Please wait a minute...
Advanced Search
数据分析与知识发现  2019, Vol. 3 Issue (6): 75-82    DOI: 10.11925/infotech.2096-3467.2018.1085
  研究论文 本期目录 | 过刊浏览 | 高级检索 |
轨迹数据融合用户表示方法的重要位置发现*
曾庆田1,2,戴明弟2,李超1,3(),段华2,赵中英2
1(山东科技大学电子信息工程学院 青岛 266590)
2(山东科技大学计算机科学与工程学院 青岛 266590)
3(同济大学嵌入式系统与服务计算教育部重点实验室 上海 201804)
Discovering Important Locations with User Representation and Trace Data
Qingtian Zeng1,2,Mingdi Dai2,Chao Li1,3(),Hua Duan2,Zhongying Zhao2
1(College of Electronic Information Engineering, Shandong University of Science and Technology, Qingdao 266590, China)
2(College of Computer Science and Engineering, Shandong University of Science and Technology, Qingdao 266590, China)
3(Key Laboratory of Embedded System and Service Computing, Ministry of Education, Tongji University, Shanghai 201804, China)
全文: PDF(2389 KB)   HTML ( 1
输出: BibTeX | EndNote (RIS)      
摘要 

目的】发现重要位置, 为用户行为轨迹特征和规律的研究提供良好数据支撑。【方法】提出融合用户表示方法的重要位置预测模型, 提出基于Word2Vec的用户行为轨迹的向量化表示方法; 基于用户向量相似度构建用户关系网络, 提取访问位置上的核心用户; 通过核心用户的访问行为进行重要位置预测。【结果】实验结果表明, 基于本文方法过滤后的核心用户对重要位置进行标注, 比直接标注的正确率提升7%。在地图上显示标注区域, 能够有效发现对应的住宅区和商业区。【局限】本文方法只能够识别居住地和工作地, 更加细粒度的标注有待进一步实现。【结论】本文所提基于用户表示学习的核心用户过滤方法, 对重要位置的标注具有重要意义, 同时为研究用户的轨迹行为特征和规律提供了更为科学的决策支持。

服务
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章
曾庆田
戴明弟
李超
段华
赵中英
关键词 重要位置轨迹挖掘表示学习支持向量机    
Abstract

[Objective] This paper tries to discover the important locations of users, aiming to provide good data support for user behavior studies. [Methods] We presented a model for predicting important locations based on user representation. First, we proposed a vectorized representation method to predict user behaviors based on Word2Vec. Then, we constructed a user relationship network based on the similarity of user vectors to extract core users. Finally, we predicted the important locations by the behaviors of core users. [Results] The precison of important locations classifiction was 7% higher than those of the exisitng methods. Moreover, the residential and commercial areas were shown in the labeled map. [Limitations] Our method can only identify residential and business areas. [Conclusions] The proposed method could effectively find important locations and provide more supports to study user behaviors.

Key wordsImportant Locations    Trajectory Mining    Representation Learning    Support Vector Machine
收稿日期: 2018-09-28     
基金资助:*本文系教育部人文社会科学青年基金项目“网络大数据环境下的学习者行为挖掘”(项目编号: 16YJCZH041)、教育部人文社会科学青年基金项目“大数据环境下基于学习者行为挖掘的个性化用户建模研究”(项目编号: 17YJCZH262)和教育部人文社会科学规划基金项目“基于大数据的政府处置突发事件网络口碑动态演化跟踪与评估方法研究”(项目编号: 18YJAZH017)的研究成果之一
引用本文:   
曾庆田,戴明弟,李超,段华,赵中英. 轨迹数据融合用户表示方法的重要位置发现*[J]. 数据分析与知识发现, 2019, 3(6): 75-82.
Qingtian Zeng,Mingdi Dai,Chao Li,Hua Duan,Zhongying Zhao. Discovering Important Locations with User Representation and Trace Data. Data Analysis and Knowledge Discovery, DOI:10.11925/infotech.2096-3467.2018.1085.
链接本文:  
http://manu44.magtech.com.cn/Jwk_infotech_wk3/CN/10.11925/infotech.2096-3467.2018.1085
[1] 章志刚, 金澈清, 王晓玲, 等. 面向海量低质手机轨迹数据的重要位置发现[J]. 软件学报, 2016, 27(7): 1700-1714.
[1] (Zhang Zhigang, Jin Cheqing, Wang Xiaoling, et al.Discovering Important Locations from Massive and Low-Quality Cell Phone Trajectory Data[J]. Journal of Software, 2016, 27(7): 1700-1714.)
[2] Isaacman S, Becker R, Cáceres R, et al.Identifying Important Places in People’s Lives from Cellular Network Data[C]// Proceedings of the 2011 International Conference on Pervasive Computing. 2011: 133-151.
[3] 陈佳, 胡波, 左小清, 等. 利用手机定位数据的用户特征挖掘[J]. 武汉大学学报: 信息科学版, 2014, 39(6): 734-738, 744.
[3] (Chen Jia, Hu Bo, Zuo Xiaoqing, et al.Personal Profile Mining Based on Mobile Phone Location Data[J]. Geomatics & Information Science of Wuhan University, 2014, 39(6): 734-738, 744.)
[4] Bao J, Zheng Y, Mokbel M F.Location-Based and Preference-Aware Recommendation Using Sparse Geo-Social Networking Data[C]// Proceedings of the 20th International Conference on Advances in Geographic Information Systems. ACM, 2012: 199-208.
[5] 文长江. 基于社交数据用户行为的时空特性分析[D]. 成都: 电子科技大学, 2018.
[5] (Wen Changjiang.Analysis of Spatio-temporal Characteristics of User Behavior Based on Social Data[D]. Chengdu: University of Electronic Science and Technology of China, 2018.)
[6] Ashbrook D, Starner T.Using GPS to Learn Significant Locations and Predict Movement Across Multiple Users[J]. Personal & Ubiquitous Computing, 2003, 7(5): 275-286.
[7] 丰江帆, 熊雨虹. 一种基于个人位置信息的重要地点识别方法[J]. 小型微型计算机系统, 2013, 34(3): 503-507.
[7] (Feng Jiangfan, Xiong Yuhong.An Important Place Identification Algorithm Based on Personal GPS Location[J]. Journal of Chinese Computer Systems, 2013, 34(3): 503-507.)
[8] Cho E, Myers S A, Leskovec J.Friendship and Mobility: User Movement in Location-based Social Networks[C]// Proceedings of the 17th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2011: 1082-1090.
[9] Ma C L, Ma T, Shan H.A New Important-Place Identification Method[C]// Proceedings of the 2015 IEEE International Conference on Computer & Communications. IEEE, 2016: 151-155.
[10] Mikolov T, Sutskever I, Chen K, et al.Distributed Representations of Words and Phrases and Their Compositionality[C]// Proceedings of the 26th International Conference on Neural Information Processing Systems. 2013: 3111-3119.
[11] Kiros R, Zhu Y, Salakhutdinov R, et al.Skip-Thought Vectors[C]// Proceedings of the 28th International Conference on Neural Information Processing Systems. 2015: 3294-3302.
[12] Le Q, Mikolov T.Distributed Representations of Sentences and Documents[C]// Proceedings of the 31st International Conference on Machine Learning. 2014: 1188-1196.
[13] Liu Y, Liu Z, Chua T S, et al.Topical Word Embeddings[C]// Proceedings of the 29th AAAI Conference on Artificial Intelligence. 2015: 2418-2424.
[14] Grover A, Leskovec J.Node2Vec: Scalable Feature Learning for Networks[C]// Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. ACM, 2016: 855-864.
[15] Feng S, Cong G, An B, et al.POI2Vec: Geographical Latent Representation for Predicting Future Visitors[C]// Proceedings of the 31st AAAI Conference on Artificial Intelligence. 2017: 102-108.
[16] Sadilek A, Kautz H, Bigham J P.Finding Your Friends and Following Them to Where You are[C]// Proceedings of the 5th ACM International Conference on Web Search and Data Mining. 2012: 723-732.
[17] Freeman L C.Centrality in Social Networks Conceptual Clarification[J]. Social Networks, 1978, 1(3): 215-239.
[1] 曾庆田,胡晓慧,李超. 融合主题词嵌入和网络结构分析的主题关键词提取方法 *[J]. 数据分析与知识发现, 2019, 3(7): 52-60.
[2] 周成,魏红芹. 专利价值评估与分类研究*——基于自组织映射支持向量机[J]. 数据分析与知识发现, 2019, 3(5): 117-124.
[3] 张金柱,胡一鸣. 融合表示学习与机器学习的专利科学引文标题自动抽取研究*[J]. 数据分析与知识发现, 2019, 3(5): 68-76.
[4] 侯君,刘魁,李千目. 基于ESSVM的分类推荐*[J]. 数据分析与知识发现, 2018, 2(3): 9-21.
[5] 黄孝喜,李晗雨,王荣波,王小华,谌志群. 基于卷积神经网络与SVM分类器的隐喻识别*[J]. 数据分析与知识发现, 2018, 2(10): 77-83.
[6] 余传明,冯博琳,安璐. 基于深度表示学习的跨领域情感分析*[J]. 数据分析与知识发现, 2017, 1(7): 73-81.
[7] 曾金,陆伟,丁恒,陈海华. 基于图像语义的用户兴趣建模*[J]. 数据分析与知识发现, 2017, 1(4): 76-83.
[8] 田世海,吕德丽. 改进潜在语义分析和支持向量机算法用于突发安全事件舆情预警*[J]. 数据分析与知识发现, 2017, 1(2): 11-18.
[9] 杨爽,陈芬. 基于SVM多特征融合的微博情感多级分类研究*[J]. 数据分析与知识发现, 2017, 1(2): 73-79.
[10] 刘红光,马双刚,刘桂锋. 基于降噪自动编码器的中文新闻文本分类方法研究*[J]. 现代图书情报技术, 2016, 32(6): 12-19.
[11] 张晔,张晗,尹玢璨,赵玉虹. 基于电子病历利用支持向量机构建疾病预测模型*——以重度急性胰腺炎早期预警为例[J]. 现代图书情报技术, 2016, 32(2): 83-89.
[12] 张策,都云程,梁然. 采用URL特征的Hub网页识别方法研究*[J]. 现代图书情报技术, 2016, 32(1): 24-31.
[13] 何跃, 宋灵犀, 齐丽云. 负面事件中的品牌网络口碑溢出效应研究——以“圆通夺命快递”事件为例[J]. 现代图书情报技术, 2015, 31(10): 58-64.
[14] 胡吉明, 陈果. 超球支持向量机文本分类方法改进[J]. 现代图书情报技术, 2014, 30(9): 74-80.
[15] 刘勘, 朱怀萍, 刘秀芹. 基于支持向量机的网络伪舆情识别研究[J]. 现代图书情报技术, 2013, 29(11): 75-80.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
版权所有 © 2015 《数据分析与知识发现》编辑部
地址:北京市海淀区中关村北四环西路33号 邮编:100190
电话/传真:(010)82626611-6626,82624938
E-mail:jishu@mail.las.ac.cn