Recognizing patterns and rhythms in social media data
Wayne Gretsky is quoted as saying that a great hockey player plays where “the puck is going to be,” not where it is. Gretsky, like the great NBA point guards (think Magic Johnson or Mark Price), was quick to detect emerging patterns in movement and flows–then take advantage of what was about to happen. In our research efforts, we often try to detect patterns in order to explore what these patterns may tell us about underlying processes.
The SoMe Lab is examining patterns in the movement and flows of information between and among social media platforms. We observe that traditional media news may inform or trigger information exchanges in the blogosphere or Twitter; and vice versa. We want to look closely at these patterns to gain insights into phenomena such as virality, the birth and life cycle of interest networks, and the dynamics of a fluid cast of gatekeepers. The accompanying image illustrates the patterns that distinguish the volume of tweets, blog posts, and traditional news items following the pepper spraying incident at UC-Davis November 18, 2011.
We’re far from developing a comprehensive view of these flows, but we have been able to visualize and understand what seem to be distinguishing frequency patterns of news and conversations about distinctive types of events.
We wrote a research note on this topic that will appear in the proceedings of the 2013 iConference (to be held in Fort Worth in February; prepublication draft here). In the note, we illustrate and discuss the numbers of tweets, blog posts, and news stories that focused on specific events related to the Occupy movement during the period from October 2011 through November 2012. (The above illustration is taken from this research note.) We looked at the timing and volume of stories and tweets at specific planned events and serendipitous events.
We observe that different types of events appear to exhibit particular patterns of activity (similar to what Sharon Meraz and Zizi Papacharissi refer to as “rhythms” in their IR13 presentation). We found a contrast among events that were planned—by civilian authorities or by protesters—and those that were unexpected and serendipitous. For example, the number of traditional media stories (newspapers, TV) in advance of authority-planned events is much greater than the number for in advance of protester-planned events. The number of stories, blog posts, and tweets about serendipitous events (such as the pepper spraying of students at UC-Davis) peaked soon after the events, but often had longer periods of activity. Some events exhibited secondary peaks appearing as a consequence of follow-up stories (e.g., investigation reports). Other events and their stories exhibited durability as they evolved into memes that represented more than the events themselves (e.g, the pepper-spraying officer).
The evidence in our initial efforts suggest that patterns—visualized using computer-based algorithms but observed and interpreted by researchers—may be a productive approach to exploring the evolutionary dynamics of our emerging information ecosystem.
The patterns we observe are relatively simple—almost obvious once they have been pointed out—but we may use these simple patterns to point us to more complex relationships. As researchers, we won’t pretend to be Wayne Gretsky or Magic Johnson, but perhaps we can improve the tools that enable us to see patterns in our data and use these tools to help us probe the mechanisms that produce these patterns.
If you have similar observations about information flow patterns in social media, let us hear from you. And if you have techniques for visualizing these patterns, let’s compare notes.