Methods Inf Med 2021; 60(05/06): 133-146
DOI: 10.1055/s-0041-1736462
Original Article

Integrating Topic Model and Network Embedding for Thread Recommendation

Wei Wei
1   School of Statistics and Mathematics, Zhongnan University of Economics and Law, Wuhan, People's Republic of China
,
Rui Wang
2   Ctrip.com International Ltd, Shanghai, People's Republic of China
› Author Affiliations

Abstract

Objectives A thread is the most common information aggregation unit in a health forum, so effective thread recommendation is critical for improving the user experience in an online health community (OHC). This paper proposes an OHC thread recommendation method based on topic model and network embedding, which recommends threads to users by training a classifier and predicting user reply behavior.

Methods The proposed model uses the network structure to describe valid information in OHCs and treats a recommendation as the task of predicting links between users and threads in the network. Topic nodes are added to the information network to better represent the features of users and threads. The results of the latent Dirichlet allocation (LDA) model describe thread topics and user interests from the perspectives of consumer health vocabulary in OHCs and social support types. The large-scale information network embedding technology LINE is used to mine the node's contextual information from the network structure to obtain the low-dimensional vectors of nodes. We optimize the representation method and similarity calculation of network nodes and enrich the network structure information contained in the recommended features to improve the recommendation effect.

Results To verify the proposed model, we collected data from the diabetes forum “Sweet Home.” The experimental results show that the proposed model can effectively extract user interests in threads from the information network and optimize thread recommendation in OHCs.



Publication History

Received: 17 January 2021

Accepted: 29 August 2021

Article published online:
22 October 2021

© 2021. Thieme. All rights reserved.

Georg Thieme Verlag KG
Rüdigerstraße 14, 70469 Stuttgart, Germany

 
  • References

  • 1 Zhao DX. Review on domestic research status of online health community. Library and Information Service 2018; 62 (09) 134-142
  • 2 Li J, Huang W, Guo SL. A method of micro-blog content recommendation based on the fusion of similarity and trust degree. Library and Information Service. 2018; 62 (11) 112-119
  • 3 Du DF. Research on Representation Learning Method and Recommendation Technology for Social Network [PhD dissertation]. Hefei, China: University of Science and Technology of China; 2018
  • 4 Tang XN, Zhang M, Yang CC. Leveraging user interest to improve thread recommendation in online forum. Paper presented at: Proceedings of the 2013 International Conference on Social Intelligence and Technology, May 2013; IEEE: Washington, DC, USA; 2013: 11-19
  • 5 Gu P, Han YQ, Gao W, Xu GD, Wu J. Enhancing session-based social recommendation through item graph embedding and contextual friendship modeling. Neurocomputing 2021; 419: 190-202
  • 6 Xiong LR, Shen SM, Fan J. Matrix factorization recommendation by integrating community structure and social influence. J Chin Comput Syst 2019; 40 (11) 2411-2417
  • 7 Esteban A, Zafra A, Romero C. Helping university students to choose elective courses by using a hybrid multi-criteria recommendation system with genetic optimization. Knowl Base Syst 2020; 194: 251-262
  • 8 Li H, Liu JY, Shen W, Liu R, Jin SQ. Recommending knowledge for online health community users based on fuzzy cognitive map. Data Anal Knowl Discov 2020; 4: 55-67
  • 9 Yang CC, Jiang L. Enriching user experience in online health communities through thread recommendations and heterogeneous information network mining. IEEE Trans Comput Soc Syst 2018; 5 (04) 1049-1060
  • 10 Li MD, Gao WT, Chen Y. A topic and concept integrated model for thread recommendation in Online Health Communities. Paper presented at: Proceedings of the 29th ACM International Conference on Information & Knowledge Management. October 19–23, 2020; Ireland
  • 11 Tu CC, Yang W, Liu ZY. Network representation learning: an overview. Scientia Sinica (Informationis) 2017; 47 (08) 980-996
  • 12 Perozzi B, Al-Rfou R, Skiena S. Deepwalk: Online learning of social representations. Paper presented at: Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, New York, USA, August 2014; ACM: New York, USA; 2014: 701-710
  • 13 Grover A, Leskovec J. node2vec: Scalable feature learning for networks. Paper presented at: Proceedings of the 22nd ACM SIGKDD International Conference On Knowledge Discovery and Data Mining. San Francisco California, USA, August 2016; ACM: New York, USA; 2016: 855-864
  • 14 Tang J, Qu M, Wang M. et al. Line: Large-scale information network embedding. Paper presented at: Proceedings of the 24th International Conference on World Wide Web, Florence, Italy, May 2015; International World Wide Web Conferences Steering Committee: Republic and Canton of Geneva, Switzerland; 2015: 1067-1077
  • 15 Hou L, Kang H, Liu Y, Li L, Li J. Mining and standardizing Chinese consumer health terms. BMC Med Inform Decis Mak 2018; 18 (5, suppl 5): 120
  • 16 Sievert C, Shirley K. LDAvis: A method for visualizing and interpreting topics. Paper presented at: Proceedings of the Workshop on Interactive Language Learning, Visualization, and Interfaces. Baltimore, Maryland, June 27, ACL; 2014: 63-70
  • 17 Stanley W, Katherine F. Social Network Analysis: Methods and Applications. Beijing: China Renmin University Press; 2012: 123-139
  • 18 El-Sappagh S, Kwak D, Ali F, Kwak KS. DMTO: a realistic ontology for standard diabetes mellitus treatment. J Biomed Semantics 2018; 9 (01) 8
  • 19 Zhang B, Ma FC. A review on link prediction of scientific knowledge network. J Lib Sci Chin 2015; 41 (03) 99-113
  • 20 Wang R. Thread recommendation in Online Health Community based on topic model and network embedding [Master dissertation]. Wuhan, China: Wuhan University; 2019