The recent earthquake in Haiti has attracted attention from Twitter users and researchers. Twitter has been used to collect donations, to contact people on the ground, to coordinate relief efforts, etc. Recently, U. Colorado’s EPIC Group proposed a hash-tag-based syntax on top of Twitter messages to help automate the parsing of actionable messages, and to do so effectively and reliably. This is a noble effort, but as Manas Tungare points out, the proposed syntax is too complex for its intended users, who have more pressing issues than dealing with hash tags.
Manas goes on to propose a much simpler version that relies on some more sophisticated (but still tractable) natural language processing to achieve the same purpose as EPIC’s group’s tag language. I wonder, however, whether even Manas’s scheme that selects tweets based on #haiti #rescue or #haitirescue tags, and then looks for actionable verbs, etc., may be too complex, particularly given some challenges around the languages used in Haiti.
To me, this seems like a good opportunity for crowd-sourcing, either through Amazon’s Mechanical Turk, or through volunteer efforts. A distributed system that allows people to parse and code messages, distributed along the lines of SETI@Home, would be much more effective at parsing, categorizing, and routing information than a fully-automated approach.
Furthermore, the infrastructure created to manage this kind of crowd-sources (whether through Mechanical Turk or not), could be trivially reused for subsequent mobilizations of this kind. Rather than having people passively watch the same damage footage over and over on the evening news, why not have them become active participants in the relief effort? This is an opportunity to improve one aspect of our disaster preparedness infrastructure in a cost-effective and scalable manner.