The Emerging Threat from Twitter’s Social Capitalists
A couple of years, ago, network scientists began to study the phenomenon of “link farming” on Twitter and other social networks. This is the process in which spammers gather as many links or followers as possible to help spread their messages.
What these researchers discovered on Twitter was curious. They found that link farming was common among spammers. However, most of the people who followed the spam accounts came from a relatively small pool of human users on Twitter.
These people turn out to be individuals who are themselves trying to amass social capital by gathering as many followers as possible. The researchers called these people social capitalists.
That raises an interesting question: how do social capitalists emerge and what kind of influence do they have on the network? Today we get an answer of sorts, thanks to the work of Vincent Labatut at Galatasaray University in Turkey and a couple of pals who have carried out the first detailed study of social capitalists and how they behave.
These guys say that social capitalists fall into at least two different categories that reflect their success and the roles they play in linking together diverse communities. But they warn that social capitalists have a dark side too.
First, a bit of background. Twitter has around 255 million active users who send 500 million tweets every day. On average, each Twitter user has around 200 followers and follows a similar number, creating a dynamic social network in which messages percolate through the network of links.
Many of these people use Twitter to connect with friends, family, news organizations, and so on. But a few, the social capitalists, use the network purely to maximize their own number of followers.
Social capitalists essentially rely on two kinds of reciprocity to amass followers. The first is to reassure other users that if they follow this user, then he or she will follow them back, a process called Follow Me and I Follow You or FMIFY. The second is to follow anybody and hope they follow back, a process called I Follow You, Follow Me or IFYFM.
This process takes place regardless of the content of messages, which is how they get mixed up with spammers, a point that turns out to be significant later.
Clearly, social capitalists are different from Twitter users who choose to follow people based on the content they tweet. The question that Labatut and co set out to answer is how to automatically identify social capitalists in Twitter and to work out how they sit within the Twitter network.
A clear feature of the reciprocity mechanism is that there will be a large overlap between the friends and followers of social capitalists. It’s possible to measure this overlap and categorize users accordingly. Social capitalists tend to have an overlap much closer to 100 percent than ordinary users.
Having identified social capitalists, another important measure is the ratio of friends to followers. Labatut and co say that those using the FMIFY strategy have a ratio smaller than 1 while those using the IFYFM will have a ration greater than 1 (because the number of followers is always greater than the number of friends).
One final way to categorize them is by their level of success. Here, Labatut and others set an arbitrary threshold of 10,000 followers. Social capitalists with more than this are obviously more successful than those with less.
To study these groups, Labatut and coanalyze an anonymized dataset of 55 million Twitter users with two billion links between them. And they find some 160,000 users who fit the description of social capitalist.
In particular, the team is interested in how social capitalists are linked to communities within Twitter, that is groups of users who are more strongly interlinked than average.
It turns out that there is a surprisingly large variety of social capitalists playing different roles. “We ﬁnd out the different kinds of social capitalists occupy very speciﬁc roles,” say Labatut and co.
For example, social capitalists with fewer than 10,000 followers tend not to have large numbers of links within a single community but links to lots of different communities. By contrast, those with more than 10,000 followers can have a strong presence in single communities as well as link disparate communities together. In both cases, social capitalists are significant because their messages travel widely across the entire Twitter network.
That has important consequences for the Twitter network. Labatut and co say there is a clear dark side to the role of social capitalists. “Because of this lack of interest in the content produced by the users they follow, social capitalists are not healthy for a service such as Twitter,” they say.
That’s because they provide an indiscriminate conduit for spammers to peddle their wares. “[Social capitalists’] behavior helps spammers gain inﬂuence, and more generally makes the task of ﬁnding relevant information harder for regular users,” say Labatut and co.
That’s an interesting insight that raises a tricky question for Twitter and other social networks. Finding social capitalists should now be straightforward now that Labatut and others have found a way to spot them automatically. But if social capitalists are detrimental, should their activities be restricted?
Answers please in the comments section below.
Ref: http://arxiv.org/abs/1406.6611 : Identifying the Community Roles of Social Capitalists in the Twitter Network
www.mpi-sws.org/~farshad/TwitterLinkfarming.pdf: Understanding and Combating Link Farming in the Twitter Social Network
Geoffrey Hinton tells us why he’s now scared of the tech he helped build
“I have suddenly switched my views on whether these things are going to be more intelligent than us.”
Deep learning pioneer Geoffrey Hinton has quit Google
Hinton will be speaking at EmTech Digital on Wednesday.
Video: Geoffrey Hinton talks about the “existential threat” of AI
Watch Hinton speak with Will Douglas Heaven, MIT Technology Review’s senior editor for AI, at EmTech Digital.
Doctors have performed brain surgery on a fetus in one of the first operations of its kind
A baby girl who developed a life-threatening brain condition was successfully treated before she was born—and is now a healthy seven-week-old.
Get the latest updates from
MIT Technology Review
Discover special offers, top stories, upcoming events, and more.