Analysis team drills down on social networks

Aug 03, 2014 by Nancy Owano weblog
Analysis team drills down on social networks
Example of construction of the Conversation Graph from conversation data. Credit: arXiv:1407.5547 [cs.CY]

Whether a teacher is posting a link for a colleague or a pet owner is sending her sister a photo of her sleeping dog, everything is of consequence for a newer breed of social network analysts who are trying to use their computers to map out social behavior and understand social structures. Researchers are eyeballing messages online, from informational, to chatty, to networking attempts—who likes who and who is following who. MIT Technology Review now reports on a recent effort to peer even further into social structures. In a paper recently submitted to the arXiv server, a team takes a still more nuanced analysis of online social data.

"Reading the Source Code of Social Ties" is by Luca Maria Aiello, research scientist at Yahoo Labs Barcelona, Rossano Schifanella, University of Torino, and Bogdan State, Stanford. The work was done when Schifanella and State were visiting Yahoo Labs Barcelona. In their paper, they discussed three different categories. Describing their work, MIT Technology Review said, "They tease apart the nature of the links that form on social networks and say these atoms fall into three different categories. They also show how to extract this information automatically and then characterize the relationships according to the combination of atoms that exist between individuals. Their ultimate goal: to turn anthropology into a full-blooded subdiscipline of computer science."

The authors used data sets from large social networks, messages sent between users of the aNobii social network, which people use to talk about books and users who commented on their photos on Flickr. One category was social-status messages, displaying appreciation or announcing the creation of the social tie such as a follow or like. The second category involved social support of some kind, such as greeting or welcoming someone to a website, to express affection or send wishes, jokes and laughter. The third category was knowledge exchange. The team worked on an algorithm to categorize the messages based on message content and similarity to messages of the same type.

The authors said they believed their methods would find applications in "online social media services," ranging from recommendation to visual link summarization.

MIT Technology Review called the study fascinating, providing "a new way of looking at as strings of interactions. In a way, it changes the atomic theory of social ties into a kind of string theory."

Their paper won a best-presentation award in June at the ACM Web Science 2014 Conference at Indiana University, Bloomington.

Explore further: China Internet population reaches 632 million

More information: Reading the Source Code of Social Ties, arXiv:1407.5547 [cs.CY] arxiv.org/abs/1407.5547

Abstract
Though online social network research has exploded during the past years, not much thought has been given to the exploration of the nature of social links. Online interactions have been interpreted as indicative of one social process or another (e.g., status exchange or trust), often with little systematic justification regarding the relation between observed data and theoretical concept. Our research aims to breach this gap in computational social science by proposing an unsupervised, parameter-free method to discover, with high accuracy, the fundamental domains of interaction occurring in social networks. By applying this method on two online datasets different by scope and type of interaction (aNobii and Flickr) we observe the spontaneous emergence of three domains of interaction representing the exchange of status, knowledge and social support. By finding significant relations between the domains of interaction and classic social network analysis issues (e.g., tie strength, dyadic interaction over time) we show how the network of interactions induced by the extracted domains can be used as a starting point for more nuanced analysis of online social data that may one day incorporate the normative grammar of social interaction. Our methods finds applications in online social media services ranging from recommendation to visual link summarization.

add to favorites email to friend print save as pdf

Related Stories

Global communications and the mesh of civilizations

Feb 18, 2014

It has been 20 years since political scientist Samuel P. Huntington published his influential "Clash of Civilizations" prediction that cultural differences and "fault lines between civilizations will be the battle lines of ...

Links between science, technology and social issues

May 27, 2014

Science and technology is the vital driving force for economic and social development. However, the fundamental links between science, technology, and society are unclear because of their complexity and hidden ...

Misinformation diffusing online

Jul 31, 2014

The spread of misinformation through online social networks is becoming an increasingly worrying problem. Researchers in India have now modeled how such fictions and diffuse through those networks. They described details ...

Recommended for you

Forging a photo is easy, but how do you spot a fake?

Nov 21, 2014

Faking photographs is not a new phenomenon. The Cottingley Fairies seemed convincing to some in 1917, just as the images recently broadcast on Russian television, purporting to be satellite images showin ...

Algorithm, not live committee, performs author ranking

Nov 21, 2014

Thousands of authors' works enter the public domain each year, but only a small number of them end up being widely available. So how to choose the ones taking center-stage? And how well can a machine-learning ...

Professor proposes alternative to 'Turing Test'

Nov 19, 2014

(Phys.org) —A Georgia Tech professor is offering an alternative to the celebrated "Turing Test" to determine whether a machine or computer program exhibits human-level intelligence. The Turing Test - originally ...

Image descriptions from computers show gains

Nov 18, 2014

"Man in black shirt is playing guitar." "Man in blue wetsuit is surfing on wave." "Black and white dog jumps over bar." The picture captions were not written by humans but through software capable of accurately ...

User comments : 0

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.