Skip to main content
SpringerLink
Log in

Heterogeneous information network embedding for user behavior analysis on social media

  • Original Article
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

User behavior prediction with low-dimensional vectors generated by user network embedding models has been verified to be efficient and reliable in real applications. However, existing graph representation learning methods mainly focus on homogeneous and static graphs and cannot well represent the real-world social networks that are heterogeneous and keep evolving. To address this challenge, we propose a dynamic heterogeneous user behavior analysis network (DHBN) model, which applies graph network embedding to fuse multi-networks information by considering their heterogeneity and evolutionary patterns over dynamic networks. In particular, by separately performing user social relationship embedding, node attribute embedding and user behavior embedding, the proposed scheme learns the highly nonlinear representations of network nodes; and then we explore recurrent neural networks based on attention mechanism to capture the networks' dynamic evolution. Our proposed method has been examined on two real-world datasets, and five state-of-the-art schemes are compared to the proposed scheme for link prediction quality and node recommendation. Especially, for dynamic user behavior link prediction task on Weibo-UBA dataset, DHBN model achieves AUROC of 77.3% and AUPOC of 71.2%. In terms of AUROC, DHBN is at least 5% better than other models, the other experimental results also demonstrate that the DHBN model has significant advantages over other comparison models. This work can provide guidance on the future user behavior prediction studies.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8

Similar content being viewed by others

Notes

  1. https://tianchi.aliyun.com/competition/entrance/231719/introduction.

References

  1. Silahtaroglu G, Donertasli H (2015) Analysis and prediction of Ε-customers' behavior by mining clickstream data. In: IEEE International Conference on Big Data. IEEE, pp 1466–1472

  2. Liu XM, Li J (2016) Using support vector machine for online purchase predication. In: International Conference on Logistics, Informatics and Service Sciences (LISS), IEEE, pp 1–6

  3. Yuan WW, He KY, Han GJ et al (2019) User behavior prediction via heterogeneous information preserving network embedding. Futur Gener Comput Syst 92:52–58

    Article  Google Scholar 

  4. Yin Y, Ji L, Zhang J et al (2019) Dhne: network representation learning method for dynamic heterogeneous networks. IEEE Access 7:134782–134792

    Article  Google Scholar 

  5. Dong Y, Chawla NV, Swami, A (2017) Metapath2Vec: Scalable representation learning for heterogeneous networks. In: Proceedings of the 23rd ACM SIGKDD international conference on knowledge discovery and data mining, pp 135–144

  6. Cen Y, Zou X, Zhang J (2019) Representation learning for attributed multiplex heterogeneous network. In: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp 1358–1368

  7. Du L, Wang Y, Song G, et al (2018) Dynamic network embedding: An extended approach for skip-gram based network embedding. In: IJCAI, pp 2086–2092

  8. Trivedi R, Farajtabar M, Biswal P, et al (2019) Dyrep: Learning representations over dynamic graphs. In: International Conference on Learning Representations, pp 1–25

  9. Grover A, Leskovec J (2016) Node2Vec: Scalable feature learning for networks. In: Proceedings of the 22nd ACM SIGKDD international conference on Knowledge discovery and data mining, pp 855–864

  10. Tang J, Qu M, Wang M, et al (2015) Line: Large-scale information network embedding. In: Proceedings of the 24th international conference on world wide web, pp 1067–1077

  11. Zhang H, Qiu L, Yi L (2018) Scalable multiplex network embedding. In: IJCAI, pp 3082–3088

  12. Goyal P, Chhetri SR, Canedo A (2020) Dyngraph2vec: capturing network dynamics using dynamic graph representation learning. Knowl-Based Syst 187:104816–1–104819

    Article  Google Scholar 

  13. Zhang Z, Cui P, Pei J, et al (2017) Timers: error-bounded svd restart on dynamic networks. arXiv preprint arXiv 1711:09541

  14. Sankar A, Wu Y, Gou L, et al. (2019) Dynamic graph representation learning via self-attention networks. In: Worshop on Representation Learning on Graphs and Manifolds in ICLR.

  15. Li B, Wang G, Cheng Y et al (2020) An event recommendation model using ELM in event-based social network. Neural Comput Appl 32(18):14375–14384

    Article  Google Scholar 

  16. Singer U, Guy I, Radinsky K (2019) Node embedding over temporal graphs. In: IJCAI, pp 4605–4612

  17. Pareja A, Domeniconi G, Chen J, et al. (2020) EvolveGCN: Evolving graph convolutional networks for dynamic graphs. In: AAAI, pp 5363–5370

  18. Chen J, Zhang J, Xu X et al (2019) E-lstm-d: a deep learning framework for dynamic network link prediction. IEEE Trans Syst Man Cybern Syst 51:1–14

    Article  Google Scholar 

  19. Hamilton WL, Ying R, Leskovec J (2017) Representation learning on graphs: methods and applications. IEEE Data Eng Bull 40(3):52–74

    Google Scholar 

  20. Goyal P, Ferrara E (2018) Graph embedding techniques, applications, and performance: a survey. Knowl-Based Syst 151:78–94

    Article  Google Scholar 

  21. Wang D, Chen Y (2019) A neural computing approach to the construction of information credibility assessments for online social networks. Neural Comput Appl 31(1):259–275

    Article  MathSciNet  Google Scholar 

  22. Sakar CO, Polat SO, Katircioglu M et al (2019) Real-time prediction of online shoppers’ purchasing intention using multilayer perceptron and LSTM recurrent neural networks. Neural Comput Appl 31(10):6893–6908

    Article  Google Scholar 

  23. Yuan WW, He KY, Guan DH et al (2019) Graph kernel based link prediction for signed social networks. Inf Fusion 46:1–10

    Article  Google Scholar 

  24. Iglesias JA, Angelov P, Ledezma A et al (2012) Creating evolving user behavior profiles automatically. IEEE Trans Knowl Data Eng 24(5):854–867

    Article  Google Scholar 

  25. Al-Radaideh QA, Al-Zoubi MM. (2018) A Data Mining based Model for Detection of Fraudulent Behaviour in Water Consumption. In: Proceedings of the 9th International Conference on Information and Communication Systems (ICICS). pp 48–54

  26. Peng F, Lin HF, Yang L et al (2018) Multi-view ensemble framework for constructing user profile. Comput Sci 45(1):179–182

    Google Scholar 

  27. Jamali M and Ester M. (2010) A matrix factorization technique with trust propagation for recommendation in social networks. In Proceedings of the 4th ACM Conference on Recommender Systems. ACM, pp 135–142.

  28. Jiang M, Cui P, Wang F et al (2014) Scalable recommendation with social contextual information. IEEE Trans Knowl Data Eng 26(11):2789–2802

    Article  Google Scholar 

  29. Wu L, Sun PJ, Hong RC et al (2018) Collaborative neural social recommendation. IEEE Trans Syst Man Cybern Syst 51:1–13

    Google Scholar 

  30. Cui P, Wang X, Pei J (2018) A survey on network embedding. IEEE Trans Knowl Data Eng 31:833–852

    Article  Google Scholar 

  31. Cao XZ, Chen HK, Wang XJ, et al (2018) Neural link prediction over aligned networks. In: Proceedings of the 32nd AAAI Conference on Artificial Intelligence. pp 249–256.

  32. Liao LZ, He XG, Zhang HW et al (2018) Attributed social network embedding. IEEE Trans Knowl Data Eng 30(12):2257–2270

    Article  Google Scholar 

  33. Chang Sy, Han W, Tang JL, et al (2015) Heterogeneous network embedding via deep architectures. In: Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 119–128.

  34. Wang J (2012) Geometric structure of high-dimensional data and dimensionality reduction. Springer, Heidelberg, pp 203–220

    Book  Google Scholar 

  35. Belkin M, Niyogi P (2002) Laplacian eigenmaps and spectral techniques for embedding and clustering. Adv Neural Inf Process Syst 14(6):585–591

    Google Scholar 

  36. Mikolov T, Chen K, Corrado G, Dean J. (2013) Efficient estimation of word representations in vector space. In: Proceedings of Workshop at International Conference on Learning Representations (ICLR).

  37. Perozzi B, Al-Rfou R, Skiena S (2014) Deep walk: Online learning of social representation. In: Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp 701–710

  38. Cao SS, Lu W, Xu QK (2015) Grarep: Learning graph representations with global structural information. In: Proceedings of the 24th ACM International on Conference on Information and Knowledge Management, pp 891–900

  39. Wang DX, Cui P, Zhu WW (2016) Structural deep network embedding. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp 1225–1234

  40. Veličković P, Cucurull G, Casanova A, et al. (2017) Graph attention networks. arXiv preprint arXiv 1710:10903

  41. Shi C, Li YT, Zhang JW et al (2017) A survey of heterogeneous information network analysis. IEEE Trans Knowl Data Eng 29:17–37

    Article  Google Scholar 

  42. Wang X, Ji H, Shi C, et al (2019) Heterogeneous graph attention network. In: The World Wide Web Conference, pp 2022–2032

  43. Hamilton W, Ying Z, Leskovec J (2017) Inductive representation learning on large graphs. Adv Neural Inf Process Syst 1024–1034

  44. Chen J, Xu X, Wu Y et al. (2018) Gc-lstm: graph convolution embedded lstm for dynamic link prediction. arXiv preprint arXiv 1812:04206

  45. Yang L, Xiao Z, Jiang W, et al (2020) Dynamic heterogeneous graph embedding using hierarchical attentions. In: European Conference on Information Retrieval. Springer, Cham, pp 425–432

  46. Zhang H, Sun Y, Zhao M et al (2020) Bridging user interest to item content for recommender systems: an optimization model. IEEE Trans Cybern 50(10):4268–4280

    Article  Google Scholar 

  47. He C, Xie T, Rong Y, et al. (2019) Bipartite graph neural networks for efficient node representation learning. The Association for the Advancement of Artificial Intelligence.

  48. Jin Z, Zhao X, Liu Y (2021) Heterogeneous graph network embedding for sentiment analysis on social media. Cogn Comput 13(1):81–95

    Article  Google Scholar 

  49. Chung J, Gulcehre C, Cho K, et al. (2014) Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv 1412:3555

Download references

Acknowledgements

This study was funded by the National Natural Science Foundation of China (No. 71502125, 52171337).

Author information

Authors and Affiliations

  1. School of Electrical and Information Engineering, Tianjin University, Tianjin, China

    Xiaofang Zhao, Zhigang Jin & Yi Hu

  2. Dept. of Computer Science and Engineering, Santa Clara University, Santa Clara, USA

    Yuhong Liu

Authors
  1. Xiaofang Zhao
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Zhigang Jin
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yuhong Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Yi Hu
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Zhigang Jin or Yuhong Liu.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Zhao, X., Jin, Z., Liu, Y. et al. Heterogeneous information network embedding for user behavior analysis on social media. Neural Comput & Applic 34, 5683–5699 (2022). https://doi.org/10.1007/s00521-021-06706-z

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-021-06706-z

Keywords

Search

Navigation