首页> 外文会议>International conference on web information systems engineering >Tweet Location Inference Based on Contents and Temporal Association
【24h】

Tweet Location Inference Based on Contents and Temporal Association

机译:基于内容和时间关联的推特位置推断

获取原文

摘要

How can we infer a tweet location? Are timestamps of tweets effective for the location inference? In this study, we propose a novel method for tweet location inference based on contents and timestamps of tweets. It is important to infer the locations of tweets for the services related to locations such as recommending restaurants, sending disaster-related information to users, and providing commercial messages to users. This study has two contributions: (1) we propose a novel method to infer tweet locations based on the contents and timestamps of tweets, andbreak (2) we experimentally demonstrate the effectiveness of the proposed method using Twitter data. The experimental results suggest that the proposed method can infer tweet locations more precisely than a baseline that does not take the temporal association into account.
机译:我们如何推断推文位置?推文的时间戳是否对位置推断有效?在这项研究中,我们提出了一种基于推文的内容和时间戳的推文位置推断的新方法。推断推文的位置非常重要,这些推文的位置与位置相关,例如推荐餐厅,向用户发送与灾难有关的信息以及向用户提供商业消息。这项研究有两个贡献:(1)我们基于推文的内容和时间戳提出了一种推论推文位置的新方法,而break(2)我们通过Twitter数据实验性地证明了该方法的有效性。实验结果表明,与不考虑时间关联的基线相比,所提出的方法可以更精确地推断鸣叫位置。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号