Real-time Event Detection based on Geo Extraction and Temporal Analysis | |
Xiao Feng1; Shuwu Zhang1; Wei Liang1; Zhe Tu2 | |
2014-12 | |
会议名称 | International Conference on Advanced Data Mining and Applications (ADMA) |
会议录名称 | In Proceedings of the 10th International Conference on Advanced Data Mining and Applications (ADMA) |
会议日期 | 2014-12 |
会议地点 | Guilin, China |
摘要 |
Abstract. Microblogging is an important source of information about what is happening in the real world. In this work, we propose a novel approach for real-time event detection targeting accident and disaster events (ADEs) using microblogs from Sina Weibo. Our aim is to detect out every microblog which reports a real-world occurrence of a target event from the microblog stream. We formulate the event detection problem as a classification problem using microblog-based features, linguistic features, content features, and event features. We propose a street-level location extraction method based on the textual content to cooperate geo-information extraction. In order to deliver fresh events, we use a temporal analysis method to filter away past events. We compare our method with two state-of-the-art baselines on event detection, and achieve improvements in both precision and recall. |
关键词 | Event Detection Microblogs Geo-information Extraction Temporal Analysis |
收录类别 | EI |
语种 | 英语 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/11230 |
专题 | 数字内容技术与服务研究中心_版权智能与文化计算 |
作者单位 | 1.Institue of Automation, Chinese Academy of Sciences, Beijing, China 2.Beijing University of Chemical Technology, Beijing, China |
推荐引用方式 GB/T 7714 | Xiao Feng,Shuwu Zhang,Wei Liang,et al. Real-time Event Detection based on Geo Extraction and Temporal Analysis[C],2014. |
条目包含的文件 | ||||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Xiao Feng ADMA2014.p(340KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论