计算机科学 ›› 2016, Vol. 43 ›› Issue (1): 251-254.doi: 10.11896/j.issn.1002-137X.2016.01.054

• 人工智能 • 上一篇    下一篇

基于时空数据的用户社交联系强度研究

陈元娟,严建峰,刘晓升,杨璐   

  1. 苏州大学计算机科学与技术学院 苏州215006,苏州大学计算机科学与技术学院 苏州215006,苏州大学计算机科学与技术学院 苏州215006,苏州大学计算机科学与技术学院 苏州215006
  • 出版日期:2018-12-01 发布日期:2018-12-01
  • 基金资助:
    本文受国家自然科学基金(61373092,61033013,61272449,61202029),江苏省教育厅重大项目(12KJA520004),江苏省科技支撑计划重点项目(BE2014005),广东省重点实验室开放课题(SZU-GDPHPCL-2012-09)资助

Social Strength Learning between Users Based on Spatiotemporal Data

CHEN Yuan-juan, YAN Jian-feng, LIU Xiao-sheng and YANG Lu   

  • Online:2018-12-01 Published:2018-12-01

摘要: word2vec是Google推出的一款将词表征为实数值的高效开源工具。采用该工具将时空数据中的每位用户表征为一个实数值向量并预测用户间社交联系的强度。提出了在word2vec学习过程中动态调整学习率的算法——Location-weight算法,根据不同位置的不同用户数目在学习过程中加入位置权重,并探索其对用户社交联系强度预测的影响。实验结果表明,加入位置权重的学习算法提高了用户社交联系强度预测的准确性。

关键词: word2vec,位置权重,用户社交联系强度

Abstract: Word2vec is a high-efficiency open-source tool issued by Google,which represents a word with a float vector.We used this tool to process spatiotemporal data.Each user is represented with a float vector to predict social strength among users.To predict social strength among users more precisely,this paper proposed a location-weight algorithm that dynamically adjusts the learning rate in the process of learning with word2vec.According to the number of different users at different locations,we added location weight to the algorithm in the process of learning.Meanwhile,we explored the effect of location-weight on prediction of social strength among users.Experimental results validate perfor-mance of the proposed algorithm.

Key words: word2vec,Location weight,Social strength

[1] Pham H,Shahabi C,Liu Y.Ebm:an entropy-based model to infer social strength from spatiotemporal data[C]∥Proceedings of the 2013 International Conference on Management of Data.ACM,2013:265-276
[2] Gonzalez M C,Hidalgo C A,Barabasi A L.Understanding individual human mobility patterns[J].Nature,2008,453(7196):779-782
[3] Cheng Z,Caverlee J,Lee K,et al.Exploring Millions of Foot-prints in Location Sharing Services[C]∥ICWSM.2011:81-88
[4] Lindqvist J,Cranshaw J,Wiese J,et al.I’m the mayor of my house:examining why people use foursquare-a social-driven location sharing application[C]∥Proceedings of the SIGCHI Conference on Human Factors in Computing Systems.ACM,2011:2409-2418
[5] Kostakos V,Venkatanathan J,Reynolds B,et al.Who’s your best friend-targeted privacy attacks In location-sharing social networks[C]∥Proceedings of the 13th International Conference on Ubiquitous Computing.ACM,2011:177-186
[6] Crandall D J,Backstrom L,Cosley D,et al.Inferring social ties from geographic coincidences[J].Proceedings of the National Academy of Sciences,2010,107(52):22436-22441
[7] Cranshaw J,Toch E,Hong J,et al.Bridging the gap between physical location and online social networks[C]∥Proceedings of the 12th ACM International Conference on Ubiquitous Computing.ACM,2010:119-128
[8] Li Q,Zheng Y,Xie X,et al.Mining user similarity based on location history[C]∥Proceedings of the 16th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems.ACM,2008:34
[9] Mikolov T,Chen K,Corrado G,et al.Efficient estimation ofword representations in vector space[J].arXiv preprint arXiv:1301.3781,2013
[10] Li Min,Wang Xiao-cong,Zhang Jun,et al.Study on Check-in and Related Behaviors of Location-based Social Network Users[J].Computer Science,2013,0(10):72-76(in Chinese)李敏,王晓聪,张军,等.基于位置的社交网络用户签到及相关行为研究[J].计算机科学,2013,0(10):72-76
[11] Mikolov T,Yih W,Zweig G.Linguistic Regularities in Continuous Space Word Representations[C]∥HLT-NAACL.2013:746-751
[12] Mikolov T,Kombrink S,Burget L,et al.Extensions of recurrent neural network language model[C]∥2011 IEEE International Conference on Acoustics,Speech and Signal Processing (ICASSP).IEEE,2011:5528-5531

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!