Estimating the Locations of Emergency Events from Twitter Streams

Abstract

Sina Weibo, the most popular microblogging service in China, plays a significance role in sharing and exchanging information on local and global level. Actually, part of the information are correlated with some events which may be local ones such as accident, protests or natural disasters to widely ones such as events concerning well-known people or political affairs. Our research interest is to detect the location where some events are occurring by analyzing only data from weibo information. In this paper, we de- note three kind of location for each weibo: (1) content-based location; (2) posting location; (3) registration location of author of weibo. There are two main contributions in our work: (a) detect event-aware location of each weibo; (b) estimate accurate event location based on sets of event-aware locations. In order to detect event-aware location, we model there kinds of location data of each weibo to tackle with detection challenge. After we obtained a set of event-aware locations, we use a hierarchical clustering to estimate the accurate event location. The result showed that our method could improve the accuracy of event location estimation.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 47 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.