Download Now Free registration required
Real-time micro-blogging services such as Twitter are widely recognized for their social dynamics - how they both encapsulate a social graph and propagate information across it. However, the content of this information is equally interesting since it frequently reflects individual experiences with a broad variety of real-time events. Indeed, events of broad interest are commonly revealed in correlated spikes of semantically-related posting activity. In this paper, the authors explore one such application this of phenomenon: using Twitter data to infer on-line Internet service availability. The authors show that simple techniques are sufficient to extract key semantic content from "Tweets" (i.e., service X is down) and also filter out extraneous noise.
- Format: PDF
- Size: 218.3 KB