lie detector
Latest
Researchers are working on a lie detector to sniff out false tweets
Sure, some less-than-true statements on Twitter are innocuous, but the social media network's vast audience means it has huge potential to spread inaccurate, even dangerous, information. Citing examples like the 2011 London riots and accusations of vote-rigging during Kenyan elections, researchers at the University of Sheffield have introduced the concept of a lie detector to analyze information shared on Twitter and other sites. The EU-funded project, dubbed Pheme, will sort online rumors into four categories: speculation, controversy, misinformation and disinformation. Additionally, Pheme will evaluate sources to determine their authority; tweets from the BBC would hold more weight than an unverified user's, for example. The system will also search for sources to confirm or deny information in a tweet, following social media conversations about a given topic to eventually determine what's true and what's false. Hypothetically, users would be able to view info about a rumor's accuracy via a virtual dashboard. To test out of the project, scientists will be running trials with the Swiss Broadcasting Corporation and the Institute of Psychiatry at King's College London. Clearly, Pheme's goal is to verify news on a national and even international scale -- so your Twitter fibs about amazing weekend plans are safe, for now.
Texting: the truth serum of the 21st century
The University of Michigan and The New School for Social Research has found that if you want someone to tell you the truth, you should text them. Dispensing with the lie detector for job interviewees, academics found that people gave more honest and detailed answers via SMS than over the phone. The team believes it's due to the lack of time pressure and not having to produce a pleasing answer for your interrogator. If the findings continue to provide similar results, it looks like Steve Wilkos could be replaced with a smartphone.
Russian ATM uses voice analysis to tell when you're lying
Credit card applications via automated teller are all the rage abroad these days. That's why Russia's Sberbank is using Speech Technology Center's voice recognition system in its new ATM to tell when you fudge your financials to get approved. Like a polygraph, the technology senses involuntary stress cues to ferret out fib-filled statements -- only instead of using wired sensors, it listens to your angst-ridden voice. Designed using samples from Russian police interrogation recordings where subjects were found to be lying, the system is able to detect the changes in speech patterns when a person isn't telling the truth. Of course, it's not completely accurate, so the biometric voice data is combined with credit history and other info before the ATM can crush an applicant's credit dreams. And to assuage the public's privacy concerns, patrons' voice prints will be kept on chips in their credit cards instead of a bank database. So, we don't have to worry about hackers stealing our biometric info, but we're slightly concerned that we'll no longer be able to deceive our robot overlords should the need arise.
Eye-tracking lie detectors inch a little closer to reality
If lie detection is your thing, choices aren't exactly scarce: you can go with Lego for the kids, Skype-centric for remote fibber identification, or even use a headband if you can corral your suspect long enough. Hoping to add to that list is the University of Utah, whose eye-tracking lie detector has been licensed to a local company in order to explore its viability as a commercial product. As with Blade Runnner's Voight-Kampff empathy test, Utah's methodology revolves around monitoring things like eye movement, pupil dilation and response time -- with the major difference being that you're trying to identify truth evaders rather than skinjobs. John Kircher, one of the lead researchers, claims results so far have been as good as or better than those obtained with polygraph testing, though he admits the project is still in its early stages. No worries, though, we're sure they'll perfect the technique in time for our post-apocalyptic, Vangelis-scored future.
No lie: voice stress analysis on iPhone
So here's the thing. If the new iPhone app Agile Lie Detector really works, and I'm fairly convinced it does on some level, do you really want to have something this potentially powerful in your pocket? Do you really want an application that could ruin your marriage, destroy your faith in humanity and wreck your respect for authority, and on top of all that, pay $7.99US for it?Yeah, you do.I was dying to try this thing out. Truth is, I was skeptical that this app would be anything more than a novelty item. But I had a serious moral dilemma on my hands. What kind of person interrogates his wife and purposely tries to make her cough up lies just so he can test out an app for a blog post? Me. So I was off, for 15 minutes, asking her question after question, spanning a wide spectrum, none of which I'll get into. Very little of my prodding resulted in anything more than a blip on the Lie Graph. None of my deep, life-altering questions drew a response that warranted much more than a light yellow reading on the Lie Meter. A few other quick tests with other people did show a wider range of results.The Agile Lie Detector uses voice stress analysis, a somewhat controversial alternative to the traditional polygraph test, to determine whether or not someone is lying. The bad side of this is that it's not considered as accurate as hooking someone up to a machine that measures more than one physiological response, like breathing and pulse. The good side is -- theoretically anyway -- you don't need to be in the same room as the person you are trying to test. In fact, it's possible to analyze speech through speakers, assuming the quality of those speakers is high enough. To play with this a bit, I searched for video on YouTube that showed people obviously lying (think Clinton's denial of his canoodling with Monica Lewinsky) or obviously under stress (think Sarah Palin talking to Katie Couric). The results of holding my iPhone up to the speaker as these and other videos played showed, in a most unscientific and probably flawed way, a difference, however slight, versus when people not under stress spoke. The very cool part of the application is that it gives you results in real time, so you can see from moment to moment when someone is getting a bit nervous. Theoretically.If I were the feds, I wouldn't be shipping off a crate of iPhones (liePhones?) to Gitmo quite yet. This application is filed under the Entertainment category in the App Store for a reason. It shouldn't be relied on in serious situations. You know, like asking your wife if she really, truly thinks you look good in that new jacket of yours. However, if voice stress analysis is your bag, definitely give this app a try. I won't lie though. It's a tad pricey.
Lie-detecting headband promises to find the truth with infrared light
While most folks working to improve on the traditional lie detector have veered towards MRIs, EEGs and the like, Scott Bunce of Drexel University's College of Medicine has taken a decidedly different approach and turned to an infrared light-based method, which he seems to think would be both less expensive and more accurate. Apparently, the system works simply by sending infrared light into your brain and measuring how much is reflected back, which varies depending on the levels of oxygen in the blood, and in turn gives an indication of brain activity. Not surprisingly, the research appears to have already attracted the interested of some of the usual suspects -- namely, the U.S. Office of Naval Research and the Department of Homeland Security, who have provided some of the funding -- but it seems like there's still some more work to be done before it moves beyond the lab. At least as far as we know.[Via Crave]
US troops to receive handheld lie detectors
In a move sure to bring the polygraph haters out of the woodwork, the US Army is issuing a handheld lie detector to select soldiers in Afghanistan in order to "root out potential terrorists" and help "narrow the list of suspects after a roadside bombing." The DoD isn't asserting that the device is perfect, but it's hoping the detection capabilities are accurate enough to save American lives and sniff out allegiances that may have otherwise gone unnoticed. Hailed as PCASS (Preliminary Credibility Assessment Screening System), the underlying unit is a TDS Ranger that relies on three sensors connected to a respondent and integrated software that uses Green to signify truth, Yellow if it can't decide and Red if it recognizes a filthy liar on the other end. Nevertheless, we're certain Lafayette Instrument Company is stoked about the deal -- you know, considering that the Army has already purchased 94 of 'em at $7,500 apiece.[Thanks, ladderless]
Cornell researchers developing lie-detection software
While most of the world simply takes what everyone else says at face value, there's always been a dark market for inconspicuous lie-detecting gadgetry for the overly paranoid, but researchers at Cornell University are hoping to take lie-detection to the next level by carefully analyzing emails and SMS messages for fibs. In a three-year effort to "compile a list of indicators of written deception," the team drew from some "40 years of research in linguistics and lies, including recent work in the context of computer media and reviews of Enron emails." By carefully inspecting word choices, verb tenses, and a variety of other textual factors, the software can purportedly use "contextual parameters" to spot lies, and they hope to market the goods to police agencies, upset spouses, and of course, corporate ethics committees.So if you're ever-so-suspicious significant other (or mischievous youngster) has just recently put down the Skype headset in favor of pounding out emails, rest assured, help is on the way.[Via TechDirt, image via Cornell]
Skype taking a stand against lying liars
If you're an avid Skype user, and you aren't entirely honest some most of the time, you should probably watch what you say from here on out. While auditory lie detectors have definitely been around, BATM is manufacturing a dedicated fib sniffer made to work specifically with Skype. The KishKish Lie Detector will be offered up as a "Skype add-on," and will reportedly analyze audio streams over a Skype conversation in real time and "illustrate the stress level" of the other person -- you know, in case you can't quite pick up the quivering on your own. Moreover, users will be able to "record calls for delayed analysis" in case you need to comb things over once you've cooled your jets. While we've got no qualms with getting down to the truth, we can't help but think this gizmo's a tad on the creepy side of things, but it's sure to please suspicious Skype users everywhere when it rolls out sometime in the future (we promise).[Via SmartMobs]
