Research

Perspective

Our lives are filled with countless interactions with other people–a bump, a glance, a text message, a video. They are not necessarily planned, but looking out across the sea of these interactions, we find that they are not random.  En masse, our interactions create patterns with enough regularity that they are assigned names, such as “small-world networks” and “information cascades.”

These are not merely statistical ephemera. From the inside, such patterns become a context that shapes local interactions, which in turn resolve into new patterns.  This reflexiveness leads our species to wander collectively across the space of possible patterns–one pattern begets another begets another.

Social technology continues to mediate more and more of our interactions. Its growing ubiquity means that it will most certainly influence the progression of patterns at a societal level.  A single design change, deployed across a billion people might fundamentally alter the path we collectively travel. Who makes these design decisions?  How should they be made?

Those who study social technology have a responsibility both to develop a more sophisticated understanding of its impact on our population, and to foster ethical design choices that are based on it.

My hope is to contribute to and promote the responsible application of such an understanding.

Projects

Knowledge Evolution in Online Conversation–Are some online communities more innovative than others?  Can we measure the innovation potential of a community? Can we improve it?

Illustrates knowledge construction during an online conversation.  Nodes represent conversation about a topic at different times.  Color indicates topic identity, size indicates relative excitement about that topic at that point, and links illustrate how topics evolve.  The node labeled "A" is the point where knowledge creation occurs.

Illustrates knowledge construction during an online conversation. Nodes represent conversation about a topic at different times. Color indicates topic identity, size indicates relative excitement about that topic at that point, and links illustrate how topics evolve. The node labeled “A” is the point where knowledge creation occurs.

I developed an algorithm called TEvA which extracts topics in online conversation and identifies moments where topics merge or split. Using this algorithm, I have found that moments where conversation brings together many prior topics and interlocutors become more excited (faster posting, more balanced participation) are moments where the groups are likely to create new knowledge.  These findings are documented in Analyzing Knowledge Evolution in Computer Mediated Teams. I believe this is the basis for a general, automated approach to quantifying the innovation potential of an online community.

I am pursuing funding with other collaborators to combine measurements of emotion and structural dynamics to develop a more comprehensive understanding of knowledge construction in online learning communities.  I am seeking both graduate and undergraduate students who would like to help with this effort.

Diffusion of Narrative in Social Networks–More to come.

Evolutionary Crowdsourcing–More to come.

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s