flucuating between horny and pretty creepy.
  • I wrote a web-based mood tracker that looks at particular strings entered into blog and discussion board posts related to whether President Bush should be impeached or otherwise removed from office.

    Link to Bush-Be-Gone Index [stevemagruder.com]

    No matter your politics, I think how the index moves up and down depending on particular events is somewhat fascinating.

Wherever you go...There you are. - Buckaroo Banzai

Working...