FaceSense: Mind-reading from MIT

70′s-style mind-reading for the digital age, or why we all say one thing and mean another.

We have a longstanding fascination with the human face and the wealth of data that it holds. Now, the Affective Computing Group at the MIT Media Lab (another Brain Pickings darling) has developed FaceSense — a software application that detects head and face gestures in real time, analyzes them and deduces information about the person’s emotional disposition and mental state.

The principle, of course, is nothing new — back in the late 70′s, legendary psychologist Paul Ekman pioneered FACS, the Facial Actions Coding System, which is used to this day by anyone from academic researchers to the CIA to draw information about cognitive-affective states based on the micromuscle contractions of the human face. Though the MIT project doesn’t explicitly disclose it, we bet the data encoding is based, at least to some degree, on FACS.

But what makes FaceSense different and important is that it enables the extraction of such cognitive-affective information from pre-recorded video. And in the midst of all the neuromarketing hype — which is, for the most part, just that: hype — it offers an interesting model for collecting consumer psychology insight remotely, a scalable and useful tool for the age of telecommuting and sentiment analysis. What’s more, it helps bypass the quintessential unreliability of self-report in product testing.

Its applications can, of course, extend far beyond the marketing industry. An accurate disposition detection model for video can be used in anything from analyzing politicians’ televised appearances to testing news anchors for bias. And, judging by the abundance of all things video at CES this year, FaceSense has firmly planted its feet in a rich and ever-expanding space.

In 2009, we spent more than 240 hours a month bringing you Brain Pickings. That’s over 2,880 hours for the year, over which we could’ve seen 29 feature-length films, listened to 72 music albums or taken 960 bathroom visits. If you found any joy and inspiration here this year, please consider supporting us with a modest donation — it lets us know we’re doing something right.

Psst, we’ve launched a fancy weekly newsletter. It comes out on Sundays, offers the week’s articles, and features five more tasty bites of web-wide interestingness. Here’s an example. Like? Sign up.

Mobile Mobile: The Christmas Tree Retought

Dusty phones, giant chandeliers, and a post-modern Christmas tree that tweets.

This month, interactive artist James Theophane was tasked with creating a holiday experience that embodied the spirit of collaboration for London ad agency Lost Boys. When he heard that there had been an agency-wide cell phone upgrade two months earlier, leaving behind fifty old phones, Theophane decided to upcycle the old phones into a reinterpretation of the idea of the Christmas tree and its role as a communal focal point.

The result was Mobile Mobile, a giant interactive chandelier, where each hanging phone plays a different note of a Christmas carol and flashes in time.

The elaborate scheme works by assigning a tone to each phone and making it individually addressable by a computer to create the choral arrangement, bringing the choir of devices to life.

Visitors and onlookers can “play” the installation from their browser, and it has also been wired to respond to tweets.

Indulge your inner geek with a behind-the-scenes look at the rather impressive production process. And if you have an old phone lying around, unless you can wire it up into a brilliant interactive chandelier, why not consider donating it to Hope Phones?

Psst, we’ve launched a fancy weekly newsletter. It comes out on Sundays, offers the week’s articles, and features five more tasty bites of web-wide interestingness. Here’s an example. Like? Sign up.

Super-Smart Learning

Why playing Oregon Trail is like learning basic Japanese, or how to beat the Ebbinghaus Curve.

For a scientifically inclined utopian, technology is the potential antidote to all of society’s ills. Techno-optimists believe every challenge, from cancer to cleanliness, has an applied-science solution. Most of us approach technology with significantly more skepticism, of course. But as 21st-century citizens, we’ve come to understand that our progressively more complex problems require more than machines alone.

As it turns out, though, simpler challenges—like, say, memorizing the names of world capitals—are in fact being better addressed by new technologies every day. So goes the story behind two learning programs, Smart.fm and SuperMemo, both garnering attention as we increasingly look to gadgets and gizmos to improve our lifestyles. (Call it the Wii Fit phenomenon.)

Smart.fm and SuperMemo aim, and claim, to help you memorize and retain knowledge in more efficient ways. Both products are based on a well-proven finding known as the Ebbinghaus, or forgetting, curve, first deduced by German psychologist Hermann Ebbinghaus in 1885. The curve is an equation (, to be specific) that describes how our brains forget things over time.

Essentially, Ebbinghaus found that memory retention of newly acquired knowledge declines unless we consciously review that knowledge. Subsequent scientific studies (mostly in the 1930s and late 1960s) revealed even more about the nature of memory and learning: If we review an item right before we’re about to forget it, immediately prior to our brains’ contact with the curve, we actually improve our ability to retain that item in memory. The way to ensure remembrance, then, is to increase the length of time between these information reviews, a technique otherwise known as spaced repetition.

When computers became more common in the 1980s, researchers began to experiment with algorithms for automating the spacing of repeated knowledge over time.

Fast forward to the future and the tantalizing promises of technology for better living. Just as exercise has its own digital assistant, so too can learning. If all it takes to remember something is a well-timed reminder, then why not leave your learning to a robot? And now not only can we automate such simple processes, we can make them fit in the palm of a hand. Smart.fm‘s newly released iPhone app promises to do just that — make learning a portable experience — as illustrated in a cheeky short its creators made to highlight the app’s features and functionality.

The iPhone app is based on Smart.fm‘s online-learning platform, which itself grew out of an adaptive-learning system called iKnow. Cerego, a Japanese venture-backed think tank, created all of the products and had already popularized iKnow’s use in Japan before introducing an English-language version. We were fascinated to see how this earlier incarnation of Smart.fm developed into its intuitive, present-day user experience, a process satisfyingly documented as a case study by the über-smart design firm Adaptive Path, which partnered with Cerego on these multiple orders of translation.

Where Smart.fm is sexy and supple in design, SuperMemo is, well, not. (Consider it the Craig’s List of online learning.) What it does have, however, is a storied pedigree documented by Wired and other ahead-of-the-curve pubs (pun unfortunately intended). SuperMemo‘s creator, Piotr Wozniak, is its ultimate evangelist because he’s also its Ur-user — he created the platform for his personal use. Wozniak developed the software behind SuperMemo in the mid-1980s without prior knowledge of Ebbinghaus’s repetitive trials. Its user interface seems like it’s changed little since Wozniak wrote his first programs, but perhaps this is SuperMemo‘s charm. In fact, a kind of cottage industry of both white-label versions and ad-hoc, pirated programs sprang up as soon as the Internet allowed for easy file sharing.

What Smart.fm hides under the hood, however, SuperMemo makes accessible. All of the statistical breakdowns driving the program’s prompts are available for your perusal, should you get excited by indices and intervals. (No need to be shy–we’re very sympathetic to such symptoms here at Brain Pickings.) For the person who wants to see and directly manipulate a product’s inner workings, SuperMemo allows for much more hands-on interaction than the plug-and-play approach designed by Adaptive Path. What both Smart.fm and SuperMemo share is a pliability in their ultimate purposes. You can use preprogrammed language-learning modules, but you can also personalize each by adding your own information for spaced repetition.

So while neither Smart.fm nor SuperMemo can cure the common cold, consider exploring technologically augmented learning for your next mental exercise–like that taxonomy of Tolkein characters you’ve been meaning to commit to memory.

Kirstin Butler is writing an adaptation of Gogol for the Google era called Dead SULs, but when not working spends far, far too much time on Twitter. She currently lives in Cambridge, MA.

Brain Pickings has a free weekly newsletter and people say it’s cool. It comes out on Sundays and offers the week’s best articles. Here’s an example. Like? Sign up.