基于社交媒体的事件感知与多模态事件脉络生成

发布时间：2018-08-28 08:19

【摘要】：随着信息技术的发展和社交媒体的流行,普通用户已经完成了从信息接受者到信息产生者的转变,每个人都可以实时分享自己身边的信息,也可以转发自己感兴趣的内容,这使得社交媒体的数据量迅速增长。在海量数据中蕴含着丰富的社会事件发生和发展的记录,如何有效地从这些数据中挖掘出有价值的信息成为了当前信息领域的重要问题。针对该问题,介绍了基于社交媒体的事件感知与多模态事件脉络生成。基于社交媒体的事件感知与多模态事件脉络生成旨在通过分析社交媒体中的文本、时间、图像、评论、观点、情感和用户交互等多模态数据,感知事件并刻画事件的关系,从而实现对事件的总结。讨论了基于社交媒体的事件感知与多模态事件脉络生成的描述模型、概念、发展历史、关键技术与挑战以及其广泛的应用领域,综述了社交媒体分析在事件感知和事件总结方面的研究进展,并对其未来发展进行了展望。
[Abstract]:With the development of information technology and the popularity of social media, ordinary users have completed the transition from information receiver to information producer. Everyone can share the information around them in real time, and they can also forward the content of their own interest. This has led to a rapid increase in the amount of data on social media. There are abundant records of the occurrence and development of social events in the massive data. How to effectively mine valuable information from these data has become an important problem in the field of information. In order to solve this problem, the event awareness and multi-modal event context generation based on social media are introduced. Event perception and multimodal event context generation based on social media aims at perceiving events and portraying the relationship of events by analyzing multimodal data such as text, time, image, comment, viewpoint, emotion and user interaction in social media. In order to achieve the summary of events. This paper discusses the description model, concept, development history, key technologies and challenges of event perception and multi-modal event context generation based on social media, as well as its wide range of applications. This paper reviews the research progress of social media analysis in event perception and event summary, and looks forward to its future development.
【作者单位】：西北工业大学计算机学院;西北工业大学明德学院;
【基金】：国家重点基础研究发展计划(973计划)(2015CB352400) 国家自然科学基金(61332005,61373119)资助
【分类号】：TP393.09

【相似文献】