Ocean
The Living Force
http://www.guardian.co.uk/technology/2008/oct/23/social-networks-ilink
US military targets social nets
The social networking landscape could change beyond recognition with technology that maps the skills and needs of users
Illustration: Tobatron
A new startup is helping reshape the social networking landscape by using artificial intelligence to automate the process of identifying, finding and retrieving specific types of information locked within online communities.
Over the past decade, social networks have become a powerful new force for attracting internet traffic. In the UK, Facebook is currently the second most popular website followed by Google, according to Hitwise, an internet research firm.
It's not surprising that the names of the various social networking sites like Facebook, MySpace and LinkedIn have become common destinations for younger people as well as businesses.
But finding information and expert sources of knowledge quickly within social networks is neither easy nor efficient and valuable information is left buried within online communities.
To date, much of the technology focus has been on building document-based information retrieval techniques, leaving the process of identifying human sources of information, also known as "expertise identification," with much less attention.
Enter a group of scientists and military officers who have helped build a new social analytics tool that identifies and automatically uncovers intelligence to help military personnel perform better in the field.
SRI International based in Menlo Park, California, teamed up with military officers to build a new social analytics tool called iLink that generates models and helps streamline the process by which a specific expert in an online community can be found.
In simple terms, iLink is a machine learning-based system that models users and content in a social network and then points the user to relevant content.
The team developed the basic social networking technology, which combines workflow and analytics. The research and development effort was part of a five-year project called CALO (Cognitive Agent that Learns and Organizes), and funded by the US Department of Defense.
"They wanted a real system to be built and deployed into military settings," said Jeffrey Davitz, an SRI scientist and co-developer of the iLink technology. "What we did was connect the text mining technology that had been done in social media and connected it to the Web 2.0 applications," he added.
The iLink system had several goals, including real-time learning by matching queries and communities users; adapting to user demands and directions, providing accuracy in message targeting and routing and, finally, dynamic user profile correction based on community behaviours and identification of community experts.
The learning in iLink occurs by watching a natural social network, and selecting effective strategies that emerge from the system as the members try to solve problems. The system continuously monitors the real social network and it is capable of drafting from the social network's learning.
"We started with a lot of analytics stuff, text flow and workflow," Davitz said.
The iLink software uses artificial intelligence software and message routing technology to help the system learn about the online participants and move specific questions to those who are best equipped to answer them. The SRI scientists basically build a profile of each person in the community and the iLink system starts to learn about the movement of information around the community.
The US military is currently evaluating the iLink technology and how it can be applied to solve battlefield problems as well as help promote professional development, and support military families.
The researchers said the military uses a Facebook-like social community to help soldiers learn from others who had been in Iraq. The SRI scientists met with cadets at West Point in early 2007 to help refine and further develop the system.
Prior to the development of the iLink system, the cadets had written and developed their own software to help connect communities so various types of questions arising from counter-insurgency and battlefield situations in Iraq could be asked. Basically, the iLink system cuts across three online military communities with the expressed purpose of improving the way army platoon leaders and even wives, share critical information.
Looking beyond the military, the applications for this kind of smart social networking technology are broad and diverse. The two SRI scientists are planning to spin off the technology into a startup to be called Social Kinetics. The team is currently working on a healthcare application.
And with the demand for social networking growing – estimates for social networking users in the US alone by 2012 is expected to hit 92.2 million, according to In-Stat's Hitwise research service – the commercial benefits to businesses and individuals could be immense.
The biggest demographic adopting and using social networking technologies are college students. In 2008, 95.7% of college students and 17.4 million people will go online at least once a month, according to a new report from eMarketer.
Much of the push for social networking technologies is because students demand access to friends and information whenever they want and wherever they are.
US military targets social nets
The social networking landscape could change beyond recognition with technology that maps the skills and needs of users
Illustration: Tobatron
A new startup is helping reshape the social networking landscape by using artificial intelligence to automate the process of identifying, finding and retrieving specific types of information locked within online communities.
Over the past decade, social networks have become a powerful new force for attracting internet traffic. In the UK, Facebook is currently the second most popular website followed by Google, according to Hitwise, an internet research firm.
It's not surprising that the names of the various social networking sites like Facebook, MySpace and LinkedIn have become common destinations for younger people as well as businesses.
But finding information and expert sources of knowledge quickly within social networks is neither easy nor efficient and valuable information is left buried within online communities.
To date, much of the technology focus has been on building document-based information retrieval techniques, leaving the process of identifying human sources of information, also known as "expertise identification," with much less attention.
Enter a group of scientists and military officers who have helped build a new social analytics tool that identifies and automatically uncovers intelligence to help military personnel perform better in the field.
SRI International based in Menlo Park, California, teamed up with military officers to build a new social analytics tool called iLink that generates models and helps streamline the process by which a specific expert in an online community can be found.
In simple terms, iLink is a machine learning-based system that models users and content in a social network and then points the user to relevant content.
The team developed the basic social networking technology, which combines workflow and analytics. The research and development effort was part of a five-year project called CALO (Cognitive Agent that Learns and Organizes), and funded by the US Department of Defense.
"They wanted a real system to be built and deployed into military settings," said Jeffrey Davitz, an SRI scientist and co-developer of the iLink technology. "What we did was connect the text mining technology that had been done in social media and connected it to the Web 2.0 applications," he added.
The iLink system had several goals, including real-time learning by matching queries and communities users; adapting to user demands and directions, providing accuracy in message targeting and routing and, finally, dynamic user profile correction based on community behaviours and identification of community experts.
The learning in iLink occurs by watching a natural social network, and selecting effective strategies that emerge from the system as the members try to solve problems. The system continuously monitors the real social network and it is capable of drafting from the social network's learning.
"We started with a lot of analytics stuff, text flow and workflow," Davitz said.
The iLink software uses artificial intelligence software and message routing technology to help the system learn about the online participants and move specific questions to those who are best equipped to answer them. The SRI scientists basically build a profile of each person in the community and the iLink system starts to learn about the movement of information around the community.
The US military is currently evaluating the iLink technology and how it can be applied to solve battlefield problems as well as help promote professional development, and support military families.
The researchers said the military uses a Facebook-like social community to help soldiers learn from others who had been in Iraq. The SRI scientists met with cadets at West Point in early 2007 to help refine and further develop the system.
Prior to the development of the iLink system, the cadets had written and developed their own software to help connect communities so various types of questions arising from counter-insurgency and battlefield situations in Iraq could be asked. Basically, the iLink system cuts across three online military communities with the expressed purpose of improving the way army platoon leaders and even wives, share critical information.
Looking beyond the military, the applications for this kind of smart social networking technology are broad and diverse. The two SRI scientists are planning to spin off the technology into a startup to be called Social Kinetics. The team is currently working on a healthcare application.
And with the demand for social networking growing – estimates for social networking users in the US alone by 2012 is expected to hit 92.2 million, according to In-Stat's Hitwise research service – the commercial benefits to businesses and individuals could be immense.
The biggest demographic adopting and using social networking technologies are college students. In 2008, 95.7% of college students and 17.4 million people will go online at least once a month, according to a new report from eMarketer.
Much of the push for social networking technologies is because students demand access to friends and information whenever they want and wherever they are.
