Spatio-temporal sentiment hotspot detection using geotagged photos

Spatio-temporal sentiment hotspot detection using geotagged photos
复制标题

使用地理标记照片进行时空情感热点检测

DOI:
10.1145/2996913.2996978
复制
发表时间:
2016
期刊:
Proceedings of the 24th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems
影响因子:
--
通讯作者:
S. Newsam
S. Newsam
中科院分区:
--
文献类型:
--
作者:
Yi Zhu;S. Newsam

文献摘要

被引文献

相似文献

我们使用带有地理标记的照片集对公众情绪进行时空分析。我们开发了一个基于深度学习的分类器,可以预测图像传达的情感。这使我们能够将情感与地点联系起来。我们进行空间热点检测,并表明不同的情绪有不同的空间分布,符合预期。我们还使用照片的捕获时间进行时间分析。我们的时空热点检测正确地识别了特定情绪的新兴集中,对选定位置的逐年分析表明,预测的情绪和已知事件之间存在很强的时间相关性。
We perform spatio-temporal analysis of public sentiment using geotagged photo collections. We develop a deep learning-based classifier that predicts the emotion conveyed by an image. This allows us to associate sentiment with place. We perform spatial hotspot detection and show that different emotions have distinct spatial distributions that match expectations. We also perform temporal analysis using the capture time of the photos. Our spatio-temporal hotspot detection correctly identifies emerging concentrations of specific emotions and year-by-year analyses of select locations show there are strong temporal correlations between the predicted emotions and known events.