Assessing spatiotemporal predictability of LBSN: a case study of three Foursquare datasets
Assessing spatiotemporal predictability of LBSN: a case study of three Foursquare datasets
复制标题
DOI：
10.1007/s10707-016-0279-5
复制
发表时间：
2018-07-01
期刊：
影响因子：
2
通讯作者：
Zipf, Alexander
中科院分区：
文献类型：
--
作者：
Li, Ming;Westerholt, Rene;Zipf, Alexander
基于位置的社交网络（LBSN）为研究人员获取有关人类时空行为的知识以及预测人们未来在空间和时间上的行为方式提供了新的可能性。在这些方面成功利用 LBSN 的一个重要要求是彻底了解各个数据集，包括它们的内在潜力和局限性。具体来说，在预测方面，我们必须知道我们实际上可以从数据中期望什么，以及如何最大限度地发挥它们的用处。然而，文献中仍然很大程度上缺乏这方面的知识。因此，这项工作探讨了一个特定的方面，即 LBSN 数据集的理论可预测性。未覆盖的可预测性用区间表示。区间的下界对应于容易预测的规则行为的数量，代表任何算法应该能够达到的正确预测率。上限对应于数据集中包含的信息量，表示任何算法都无法超过的最大正确预测率。以来自三个美国城市的三个 Foursquare 数据集为例进行研究。研究发现，在我们研究的数据集中，人类时空行为的可预测性下限为 27%，上限为 92%。因此，阐明了数据集预测人类时空行为的内在潜力，并且所揭示的间隔允许对预测质量以及相关算法的质量进行现实评估。此外，为了进一步了解数据集的实际使用，从三个不同的角度研究了可预测性和签到频率之间的关系。结果发现，个人观点在可预测性和签到频率之间没有提供显着的相关性。相反，从时间和空间的角度来看，相同的两个量被发现呈负相关。我们的研究进一步表明，频繁出现的环境和一些特殊的地理特征（例如机场）可能是有效改进预测算法的良好起点。总的来说，这项研究提供了有关 LBSN 数据集性质的新颖知识，并为更合理地利用数据集提供了实用见解。
Location-based social networks (LBSN) have provided new possibilities for researchers to gain knowledge about human spatiotemporal behavior, and to make predictions about how people might behave through space and time in the future. An important requirement of successfully utilizing LBSN in these regards is a thorough understanding of the respective datasets, including their inherent potential as well as their limitations. Specifically, when it comes to predictions, we must know what we can actually expect from the data, and how we could maximize their usefulness. Yet, this knowledge is still largely lacking from the literature. Hence, this work explores one particular aspect which is the theoretical predictability of LBSN datasets. The uncovered predictability is represented with an interval. The lower bound of the interval corresponds to the amount of regular behaviors that can easily be anticipated, and represents the correct predication rate that any algorithm should be able to achieve. The upper bound corresponds to the amount of information that is contained in the dataset, and represents the maximum correct prediction rate that cannot be exceeded by any algorithms. Three Foursquare datasets from three American cities are studied as an example. It is found that, within our investigated datasets, the lower bound of predictability of the human spatiotemporal behavior is 27%, and the upper bound is 92%. Hence, the inherent potentials of the dataset for predicting human spatiotemporal behavior are clarified, and the revealed interval allows a realistic assessment of the quality of predictions and thus of associated algorithms. Additionally, in order to provide further insight into the practical use of the dataset, the relationship between the predictability and the check-in frequencies are investigated from three different perspectives. It was found that the individual perspective provides no significant correlations between the predictability and the check-in frequency. In contrast, the same two quantities are found to be negatively correlated from temporal and spatial perspectives. Our study further indicates that the heavily frequented contexts and some extraordinary geographic features such as airports could be good starting points for effective improvements of prediction algorithms. In general, this research provides novel knowledge regarding the nature of the LBSN dataset and practical insights for a more reasonable utilization of the dataset.