Mining Multimodal Information on Social Media for Increased Situational Awareness
Mining Multimodal Information on Social Media for Increased Situational Awareness
复制标题
挖掘社交媒体上的多模式信息以提高态势感知
DOI：
--
复制
发表时间：
2017
期刊：
影响因子：
--
通讯作者：
K. Ahmad
中科院分区：
文献类型：
--
作者：
Stephen Kelly;Xiubo Zhang;K. Ahmad
社交媒体平台已成为及时描述重大事件的大量实时信息的来源。在本文中，我们描述了一种从 Twitter 消息中的文本和图像内容中实时提取信息的系统，并结合消息的时空元数据来过滤紧急事件的数据流，并在交互式地图上可视化输出。通过分析发布的文本内容和图像，监控某个地理区域的 Twitter 消息是否有洪水事件。将检测到的事件与真实情况进行比较，以查看社交媒体中的信息是否与实际事件相关。我们建议将入侵指数作为该原型的一部分，以促进符合道德的数据收集。原型系统创建了一个地图图层，可根据地理位置可视化分析和过滤的 Twitter 消息。
Social media platforms have become a source of high volume, real-time information describing significant events in a timely fashion. In this paper we describe a system for the real-time extraction of information from text and image content in Twitter messages and combine the spatio-temporal metadata of the messages to filter the data stream for emergency events and visualize the output on an interactive map. Twitter messages for a geographic region are monitored for flooding events by analysing the text content and images posted. Events detected are compared with a ground truth to see if information in social media correlates with actual events. We propose an Intrusion Index as part of this prototype to facilitate ethical harvesting of data. A map layer is created by the prototype system that visualises the analysis and filtered Twitter messages by geolocation.