Microblogging services like Twitter are becoming an important part of how many people manage information in their day to day activities. As microblog traffic increases (Twitter currently sees about 50 million tweets per day) information management and organization will become keen problems in this area.
Search engines are very good at what they do. But it's not clear that the standard search model works well for microblog data. For instance, microblog data is challenging to work with because it becomes most interesting in the aggregate. An individual tweet may or may not be of interest. But by intelligently connecting these short texts we can deliver information such as consensus, debate, open questions, recommendations--all in the scope of a particular information need.
This project will define the core problems in microblog search and propose solutions to these challenges in the form of both theoretical models and prototype search systems.
Initial work is described in our 2010 SIGIR poster, Hashtag Retrieval in a Microblogging Environment.