Technology that derives personality traits from Twitter updates is being tested to help target promotions and personalize customer service.

By Tom Simonite on November 8, 2013

Trying to derive a person’s wants and needs—conscious or otherwise—from online browsing and buying habits has become crucial to companies of all kinds.

Now IBM is taking the idea a step further. It is testing technology that guesses at people’s core psychological traits by analyzing what they post on Twitter, with the goal of offering personalized customer service or better-targeted promotional messages.

“We need to go below behavioral analysis like Amazon does,” says Michelle Zhou, leader of the User Systems and Experience Research Group at IBM’s Almaden Research Center in California, which developed the software. “We want to use social media to derive information about an individual—what is the overall affect of this person? How resilient is this person emotionally? People with different personalities want something different.”

Zhou’s software develops a personality profile based on a person’s most recent few hundred or thousand Twitter updates. That profile scores the “big five” traitscommonly used in psychological research: extroversion, agreeableness, conscientiousness, neuroticism, and openness to experience. It also scores the person on measures of “values” (for example, hedonism and conservatism) and “needs” (for example, curiosity and social harmony).

Zhou says she is working with several IBM customers to test how the technology might help their businesses. She declines to identify the companies but says they might use the system, for example, to tune marketing messages sent by e-mail or social media, or to select the promotional content displayed when a customer logs in to his or her account.

A crucial part of the pilot program will test whether messages targeted with the technology’s help perform better than others. “Our hypothesis is that the conversion rates will be quite high,” says Zhou. At least, she expects them to be higher than is typical: e-mail marketing messages ordinarily have a response rate of just 0.34 percent, she says, and phone marketing calls achieve about 13 percent.

Zhou says that having a rough idea of a person’s personality could also help in call centers or other customer service settings, such as when an airline must break the news that a flight has been cancelled or delayed.

“Studies show people that are extroverted want a reward and recognition, like 10,000 [frequent flyer] points,” she says. “Conscientious people want efficiency, to know their new flight right away.” In a call center scenario, a customer’s personality profile might advise a customer service agent whether to efficiently provide “just the facts” or to try to be more engaging and supportive, says Zhou.

Many businesses already make use of software that analyzes social-media activity. However, it is aimed either at helping corporate representatives interact with customers or at summarizing the overall volume and tone of a discussion (see “A Social-Media Decoder”), not at profiling individuals.

IBM’s software was developed by recruiting people to answer psychological questionnaires and comparing the results with their Twitter activity. Machine learning software then looked at how different patterns of word use matched with psychological traits. Those correlations were used to derive models that can create a profile from a person’s tweets alone.

In a study where 300 people had their Twitter profiles processed by the software and also took psychometric surveys, the results were “highly correlated” more than 80 percent of the time, says Zhou. However, she notes that when people use Twitter in a specialized way—for example, journalists discussing their beat—their tweet-derived profiles may not be so representative.

Still, Zhou argues that since the methods companies currently use to target and understand their customers are relatively imprecise, IBM’s software doesn’t have to capture a person’s personality completely to be useful. She also says it should be possible to adapt the software to use other sources of data, such as call center transcripts or online customer service chats.

Software like Zhou’s that relies on language use should be able to usefully capture something of a person’s personality, says Andrew Schwartz, a researcher at the University of Pennsylvania, who recently published a major study of how personality traits show up in Facebook activity (See “How Your Facebook Profile Reveals More About Your Personality Than You Know”). He says previous research has shown that measured personality traits can predict future actions, such as the number of sick days or doctor’s visits a person will report.

“It seems reasonable that personality would be useful for presenting ads that resonate better with the recipient,” says Schwartz. “The ad-targeting application has been talked about for a few years now, but I think language-based measures of personality are just now becoming reliable enough to see it happen.”

Pebble unveils developer tools that allow for motion- and gesture-tracking apps for its smart watch.

By Rachel Metz

Smart watch maker Pebble unveiled updates on Wednesday to the software tools that developers can use to build apps for its wrist-worn device. The tools extend the watch’s capabilities and may put it in more direct competition with popular fitness-tracking devices like the Jawbone Up and the Nike Fuelband.

The changes come as a growing number of smart watch makers like Samsung and Sony and fitness-tracking competitors like Jawbone and Nike jostle for consumers’ wrists. The push also shows that Pebble recognizes the role that simple sensing could play in the emergence of more broadly appealing wearable computers (see “So Far, Smart Watches Are Pretty Dumb”).

While not the first smart watch on the market, the $150 Pebble was the first to really resonate with consumers and app makers. Last year, the company raked in $10 million on the crowdfunding site Kickstarter for its gadget, which connects to your smartphone and buzzes to alert you of incoming calls and messages. About 190,000 Pebble watches have been sold.

From the start, Pebble hoped that most of the watch’s functionality would come from third-party developers. But speaking in San Francisco this week, Pebble founder and CEO Eric Migicovsky said that, in the early days, the company’s biggest goal was simply to ship the watch to its tens of thousands of Kickstarter backers.

The software development kit (SDK), officially released in April, was “definitely an alpha” version that Pebble “pushed out kind of to see what people would do with it,” he said. That kit led to the development of over 2,000 apps ranging from simple watch faces and games to remote controls, but there was clearly a lot of work still to be done. “The bug request line was ringing,” Migicovsky said.

The new SDK gives developers the option to add motion- and gesture-tracking features to Pebble apps. Several sports-related apps are already available for the Pebble, but they aren’t able to take advantage of the watch’s accelerometer.

Developers will also be able to build apps that can cache a small amount of data on the watch when the owner’s smartphone is out of range and automatically transfer it to the smartphone later on. These features could help deal with dropped Bluetooth connections and could be useful for tracking activities like swimming and running, where the user is typically separated from his phone.

Additionally, Migicovsky said, the new SDK will make it easier for developers to build Pebble apps that work with both the iPhone and Android smartphones.

Pebble is also bringing in more established companies as app developers. The company said on Wednesday that it will be adding apps from Yelp and Foursquare, among others. Pebble will roll out a software update for users before the end of the year that will enable apps with these new features to work on existing watches, and these apps will become available at that time as well.

Also on Wednesday, Pebble announced an update to its smart watch software for customers who use the Pebble with an iPhone. It will let users choose to see any app notifications on their Pebble that they’ve elected to see on their iPhone. Previously, iOS notifications on the Pebble had been limited to just a handful of functions including calls, e-mails, and texts.

By Konrad Krawczyk/Published November 08, 2013/Digital Trends

Depending on who you are, where you hail from, and where you stand on guns, 3D printing and related issues, this bit of news will either thrill and astound you, terrify you, or compel you to say “meh.”

But here goes: A company by the name of Solid Concepts has made the world’s first metal gun using a 3D printer.

Based out of Austin, Texas, the 3D-printed metal pistol made by Solid Concepts is based on the Browning 1911 firearm. Solid Concepts set out to make this gun in an effort to prove that they can make weapons that are fit for “real world applications.”

To make the gun, Solid Concepts utilized a manufacturing process known as direct metal laser sintering, or DMLS. DMLS is a 3D manufacturing process used to make metal parts for the aerospace and medical industries. The application for DMLS in the latter example is specific to surgical tools, meaning it’s perfectly suited for the creation of precision firearms.

“The whole concept of using a laser sintering process to 3D Print a metal gun revolves around proving the reliability, accuracy, and usability of 3D Metal Printing as functional prototypes and end use products,” says Solid Concepts’ vice president of additive manufacturing Kent Firestone. “It’s a common misconception that laser sintering isn’t accurate or strong enough, and we’re working to change people’s perspective.”

While 3D printers are becoming more and more affordable all the time, don’t get the wrong idea: you can’t just slap down a couple thousand bucks for a MakerBot 3D printer and hope to make your own firearm from the comfort of your own garage.

“The industrial printer we used costs more than my college tuition (and I went to a private university),” said Alyssa Parkinson, a Solid Concepts rep. ”And the engineers who run our machines are top of the line; they are experts who know what they’re doing and understand 3D Printing better than anyone in this business.”

In other words, there’s a big difference between the gun made by Solid Concepts and the weapons made by Defense Distributed, a Texas-based firm that designed guns intended to be built using 3D printers in your home.

By Megan Gannon/Published November 08, 2013/LiveScience

Before humans can trust robots to work as grocery store cashiers, these machines will have to prove they can do certain things like not squishing our perfect heirloom tomatoes or stabbing us with new kitchen knives at the checkout line.

A group of researchers at Cornell University is teaching a robot dubbed Baxter how to handle, properly and safely, a variety of objects, from sharp knives to egg cartons, based on human feedback in a grocery-store scenario.

“We give the robot a lot of flexibility in learning,” Ashutosh Saxena, an assistant professor of computer science at Cornell, said in a statement. “The robot can learn from corrective human feedback in order to plan its actions that are suitable to the environment and the objects present.”

For their experiments, Saxena and colleagues had a Baxter robot set up as a cashier in a mock checkout line. Baxter is a cheap, flexible robot built by a Boston-based startup called Rethink Robotics. It was primarily designed to work in assembly lines alongside people, but Baxter’s learning skills also make it an easy-to-teach cashier.

As this video of the knife-wielding robot shows, the researchers are teaching Baxter how to handle different items by manually correcting Baxter’s arm motions.

If the robot swings a sharp kitchen knife, for example, too close to the human playing customer at the checkout, a researcher could grab Baxter’s arm and guide it in the right direction.

Over time the robot learns to associate different trajectories with different objects, such as a quick flip for a cereal box or a delicate lift for a carton of eggs, the researchers say.

Saxena and colleagues will present their work at the Neural Information Processing Systems conference in Lake Tahoe, Calif., next month, but an early version of their research paper is available online.

BY NICOLA LESKE AND OLIVIA ORAN

NEW YORK Fri Nov 8, 2013 2:37pm EST

(Reuters) – Data storage company Box, one of the most highly anticipated IPO candidates in Silicon Valley, has selected banks to lead a proposed initial public offering that could come in the first half of 2014, according to three people familiar with the matter.

The fast-growing technology start-up has selected Morgan Stanley, Credit Suisse andJPMorgan Chase & Co to lead the offering that could raise around $500 million, the people said.

Representatives for Box, Morgan Stanley and Credit Suisse did not immediately respond to requests for comment. JPMorgan declined to comment.

Box is one of several high-profile start-ups gearing up for an IPO, on the heels of a successful debut by Twitter Inc on Thursday, which raised more than $1.8 billion for the microblogging company.

Other closely watched startups which may be exploring an IPO include mobile payments company Square, Uber and Pinterest.

A public float for Box would come amid the strongest dollar volume for U.S. IPOs since 2000.

U.S. companies have raised $50.7 billion in proceeds year to date, a 26 percent increase compared to a year earlier, according to Thomson Reuters data.

This year is also the strongest year for the number of U.S. new listings since 2004.

Box, started in 2005 by University of Southern California drop-out Aaron Levie and his childhood friend Dylan Smith, has been valued at more than $1.2 billion by private investors, although it remains unclear whether the company is profitable.

The online storage company has tapped into growing demand by professional workers who increasingly want to share documents across different computers and has been locked in fierce competition with a number of rivals, including Dropbox, another privately held firm that is valued at $4 billion.

Box and Dropbox, which provide users with free storage but charge fees for additional space, have been able to steadily gain market share even though tech giants like Google Inc, Microsoft Corp and Apple Inc all offer their own versions of file-sharing utilities.

In 2011, Box rebuffed a takeover offer by Citrix Systems worth more than $500 million.

Emerging Technology From the arXiv

GPS is power hungry and often suffers from poor signal strength in city centres. Now computer scientists have worked out how your smartphone’s inertial sensors can fill in the gaps.

If you’ve ever used a smartphone to navigate, you’ll know that one of the biggest problems is running out of juice. GPS sensors are a significant battery drain and so any journey of significant length requires some kind of external power source. Added to that is the difficulty in even getting a GPS signal in city centre locations where towering office blocks, bridges and tunnels regularly conspire to block the signal.

So a trick that reduces power consumption while increasing the device’s positioning accuracy would surely be of use.

Today, Cheng Bo at the Illinois Institute of Technology in Chicago and a few pals say they’ve developed just such a program, called SmartLoc, and have tested it extensively while travelling throughout the windy city.

They say that in the city, GPS has a positioning accuracy of about 40 metres. By comparison, their SmartLoc system pinpoints its location to within 20 metres, 90 per cent of the time.

So how have these guys achieved this improvement? The trick that Bo and pals use is to exploit the smartphone’s inertial sensors to determine its position whenever the GPS is off line.

The way this works is straightforward. Imagine a smartphone fixed to the windscreen of a car driving around town. Given a GPS reading to start off with, the smartphone knows where it is on its built-in or online map. It then uses the inertial sensor to measure its acceleration, indicating a move forwards or a turn to the left or right and so on.

By itself, this kind of data is not very useful because it’s hard to tell how far the vehicle has traveled and whether the acceleration was the result of the car speeding up or going over a humpback bridge, for example.

To get around this, the smartphone examines the section of road on the map looking for road layouts and features that might influence the sensors; things like bends in the road, traffic lights, humpback bridges and so on. Each of these has a specific inertial signature that the phone can spot. In this way, it can match the inertial signals to the road features at that point.

The key here is that each road feature has a unique signature. Bo and co have discovered a wide range of inertial signatures, such as the deceleration, waiting and acceleration associated with a set of traffic lights, the forces associated with turnings (and how these differ from the forces generated by changing lanes, for example) and even the change in the force of gravity when going over a bridge.

Having gathered this data, the SmartLoc program looks for these signatures while the car is on the move. These guys have tested it using a Galaxy S3 smartphone on the city streets in Chicago and say it works well. They point out that in the city centre, the GPS signal can disappear for distances of up to a kilometre, which would leave a conventional navigation system entirely confused.

However, SmartLoc simply fills in the gaps using its inertial signature database and a map of the area. “Our extensive evaluations shows that SmartLoc improves the localization accuracy to less than 20m for more than 90% roads in Chicago downtown, compared with ≥ 50% with raw GPS data,” they say.

That certainly looks handy. And this kind of performance could also help save battery power by allowing a smartphone to periodically switch off the GPS sensor and run only using the inertial sensor.

What Bo and co don’t do is explain their plans for their new system. One obvious idea would be to release it as an app–it clearly already works on the Android platform. Another idea would be to sell the technology to an existing mapping company. Perhaps they’re planning both. Whatever the goal, it seems worth keeping an eye on.

Twitter may make major interface changes to address the growing need to make money.

By Josh Dzieza

Last week Twitter underwent one of the biggest redesigns in its seven-year history, but you’d be forgiven for missing it. Embedded images and video are now displayed automatically in the updates you see, instead of requiring a click to expand and view. Buttons for “retweeting,” “replying,” and “favoriting” tweets were also brought to the surface, cutting in half the number of clicks needed to interact with a tweet.

Which is not to say the changes are insignificant. Indeed, they are a sign of things to come, as Twitter tries to balance its simple appeal and the demands of its users with a growing need to make money.

As Twitter nears its IPO, the new presence of images and videos may help woo people currently using Instagram, Snapchat, or other rapidly growing social photo-sharing services. They certainly make Twitter more appealing to advertisers: previously users would have to click on a promoted tweet to see an image; now it’s in your face. (After the update, some people joked that Twitter just launched banner ads.) The newly prominent social buttons will also encourage more interaction, making it easier for Twitter’s many lurkers to engage, and lowering the threshold for tweets to go viral.

Twitter has been signaling for some time that a more radical redesign is imminent. As a soon-to-be publicly traded company, it needs to increase users, and one way to do that would be to find a way of diminishing the number of people who sign up for Twitter, can’t figure out what to do with it, and never come back. Last month a Reuters/Ipsos poll found that 36 percent of people who joined Twitter say they don’t use it, citing a lack of friends on Twitter, and confusion over how to use it and what it was for, among other reasons. In comparison, only 7 percent of Facebook members say they don’t use the site after signing up. Possibly the rumored television stream—a separate column for people discussing television shows, and for broadcasters to promote shows, and for companies to place ads across both screens—could serve this purpose without disrupting the main feed. And possibly Twitter could continue its attempts to recommend content it thinks people will be interested in, carrying on the work of the neglected Discover tab—a personalized stream of top stories and tweets that will reportedly be cut—in some other form.

But the Discover column’s neglect indicates an important challenge for Twitter. Its users are reluctant to take too much heavy guidance, and they have the perfect venue for venting their displeasure if they disagree with changes. Even the minor addition of blue lines to sort Twitter conversations into groups elicited a backlash, though that appears to have faded. Twitter is also driven disproportionately by the activity of a small coterie of power users, some of whom have several million followers.

Twitter’s light touch with redesigns shows that it knows this. The challenge will be keeping this in mind going into the IPO—as pressure to make money inevitably increases.

In contrast to Twitter, Facebook has undergone major overhauls of its user interface several times, each of them usually accompanied by howls of outrage and petitions (on Facebook) to roll them back. Twitter looks extremely similar to when it launched in 2006. Many of Twitter’s redesigns amounted to adjusting its interface and features to better accommodate things its users are already doing, rather than foisting new features upon them. Some of Twitter’s most iconic features, like the hashtag and retweet, were first created by users before Twitter built them into the architecture of the site.

“Facebook tends to build what they want for their users rather than listening to users and building what they want,” says Brian Blau, an analyst who covers Twitter for Gartner—“not that one is good or bad.” He attributes the difference partly to the two sites’ different goals: “Facebook has much broader ambitions, to connect the world, and when you say that you can think about different ways of connecting people—the wall, timeline, news feed. You can change the user interface, and people may not like it, but they like being on Facebook so they tolerate it, and now they don’t remember.” Facebook, it’s worth pointing out, is more embedded in users’ real-world social lives, making it harder to quit or ignore.

Twitter, he says, has stayed very focused on a single pillar: real-time, short-form communication. It has kept its focus even though Twitter’s original constraint, the 140-character limit, was a limit imposed by the SMS texting the site originally used, and no longer applies.

“Twitter’s beauty is its simplicity and its creativity is its constraint, 140 characters,” says S. Shyam Sundar, the founder of the Media Effects Research Laboratory at Penn State. When your form is your function, Sundar says, it creates certain constraints when it comes to redesigns. You can add videos and images and shortened links to tweets, but if you touch the format of short messages presented in a reverse-chronological stream, Twitter won’t be Twitter.

So far, when Twitter has made design tweaks, it has tended toward giving users greater latitude in how they use the site rather than directing them how to use it (as Facebook might do). When the first Twitter users signed on, the site prompted them with the question, “What are you doing?” As Twitter moved from a microblogging platform often mocked for its mundanity to a place where people posted about news and events, that injunction was swapped out for the more open ended, “What’s happening?” Today it’s simply, “Compose a new tweet.”

As people started using Twitter as a way to share and discover hyperlinks to interesting content as much as a blogging platform, Twitter accommodated them, developing its own URL shortening service. After images became one of Twitter’s major functions—the twitpic of the plane that crash-landed in the Hudson River was a turning point—it decided to host its own photos. Even the “trending topic” chart in the margin, a major new feature in 2009, simply gave a more prominent location to information about what was already happening on Twitter.

So far Twitter has stayed remarkably dedicated to its original interface, taking a hands-off approach to how its 230 million users want to use it. But it will soon have another powerful bunch of people—investors—who also want to be heard.