Approach could help software learn how to identify fake accounts with less honorable intentions.

By Tom Simonite

It’s not unusual to have user profiles on multiple social networks, or even separate accounts on sites like Twitter–one for work and one for play. But Kyumin Lee at Texas A&M University has 60 Twitter accounts, and not because he’s popular.

Lee’s accounts are “honeypots,” designed to attract the attention of the spammers that increasingly use social networks to spread links to malware and phishing Web sites. Software developed by Lee monitors messages sent to the honeypot accounts to learn the tactics used by spammers.

“The concept of a honeypot is well established at the network level,” says Lee. Usually it takes the form of unprotected computers used to monitor spam e-mail or network-based attacks. “We decided to apply it at a higher level to learn about spam in social networks.” Lee is carrying out the project with A&M colleagues James Caverlee and Brian David Eoff, and with Steve Webb at Georgia Tech University. The work is partially supported by a research award from Google.

The honeypot accounts, like this one, automatically post updates drawn from a collection of 120,000 real tweets harvested from Twitter. The team has also deployed honeypots on MySpace, and created software that uses dummy profiles on both networks to learn about spammer tactics. “We have a bot monitor who contacts our profiles, ” says Lee. “It looks at what they put in their messages and also accesses their profile to see their demographic information and past updates.”

So far, Lee says, “our 61 honeypots tempted and collected 30,867 spammers on Twitter.” The data gathered by those bots can also be used to train “classifier” algorithms to identify spammers that haven’t yet contacted a honeypot. A classifier trained using the Twitter honeypots proved capable of correctly identifying spam profiles more than 80 percent of the time. A public Web service is being built from the trained model that will allow people to look up which accounts it considers spam, and submit corrections for any that are misidentified, says Lee.

Spam and phishing attacks delivered over social networks are a growing problem, says Don DeBolt, director of threat research for IT software firm CA Technologies. For example, a phishing scam operating over Twitter recently stole the iTunes accounts of some users. “People immediately trust these applications because it is how they communicate with friends,” DeBolt explains. “Because people are sending much less text than an e-mail, and URL shorteners are often used, it is harder for people to realize a message may not be real.”

DeBolt’s team maintains honeypot profiles of its own, and monitors them manually to look for new spammer tactics. “We have to take great care, though, in curating them as research profiles that don’t impersonate a real person,” he says.

The fact that social network honeypots must be part of a community is a fundamental difference from the conventional approach, says Azer Bestavros, a networking specialist at Boston University who has, in the past, worked on analyzing blog spam. A honeypot computer on a network is typically allocated to “dark” address space so that they would never legitimately be contacted by another machine.

“Other users could consider our honeypot a real person,” Lee acknowledges. “But we do not have friends or contact other people, and on Twitter our profiles posted random messages so a normal user would not think to contact us.”

Some messages and friend requests sent to a social honeypot may be from legitimate users, so information collected from them needs to be treated carefully, says Bestavros. Lee and colleagues are experimenting with varying the output and demographic characteristics of their honeypots to find out what most attracts spammers–for example, varying the dummy user’s age and location, or the frequency of their updates. “Most of the spammers present themselves as college-age females,” says Lee. Data from MySpace honeypots shows that most claim to be located in California, and so far it seems that college-age males are the preferred target.

Lee and colleagues are also interested in trying the approach on the world’s largest social network: Facebook. “It is a more private network, but if we were able to get permission from them it would be interesting to try it there,” he says.

Source: http://www.technologyreview.com/web/25774/page2/

Popularity: 3% [?]

Share on Facebook Approach could help software learn how to identify fake accounts with less honorable intentions.

Service tracks social network chitchat about a product

February 27, 2010 by raj  
Filed under IT News, Social Media

Big-name companies increasingly recognize the importance of discussions about their products on social media sites such as Facebook and Twitter. But keeping track of so many conversations in real-time is a daunting challenge.

A startup called Viralheat, based in San Jose, CA, has launched an analytics package designed to allow in-depth analysis of the tenor of this back and forth. The company hopes its software will help its clients sort through the often overwhelming amount of available data from the social Web.

“The huge issue that everybody is having with social media right now is that it’s just incredibly fragmented,” says Viralheat’s founder and CEO, Raj Kadam. There are dozens of sites where users may be discussing a brand, Kadam says. “Big brands only have so many hours in their day to understand this,” he says. “They need to listen, measure what’s happening with their audience, analyze it, and then figure out a way to engage their customers.”

Viralheat monitors tweets, blog posts, video uploads, discussion on Facebook pages, and other social data sources. A user can be quite specific about what she wants to monitor–for example, focusing on discussions about the movie Avatar that take place outside the United States. The tool collects data that fits the bill and lets customers view them individually or as graphs that show broader trends.

The software also tries to identify the mood of a conversation, and to figure out who the main influencers are. To do this, Viralheat uses natural language processing techniques and a set of proprietary algorithms that tag posts as either “positive” or “negative” in tone. Kadam stresses that this is not the same as looking for simple phrases such as “this is cool” or “this stinks.” Instead, he says, the company trains its system regularly using sets of data taken from real social media sites, to ensure it recognizes complex statements and stays accurate and up-to-date.

The data collected by Viralheat can be sliced in several ways to uncover the most influential parties in a conversation. A user can see how many people have tweeted about a particular topic, and a rough estimate of the impact of each tweet. The estimate is based on how many followers a Twitter user has, whether the message was original or simply a retweet, and whether any new information was added. Viralheat identifies two types of top influencers–those with lots of followers, and those who are most active in discussing a topic. The software offers similar tools for other social platforms as well as an application programming interface (API) so that customers can repurpose the data.

“The depth of their analytics is really stunning,” says Carla Thompson, a senior analyst for Guidewire Group, a firm that analyzes early-stage technology companies. She’s particularly impressed by the sentiment analysis that Viralheat does, which calls for fairly sophisticated algorithms and processing power.

But Thompson believes that Viralheat, like other analytics companies, could do a better job of helping its customers act on data. For example, while Viralheat can show that mentions of a brand are spiking, she says, it would be ideal if it could suggest a next action to help take advantage of this buzz.

Counter to common startup wisdom today, Viralheat’s founders say it’s cheaper for the company to avoid cloud-computing services. Founder and CTO Vishal Sankhla explains that the service constantly uses a lot of bandwidth, making it more effective to build and operate its own server farm. “We analyze five to six terabytes of data every month,” and paying a third party for that level of usage would quickly become cost-prohibitive, he says.

Thompson believes that Viralheat is well-placed to be a viable player in the market, particularly because the company’s pricing plans are more cost-efficient than any of the other analytics companies that she’s seen. Most analytics companies charge based on how many times a brand is mentioned, so she expects that this company’s offer of unlimited mentions will be attractive to potential customers.

The company offers several levels of pricing, ranging from $9.99 per month for the individual plan to $89.99 per month for the plan intended for large companies. The basic plan allows a user to monitor up to 10 profiles, while the premium plans add features such as access to the API.

Viralheat already counts Coca-Cola, Microsoft, and Nokia among its customers. Its closest competitors are Radian6 and Scout Labs.

http://www.technologyreview.com/web/24503/page2/

Popularity: 4% [?]

Share on Facebook Service tracks social network chitchat about a product

What happens when your online pals meet your TV?

January 12, 2010 by raj  
Filed under IT News

Comments Off

In the 1960s, families gathered in the living room to watch Bonanza. In the 1980s, friends met at the water cooler to speculate about who shot J.R. In 2010, mom watches HGTV in the bedroom, dad cheers for the Longhorns in the living room, and the kids laugh at the new episode of Glee on Hulu.com in the study.

Social shows: A prototype TV menu lets viewers see what their friends are watching. Motorola researchers designed this version while studying the concept in 2008.

In an effort to “make TV social again” and to bring even far-flung family members and friends together around the screen, researchers at companies including Motorola, BT, and Intel are working on ways to combine social networking with TV viewing. The goal is to get as close as possible to a physically shared viewing experience–and to make it easier to find something decent to watch among the ever-increasing number of channels.

The idea is not new, says Jeff Patmore, BT’s head of strategic university research, who works with students at schools including MIT and the University of Cambridge in the United Kingdom. About 12 years ago, BT experimented with “interactive television,” allowing people to send messages to one another over their TV screens. But “we’ve been there and done that, and we don’t want to do it again,” h

Popularity: 2% [?]

Share on Facebook What happens when your online pals meet your TV?

Facebook Users to Get Personalized URLs

June 11, 2009 by Rajesh Kumar  
Filed under Social Media

facebook_site1Facebook’s new personalized usernames and URLs could be a boost to online marketers, but is it a lost opportunity for the social networking site?

One minute after the stroke of midnight on Saturday could usher in a virtual land grab for vanity URLs on Facebook, with the social networking site poised to enable members to create usernames for personalized online addresses.

Currently, the URL for a Facebook profile ends with a string of digits. But beginning on Saturday morning, members can substitute the numbers with a name of their choice to make it easier for friends to navigate to their site.

Names will be available on a first-come-first-served basis to anyone with a Facebook profile, or a fan page with more than 1,000 fans, must be a minimum of five characters long and is permanent — no changing it later. Participating in the free personalization service is optional.

Facebook designer Blaise DiPersia made the announcement in a blog post.

“Your new Facebook URL is like your personal destination, or home, on the Web. People can enter a Facebook username as a search term on Facebook or a popular search engine like Google, for example, which will make it much easier for people to find friends with common names,” DiPersia wrote. “Your username will have the same privacy setting as your profile name in Search, and you can always edit your search privacy settings.”

To prevent cybersquatting, anyone who signed up for Facebook after 3 p.m. Eastern time today will not be able to secure a username until after 12:01am on June 28. Facebook also said it reserves the right to revoke a username, and will allow trademark owners to contest names they believe infringe on their trademarks.

The news comes at time when social media marketing is gaining traction as a way for brands to build awareness and offer interactive promotions, potentially at a lower cost and higher effectiveness than traditional media. Now that personalized URLs have been added to the mix, it could be a boost to those marketers using Facebook for online marketing by ensuring that brand’s fan page is easier to find.

It remains to be seen how Facebook itself will benefit from offering personalization for free — aside from pleasing its user community, which had been requesting such a feature for some time, according to the company.

“I think certain people would be willing to pay, but that’s not the best solution because people have different resources and means, so we wanted a solution in the best interest of all our users, as opposed to serving a subset. The fairest thing is to offer it for free,” a Facebook spokesperson told InternetNews.com.

The spokesperson declined to comment on what future ways usernames could be employed but agreed that easier search functionality will benefit online marketers in addition to the general community.
The monetizing question

But offering personalized URLs for free could also spell a lost opportunity for making money. Given that people often pay for domain URLs and Facebook members are already spending money at the site to play social networking games — for instance, buying virtual poker chips for card games — the move may be a missed chance at generating revenue, something with which the site has been grappling for some time.

Most recently, however, Facebook introduced a unified payment system for virtual goods used in games at the site, therefore putting the company in a position to get a slice of the revenue from such transactions.

The way transactions work now on Facebook leaves the site out of the payment loop, as third-party developers create their own payment systems and take all the revenue.

Facebook is hoping that a unified payment system for items such as virtual poker chips would make it easier for the site’s members to play more games. This, in turn, would benefit everyone involved, but especially Facebook, which would be getting a cut of the transaction, and therefore presumably making money off the revenue stream for games.

For now, it seems Facebook is using the payment system with just three applications, but plans to introduce it to more applications in coming weeks.

Meanwhile, Facebook’s efforts to unveil new features and ramp up its revenue stream comes as social networking continues to grow at a rapid clip. The amount of time people in the U.S. spend on social networking sites jumped 83 percent over the past year, according to a study by market researcher Nielsen Online.

And Facebook is leading the way — the site’s U.S. users collectively spent 13.9 billion minutes on Facebook in April 2009, up 700 percent from the 1.7 billion minutes they were spending in April 2008, according to the study.

Minutes spent on Twitter soared a whopping 3,712 percent to almost 300 million, versus around 7.8 million from the same month a year ago.

“We have seen some major growth in Facebook during the past year, and a subsequent decline in MySpace,” Jon Gibs, Nielsen’s vice president for online media and agency insights, said in a statement. ”

Source:http://www.internetnews.com/webcontent/article.php/3824386/Facebook+Users+to+Get+Personalized+URLs.htm

Popularity: 1% [?]

Share on Facebook Facebook Users to Get Personalized URLs

Wordpress Seo Plugin