TCB: A feature transformation method based central behavior for user interest prediction on mobile big data
TCB: A feature transformation method based central behavior for user interest prediction on mobile big data
复制标题
TCB：一种基于中心行为的移动大数据用户兴趣预测特征变换方法
DOI：
10.1177/1550147716671256
复制
发表时间：
2016-10
影响因子：
2.3
通讯作者：
Wu Yuanshan
中科院分区：
文献类型：
--
作者：
Zhou Chen;Jiang Hao;Chen Yanqiu;Wu Jing;Zhou Jianguo;Wu Yuanshan
虽然传统的时空特征，如旋转、概率和连续记录之间的间隔，有助于建立人体动力学模型，但这些基本的时空特征在预测移动用户兴趣方面的重要性并未得到充分的研究。此外，这些典型特征忽略了这样一个事实，即人类行为是高度可预测和集中的。具体地说，人的移动性被限制在由几个热点描绘的小区域内，并且用户倾向于在几个特定的时隙上密集地访问移动互联网，本文将这些时隙定义为热点时间。因此，本文提出了一种基于中心行为的特征变换方法来构造信息特征集。基于中心行为的变换方法只需要少量的记录来提取每个用户的热点/热点时间信息，并将原始记录投影到一个相对向量空间中，该向量空间的坐标表示相应的中心性(热点/热点时间)所受的影响。然后，通过与热点/热点时间相关的统计摘要进一步丰富了新的空间。在现有分类算法的基础上，基于中心行为的转换方法在真实世界中产生的大量使用细节记录数据集上进行了验证。结果表明，基于中心行为的转换方法生成的特征在查准率、查全率和F1-Score方面都优于传统的时空特征和偏好。
Although traditional spatial-temporal features, such as gyration, probability, and the intervals between consecutive records, have contributed to model human dynamics, the importance of these basic spatial-temporal features in predicting mobile user interest is not fully investigated. Moreover, these typical features ignore the fact that human behaviors are highly predictable and centralized. Specifically, human mobility is constrained in a small area depicted by several hotspots, and users tend to access mobile Internet intensively on several particular timeslots, which are defined as hot-times in this article. Thus, this article proposes a feature transformation method based central behavior to construct informative feature sets. Transformation method based central behavior only requires small amount of records to extract hotspots/hot-times information for every user, and projects original records into a relative vector space, of which coordinates represent the effects suffered from corresponding centralities (hotspots/hot-times). Then, the new space is further enriched by statistical summaries related to hotspots/hot-times. Based on the state-of-the-art classification algorithms, the proposed transformation method based central behavior is validated on a large Usage Detail Records dataset generated in real physical world. Results show that features generated by transformation method based central behavior surpass traditional spatial-temporal features and preference in the terms of precision, recall, and f1-score.
登录
查看更多内容
DOI：
10.1145/2684822.2685287
发表时间：
2015-02
期刊：
Proceedings of the Eighth ACM International Conference on Web Search and Data Mining
影响因子：
--
作者：
Yuan Zhong;Nicholas Jing Yuan;Wen Zhong;Fuzheng Zhang;Xing Xie
通讯作者：
Yuan Zhong;Nicholas Jing Yuan;Wen Zhong;Fuzheng Zhang;Xing Xie
影响因子：
2.9
作者：
Zhi-Dan Zhao;Shimin Cai;Yang Lu
通讯作者：
Zhi-Dan Zhao;Shimin Cai;Yang Lu
影响因子：
22.7
作者：
G. Szabó;B. Huberman
通讯作者：
G. Szabó;B. Huberman
DOI：
10.2139/ssrn.1755748
发表时间：
2011-02
期刊：
Information Systems: Behavioral & Social Methods eJournal
影响因子：
--
作者：
S. Asur;B. Huberman;G. Szabó;Chunyan Wang
通讯作者：
S. Asur;B. Huberman;G. Szabó;Chunyan Wang
DOI：
10.1145/2699667
发表时间：
2015-02
期刊：
ACM Transactions on Information Systems (TOIS)
影响因子：
--
作者：
Quan Yuan;G. Cong;Kaiqi Zhao-;Zongyang Ma;Aixin Sun
通讯作者：
Quan Yuan;G. Cong;Kaiqi Zhao-;Zongyang Ma;Aixin Sun