Social Media + Credit Score? Please No!

Since quite a while I had been wanting to write this particular blog post related to some of the news making rounds on the Internet, that, your activity on different social media sites, such as Facebook and Twitter are used by the credit card companies to effect, in some way, your credit score. Though note that the company focusing on "computational advertising" on similar lines has denied such news (rumors) on their blog.

However I have been thinking on this issue quite a bit. Even if it's being done hypothetically sometime somewhere, is it an appropriate thing to do, given the affordances of these online social sites? To take an example, I felt it completely thrown away by the idea that our activities on an online space such as Facebook or Twitter could even remotely be correlated with serious physical world aspects, that are likely to have serious and widespread consequences.

For example, if not Facebook, most of us would agree that our Twitter friends or even our tweets are often not reflective of the actual person we are, or the kinds of things we might take seriously in real life. I follow several people on Twitter, and even presumably respond or RT their tweets. But should you ask me how much I really know about those guys, apart from the content of their tweets, or the number of followers they have, I really have zero clue! Similarly, also, though Facebook tries to organize user profile around common social foci, i.e. common organizational affiliations, and as a result our friend circles are often a projection of our real social ties; however it is far away from being reflective in any sense of what kind of a person we are in physical world. I would often comment on or share items from someone who is possibly just an "acquaintance" from a course I took a long time ago in early graduate school. However, if someone is trying to sneak in and use these interactions or the kinds of friends I have to make real world judgments for me, it would be utterly disappointing!

I am not trying to take away the utility of online social media in this post. After all, it's what is my research "testbed" and I am completely a "pro" social media lover! But the reason I find social media most interesting is hardly because they are some sort of "projections" of our physical world online spaces. Rather what I find really interesting as well as challenging in the scope of the interactions in these online social spaces, is how they are shaping our entire perception of socially communicating altogether! Additionally, as you would feel, the definition of a "friend" on social media has a completely different perception than what we mean by it in reality!

Nevertheless not trying to produce here evidences that studying social media has no utility to our actual lives at all! In fact, studying these online behavior could have significant impact on how our perceptions of social ties are changing, and how our modalities of interactions have evolved due to the presence of these diverse media. This can be valuable to study social phenomena, both virtual and physical. However my skepticism still stands aforth to utilize such knowledge towards making decisions that can potentially affect a person's life extremely adversely.

How "Birds of a Feather Flock Together" on Online Social Spaces

This post is among my first attempts to talk about my research and a specific problem of interest to a generic audience. Your comments are welcome!

A primary domain of interest to social researchers through several decades has been the study of interpersonal communication among groups of individuals. Communication is central to the evolution of social systems. Hence the monotonic surge of interest springs from the potential of such communication impacting variegated social processes: such as propagation of influence, evolution of communities and so on.

Typically studies geared towards understanding these social processes via communication, until a few years back, have essentially been cross-sectional in nature, often based on participant observations and surveys on relatively small sets of people. However, the advent of the "social web" over the past decade is providing researchers with newer ways to validate their hypotheses on large-scale data. For example, the Web 2.0 technologies today have provided considerable leeway to a rich rubric of platforms that promote multifaceted user interactions on shared spaces. The resultant impact of these plethora of social websites such as Flickr, YouTube, Twitter, Digg, Facebook and the Blogosphere have been widespread. Right from shopping a new car, to getting suggestions on investment, searching for the next holiday destination or even planning their next meal out, people have started to rely heavily on opinions expressed online or social resources that can provide them with useful insights into the diversely available set of options.

My research spans the study of large-scale social processes on such online platform, an area that has popularly begun to be known as "computational social sciences". This post deals with the specific problem of understanding, modeling and analyzing how information propagates in a "network" of individuals, via a certain mode of communication. Today, because electronic social data can be collected at comparatively low cost of acquisition and resource maintenance, can span over diverse populations and be acquired over extended time periods, it provides a rich and broad test bed to understand the social process of information diffusion.

Specifically, in this context, I present the impact of the "homophily" principle on information diffusion in social media. The homophily principle states that users in a social system tend to bond more with ones who are "similar" to them than ones who are dissimilar. Hence homophily structures networks: people's ego-centric social networks are often homogeneous with regard to diverse social, demographic, behavioral, and intra-personal characteristics or revolve around social foci such as co-location or commonly situated activities. The existence of such homogeneity, i.e. homophily is therefore likely to impact the information these individuals receive and propagate and the communication activities they engage in.

In our work, we consider communication occurring via posts on the popular micro-blogging service Twitter and investigate the relationship between homophily among users and the social process of diffusion. We particularly study four kind of contextual attributes on Twitter: location, activity behavior, social role and activity distribution. Thereafter we predict diffusion characteristics under homophily on these attributes based on a novel probabilistic framework. Our experimental results on a large dataset from Twitter have been promising, and reveals how "similarity breeds connection" in a social network.

Backchannel Communication & Homophily

As I am bored to death in the flight back to Tempe from New York City (happens to be a five and half hour long cross-country journey), I thought I might just use this opportunity to write. Today, sitting at JFK I was amused to read this blog post by Danah Boyd on how the sense of being "connected" at every moment is changing our ways of interaction in the real world. She talks about the perception of "backchannel communication" in public environments and how the acts of tweeting, blogging, wiki-ing makes a one-sided conversation more engaging. The article clearly can be controvertial, but as a person born in the early eighties and a person who actually saw the entire "Internet" buzz bloom since teen age, would certainly be able to connect with her thoughts!

As Danah says while she is in a lecture / talk, she would carry along her laptop and pick up the points which are not-so-clear from the presenter and / or gather more intensive information related to the topic, or even tweet about it to understand the opinions of her social network, I am at a point where I think I can justify similar acts I have indulged in, in the past.

Since I was in high school, I always hated taking notes in classes. My idea was that, if there are something I really didn't know, or I thought I should keep in mind, I ought to be able to remember it anyways. It was kind of arrogant / crude / bad information management you might say, but that's how things have been working out for me. However, once I came to grad school, I felt obliged to change my principle a little bit! I still wouldn't take notes, instead carry my laptop, and as with Danah, would look up / read relevant or useful information that was being dispensed in the course lectures. It worked out pretty okay.

Today, with no courses left to deal with (!), I often route my inquisitveness / doubts / questions / brain-storming ideas over one of these social media sites. Two of the most useful and successful backchannel modes of communication that I have come across with are the Facebook status updates, and IM (Google Talk) status updates. And fortunately, I have often received very immediate flurry of responses about those questions from my social network!

My point here is however, not to reinforce the culture of backchannel communication. Rather the point that sort of intrigues me is that the ways we consume information has radically changed over the years - from the high school taking-notes-lecture days to today's way of asking a question to your network via your Facebook status. There seems to be a lot of hue and cry about the propagation / diffusion of information in all these social networks, but the point I am trying to make here is that even our modes of consuming that diffused information has changed drastically.

Nevertheless, the more sort of research question that still remains unanswered is that why do some of these forms of backchannel communication create a chatter, while some just faze away? Of course, the simplest answer is that for certain topics there exists homophily between you and a significant segment of your network. However when I conducted a simple experiment to validate this by posting a very "research-specific" question as my Facebook status, I was surprised to see that many of the comments were actually not at all from people who seems to experts in the topic! Do what role does homophily play in promoting effective backchannel communication that Danah talks about? More fundamentally, does homophily (or the idea that your friends are "like" you) actually make sense in today's social-media-rich culture? I don't quite know the answer yet - but I am inclined to believing that multiple modes of interaction are likely to promote backchannel communication in different manner and possibly for different subsets of your social network. Some of which might actually not have any homophily with you at all!