Crowdsourced POI labelling: Location-aware result inference and Task Assignment
Crowdsourced POI labelling: Location-aware result inference and Task Assignment
复制标题
DOI：
10.1109/icde.2016.7498229
复制
发表时间：
2016-05
期刊：
影响因子：
--
通讯作者：
Huiqi Hu;Yudian Zheng;Z. Bao;Guoliang Li;Jianhua Feng;Reynold Cheng
中科院分区：
文献类型：
--
作者：
Huiqi Hu;Yudian Zheng;Z. Bao;Guoliang Li;Jianhua Feng;Reynold Cheng
识别兴趣点（POI）的标签（也称为POI标签）在基于位置的服务中提供了显著的益处。然而，用户手动添加或人工算法生成的原始标签的质量无法得到保证。这种低质量的标签降低了可用性，并导致糟糕的用户体验。在本文中，通过观察众包是最适合计算机硬任务，我们利用众包来提高POI标签的质量。据我们所知，这是第一个关于众包POI标签任务的工作。具体地，存在两个子问题：（1）如何基于工作者的回答来推断每个POI的正确标签，以及（2）如何有效地将适当的任务分配给工作者以便为下一个可用的工作者做出更准确的推断。为了解决这两个问题，我们提出了一个框架，包括一个推理模型和一个在线任务分配器。推理模型通过精心利用（i）工作者的固有品质、（ii）工作者与POI之间的空间距离以及（iii）POI影响来测量工作者对POI的品质，一旦工作者提交答案，这就可以提供可靠的推理结果。由于工人是动态的，在线任务分配器明智地分配适当的任务给他们，以利于推理。推理模型和任务分配器交替工作，以不断提高整体质量。我们在一个真实的众包平台上进行了大量的实验，在两个真实的数据集上的结果表明，我们的方法显着优于最先进的方法。
Identifying the labels of points of interest (POIs), aka POI labelling, provides significant benefits in location-based services. However, the quality of raw labels manually added by users or generated by artificial algorithms cannot be guaranteed. Such low-quality labels decrease the usability and result in bad user experiences. In this paper, by observing that crowdsourcing is a best-fit for computer-hard tasks, we leverage crowdsourcing to improve the quality of POI labelling. To our best knowledge, this is the first work on crowdsourced POI labelling tasks. In particular, there are two sub-problems: (1) how to infer the correct labels for each POI based on workers' answers, and (2) how to effectively assign proper tasks to workers in order to make more accurate inference for next available workers. To address these two problems, we propose a framework consisting of an inference model and an online task assigner. The inference model measures the quality of a worker on a POI by elaborately exploiting (i) worker's inherent quality, (ii) the spatial distance between the worker and the POI, and (iii) the POI influence, which can provide reliable inference results once a worker submits an answer. As workers are dynamically coming, the online task assigner judiciously assigns proper tasks to them so as to benefit the inference. The inference model and task assigner work alternately to continuously improve the overall quality. We conduct extensive experiments on a real crowdsourcing platform, and the results on two real datasets show that our method significantly outperforms state-of-the-art approaches.