The information overload created by social media messages in emergency situations challenges response organizations to find targeted content and users. We aim to select useful messages by detecting the presence of conversation as an indicator of coordinated citizen action. Using simple linguistic indicators associated with conversation analysis in social science, we model the presence of conversation in the communication landscape of Twitter in a large corpus of 1.5M tweets for various disaster and non-disaster events spanning different periods, lengths of time and varied social significance. Within Replies, Retweets and tweets that mention other Twitter users, we found that domain-independent, linguistic cues distinguish likely conversation from non-conversation in this online (mediated) communication. We demonstrate that conversation subsets within Replies, Retweets and tweets that mention other Twitter users potentially contain more information than non-conversation subsets. Information density also increases for tweets that are not Replies, Retweets or mentioning other Twitter users, as long as they reflect conversational properties. From a practical perspective, we have developed a model for trimming the candidate tweet corpus to identify a much smaller subset of data for submission to deeper, domain-dependent semantic analyses for the identification of actionable information nuggets for coordinated emergency response.
Available at: http://works.bepress.com/john_flach/82/