Language Lounge
A Monthly Column for Word Lovers
They Also Serve Who Only Kvetch and Tweet
Have you ever sent a really EPIC tweet? There are different ways to answer that question: I'll proceed with one way that probably doesn't occur to you. The EPIC tweets under the microscope here are tweets that are of interest to Project EPIC — that is, Empowering the Public with Information in Crisis. It's a National Science Foundation-funded project, carried out jointly by researchers at the University of Colorado at Boulder (full disclosure: my day-job employer) and the University of California, Irvine.
EPIC is developing computational techniques that use information people generate using social media in disrupted situations. That's not disrupted like when your usual bus is running late this morning, but disrupted like you get when there is a hurricane, tornado, earthquake, explosion, invasion by aliens, or other disruptive emergency.
Ultimately EPIC wants to create a set of applications intended for use by members of the public that will help people pool online information and information sources, whether official ones or unofficial. The best information should enable people to make the best decisions in critical situations, and making optimal decisions for whatever unexpected disaster you find yourself in the middle of might make a big difference — even between life and death.
EPIC depends on two things that are fairly reliable: our communications network, which seems to have enough built-in redundancy to withstand major disruptions; and human nature, which can be depended upon to speak up when something is not right. Twitter, Facebook, and other social media enable everyone to speak with a slighter louder voice than ever existed before the Internet.
Lest you start to think that now is the time to raise your hand to be an EPIC first-responder, that job is already taken. It's a job that belongs to everyone — at least, everyone who uses social media — and EPIC is usually not much interested in individual tweets, posts, and status updates; it's interested in dozens or hundreds or thousands of them (geotagged ones are particularly helpful) that can be processed computationally to develop a clear picture of what is actually happening on the ground, drawn by the people who are there. Reliable, peer-generated information sources for EPIC are emergent — you don't know who the EPIC heroes will be until the event happens.
That sounds really cool, you may be thinking, but how is it going to work, and what has it got to do with language? The toolbox for EPIC is mostly a collection of natural language processing (NLP) techniques, some of which we have talked about in the Lounge before. One of the chief tools is sentiment analysis, a widely-used NLP tool that attempts to get a grip on what people are thinking and feeling on the basis of what they say on social media. We talked about it a bit in the Lounge from July 2013, in discussing a study that made judgments about the happiest places in the United States.
In a time of crisis or emergency, happy talk will be of little interest to anyone who needs critical information, but the same tools that can detect pockets and patterns of happy talk can also zero in on feelings at the other end of the scale: anxiety, fear, anger, panic, and the like. People express such feelings in language with an identifiable set of words in every language and by analyzing the usage patterns of such words (consider, for example, scared, afraid, disaster, catastrophe, danger, or emergency) in geographically identified areas, scientists can develop at least a fuzzy picture of where the most dire things may be happening.
Another promising area of research for EPIC is event detection, another topic we touched on in a Lounge from last year. People like to talk about events: the ones they plan, the ones that are happening, or the ones that they fear may happen. The poster-child of event detection is the verb. Hardly anything goes down that cannot be talked about with verbs, and researchers can analyze the usage and frequency of the many verbs in tweets that may indicate that something has gone terribly wrong, or is about to.
Humans, like many other organisms, have an instinctive fight-or-flight response. What sets us far apart from other species who enjoy this adaptive behavior for situations of acute stress is that we have language as well, and when we have the opportunity, we are likely to use language to notify our flight decisions to others. Twitter and other social media enable modern hominids to broadcast their decisions like never before, and the collection of such shout-outs is another valuable data source for EPIC.
Long before social media came along, scientists were interested in what motivates people to make a protective decision — that is, a decision to act in order to avoid risk or hazard. Early research in this area had already determined that people consider severity, susceptibility, barriers, cost variables, and quality of information in deciding whether, for example, they should evacuate an area threatened with a hurricane or nuclear disaster. Findings from this early research are being integrated into the corpus of language that the Twitterverse provides in order to zero in on what people think about before deciding whether to stay or go.
When a forewarned disaster looms, an inevitable news story accompanying it is the interview with the stalwarts who choose to ignore evacuation orders. The media has long given sensationalist attention to such individuals, who seem to enjoy the opportunity of a microphone thrust in their faces in order to spout clichés about their defiance. Of much greater interest to authorities are those on the flipside of the media darling: the individuals who respond to an evacuation order by leaving immediately. The developers of EPIC are hopeful that they can develop a predictive model of who will evacuate, who won't, what factors help them to decide, and how long it will be before they make up their minds.
Computers, like people, love to learn by examples; computers in fact are not very good at learning except by examples, and for this, they need training data — that is, data that can be used to discover predictive relationships among discrete data points. Disasters in the modern world come along at a fairly steady clip, and so today, scientists can collect data from recent disasters in which people tweeted and posted their fears, anxieties, and decisions, to build a model of what the relationship is between what people say and what they do, or are likely to do.
Project EPIC is beginning to look at geo-tagged Twitter data from Hurricane Sandy and trying to identify evacuators based on their location and what language they used to signal their imminent departure. The "tweets before the storm" constitute a goldmine for researchers to discover nuggets of information that they hope will prove useful in the management of future disasters.
Join the conversation
Comments from our users:
Or more like, hardly anything goes down that can be talked about _without_ using verb--?
As an aside, I've read that Twitter can be used for predictive analysis for crime, the stock market, and other phenomena. The wisdom of crowds, indeed.
Orin, thanks for this, which I had no knowledge of at all. I have a question which needs a bit of preamble, so please bear with me.
Re the Black Friday scrimmages and near-riots in stores, a psychologist remarked that most of the people who were displaying such reprehensible behaviour (trampling over people, etc) would have condemned such behaviour if asked their opinion *individually* prior to the event. Perfectly rational individuals may act irrationally en masse. We sort of know that already.
I wonder, therefore, will EPIC possibly be misled by its assessment of mass responses by consulting tweets, which are posted by individuals? An individual who tweets "A hurricane is approaching but I've been in enough of them not to panic and leave!" may quickly change his mind when he sees a line of cars passing his house with horns blaring. And he might be too busy grabbing his treasures to bother tweeting his change of mind!
So my question is, can EPIC sufficiently distinguish between individual and mass responses to disaster (both before and during) just by using Tweets?
And conversely, doesn't the Twittersphere, by creating a mass response out of thousands of individual responses, induce a self-perpetuating response that can lead to irrational and perhaps regrettable actions, such as revolutions that haven't been sufficiently thought through or prepared for?
I can see what EPIC is aiming for, but I just wonder if there is an inherent danger in trusting the mass response engendered by lots of individual reactions. EPIC may conclude that yes, the correct response is flight when individuals left to their own considered thinking, without mass influences, may rightly conclude that in their individual situation and circumstance, staying and fighting is the correct response.
Geoff and Mike, I happened on this headline yesterday: http://www.natureworldnews.com/articles/10784/20141129/facebook-twitter-unreliable-sources-of-human-behavior.htm
So yes, there are serious limitations to what may be gleaned from the Twittersphere, and the trick for researchers will be first to separate the baby from the bathwater, and second, to be clear about which to keep and which to throw out.
Are the designers of EPIC considering other options? For instance, what if people got used to tweeting the word FLIGHT if they were thinking of choosing that option, or STAY if not? Even I could do that (I subscribe but never tweet)!
Indeed, by encouraging people to use social media in this way, with key words provided for them to use in various scenarios, such as during an epidemic or extreme weather, the public might feel they were *knowingly* helping the common cause rather than feeling they are being unwittingly used to that end.
Since it's illegal and impractical to read individual tweets, I presume EPIC is using the same 'key words' technique as our security services employ to detect terrorist activity. So EPIC counts all the tweets containing the word 'afraid' or 'apprehensive' if there is a storm warning, while also counting tweets containing 'confident' or 'safe', to gauge the balance between flight and fight responses to the warning. This allows the authorities to hone their warnings.
Are tweets geo-locatable? And does the collection software gather more than single words? I'm wondering if it can distinguish, for instance, between 'afraid' and 'not afraid'?
Anyway, as you say, Orin, it's early days, but it has caught my imagination now that extreme events are becoming more common - especially, it seems, in the United States - or is that just me because I watch the CNBC news every night?!
True it is that our human species has --maybe all on our own, or perhaps not--come a long way in overcoming and figuring the exigencies of life; But we are still herd animals.
Of the individuals we may lay claim to as being an ancestor some one of them might all on his own have made the brilliant decision to tackle and overcome a threat to survival-- he/she might all by him/herself have made the supreme effort not only to stand on the back two limbs but to remain there in order to be able to see over long grasses--but from that point the individual not only retained self-identification as a herd animal but that part of human nature was actually honed and amplified with increased awareness of a basic need for and dependence upon âthe tribeâ (the herd) for nourishment (survival !!)
At this time--and I would venture to suggest for a period extending far into the future--we certainly do need the bright spark individual who is capable of assessing from a solitary point, with unique ability to perceive multi-layered possibilities at depth,-- but we are still herd animals and we do still need the support of âthe others' to alert us to danger, to provide the kind of company which encourages adrenalin flow (just as necessary for âflightâ as for âfightâ).
oh you can call such borrowed strength 'false bravado', or 'mass hysteria', you can put down the likely outcome of being influenced by "...'mass response'... leading to... 'irrational and perhaps regrettable actions' â¦."--but how many individuals can you really find who, through solitary action either physical or intellectual, made decision to "stay and fight as unique hero" and who have really actually survived ??
I am one of the first to denigrate the logic of the masses (too often it seems that they are incapable of following any syllogistic exercise which has more than 1 or at the most 2 steps--"All dogs have 4 legs, My cat has 4 legs, Therefore my cat is a dogâ¦." but I am convinced that we are still very much in the mould of having the consciousnesses of both unique individual reasoning abilities and reflex herding.
I suspect the next stage will happen much more quickly than have other evolutionary phases--I suspect it will encompass both recognition of human beings as unique individuals and also awareness of them as mere components of the whole, the group.--furthermore: I think that it will be accelerated by the very technology so many of us aged people fear and hate--
Meanwhile I continue to stomp on, dragging my tail and munching the tops of treesâ¦.
Grandma in Vancouver, Canada
These are very interesting questions, firstly whether it is *true* that individuated humans are morally and socially biased towards tolerance and equality, and secondly, if this is indeed true, WHY that might be the case?
Conversely, is it the herd instinct to be intolerant of the Other and to assume that violence is the best way to achieve social goals? And likewise, if this is true, why?
I am curious why you think that modern technology might square the individual/herd circle.
Will it be by allowing us all to be (highly educated) individuated beings in our physical solitude, while satisfying our herd instincts by herding online and in social media? Isn't Japan trending that society, where women aren't able to tempt young men into the real life dating herd because they are too happy alone with their computers in cyber-touch with the whole world?
You're right that Tweeters are not currently a representative slice of the population--I'm not one. But in a disaster, everyone is equal and in equal peril, which somewhat negates the demographic bias of Twitter than emerges in other contexts.