You Are Where You Go: Inferring Demographic Attributes from Location Check-ins
You Are Where You Go: Inferring Demographic Attributes from Location Check-ins
复制标题
DOI：
10.1145/2684822.2685287
复制
发表时间：
2015-02
期刊：
影响因子：
--
通讯作者：
Yuan Zhong;Nicholas Jing Yuan;Wen Zhong;Fuzheng Zhang;Xing Xie
中科院分区：
文献类型：
--
作者：
Yuan Zhong;Nicholas Jing Yuan;Wen Zhong;Fuzheng Zhang;Xing Xie
用户分析对许多在线服务至关重要。最近的几项研究表明，人口统计学属性可以从不同的在线行为数据中预测，例如用户在Facebook上的“喜欢”，友谊关系以及推文的语言特征。但位置签到作为用户线上和线下生活的桥梁，在用户档案的推断中却被普遍忽视。在本文中，我们调查的预测能力的位置签入推断用户的人口统计数据，并提出了一个简单而通用的位置配置文件（L2 P）框架。更具体地说，我们提取丰富的语义用户的签到的空间性，时间性和位置知识，其中的位置知识丰富的语义挖掘从异构域，包括在线客户评论网站和社交网络。此外，张量因子分解绘制出低维表示的用户的内在签到偏好考虑上述因素。同时，提取的特征用于训练预测模型，以推断各种人口统计属性。我们收集了一个大型数据集，其中包括来自在线社交网络的159，530名经过验证的用户的个人资料。基于该数据集的大量实验结果验证了：1）位置签到是各种人口统计属性的诊断表示，例如性别，年龄，教育背景和婚姻状况; 2）所提出的框架在各种评估指标方面大大优于比较模型，例如精度，召回，F-测量和AUC。
User profiling is crucial to many online services. Several recent studies suggest that demographic attributes are predictable from different online behavioral data, such as users' "Likes" on Facebook, friendship relations, and the linguistic characteristics of tweets. But location check-ins, as a bridge of users' offline and online lives, have by and large been overlooked in inferring user profiles. In this paper, we investigate the predictive power of location check-ins for inferring users' demographics and propose a simple yet general location to profile (L2P) framework. More specifically, we extract rich semantics of users' check-ins in terms of spatiality, temporality, and location knowledge, where the location knowledge is enriched with semantics mined from heterogeneous domains including both online customer review sites and social networks. Additionally, tensor factorization is employed to draw out low dimensional representations of users' intrinsic check-in preferences considering the above factors. Meanwhile, the extracted features are used to train predictive models for inferring various demographic attributes. We collect a large dataset consisting of profiles of 159,530 verified users from an online social network. Extensive experimental results based upon this dataset validate that: 1) Location check-ins are diagnostic representations of a variety of demographic attributes, such as gender, age, education background, and marital status; 2) The proposed framework substantially outperforms compared models for profile inference in terms of various evaluation metrics, such as precision, recall, F-measure, and AUC.