arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1902.03111cs.SIcs.LG
收藏

使用具有动态结构的深度学习从推文进行高分辨率家庭位置预测

High-resolution home location prediction from tweets using deep learning with dynamic structure

Florida State University(佛罗里达州立大学);University of West Florida(西佛罗里达大学)

Meysam Ghaffari, Ashok Srinivasan, Xiuwen Liu

摘要:

及时和高分辨率地估计足够大的人口子集的家庭位置对于有效的灾害应对和公共卫生干预至关重要,但这仍然是一个悬而未决的问题。传统的数据来源,如人口普查和调查,有很大的时间滞后,无法捕捉季节性趋势。最近,社交媒体数据已被利用来解决这个问题,利用其庞大的用户群和实时性。然而,固有的稀疏性和噪声,以及家庭位置的大估计不确定性,限制了它们的有效性。因此,以前的许多研究只针对粗略的空间分辨率,高分辨率方法的精度有限。在本文中,我们开发了一种深度学习解决方案,该解决方案使用两阶段动态结构来处理稀疏和嘈杂的社交媒体数据。在第一阶段,使用随机森林实现高召回,产生更平衡的归属位置候选。然后使用两个深度神经网络来高精度地检测家庭位置。我们在一个常用的数据集上获得了超过90%的大子集准确率。与其他高分辨率方法相比,我们的方法通过将高分辨率家庭预测误差从21%以上降低到8%以下,从而产生高达60%的误差减少。系统的比较表明,我们的方法提供了最高的准确性,为整个样本和子集。对一个现实公共卫生问题的评价进一步验证了该方法的有效性。

英文摘要:

Timely and high-resolution estimates of the home locations of a sufficiently large subset of the population are critical for effective disaster response and public health intervention, but this is still an open problem. Conventional data sources, such as census and surveys, have a substantial time lag and cannot capture seasonal trends. Recently, social media data has been exploited to address this problem by leveraging its large user-base and real-time nature. However, inherent sparsity and noise, along with large estimation uncertainty in home locations, have limited their effectiveness. Consequently, much of previous research has aimed only at a coarse spatial resolution, with accuracy being limited for high-resolution methods. In this paper, we develop a deep-learning solution that uses a two-phase dynamic structure to deal with sparse and noisy social media data. In the first phase, high recall is achieved using a random forest, producing more balanced home location candidates. Then two deep neural networks are used to detect home locations with high accuracy. We obtained over 90% accuracy for large subsets on a commonly used dataset. Compared to other high-resolution methods, our approach yields up to 60% error reduction by reducing high-resolution home prediction error from over 21% to less than 8%. Systematic comparisons show that our method gives the highest accuracy both for the entire sample and for subsets. Evaluation on a real-world public health problem further validates the effectiveness of our approach.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑