TwitterStand: news in tweets

摘要: Twitter is an electronic medium that allows a large user populace to communicate with each other simultaneously. Inherent asymmetrical relationship between friends and followers provides interesting social network like structure among the users of Twitter. messages, called tweets, are restricted 140 characters thus usually very focused. We investigate use build news processing system, TwitterStand, from tweets. The idea capture tweets correspond late breaking news. result analogous distributed wire service. difference identities contributors/reporters not known in advance there may be many them. Furthermore, sent according schedule: they occur as happening, tend noisy while arriving at high throughput rate. Some issues addressed include removing noise, determining tweet clusters interest bearing mind methods must online, relevant locations associated