Research on Web Service Clustering Method Based on Word Embedding and Topic Model

  • Yanping Chen
  • Xin Wang
  • Hong XiaEmail author
  • Zhongmin Wang
  • Zhong Yv
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 1075)


Because of the short length of documents describing Web services on the Internet, the traditional modeling method is not ideal, which affects the clustering effect of Web services. To this end, we propose a word-embedded topic model, which can effectively solve the problem of data sparsity. A method based on embedded words and topic models. Firstly, Wikipedia is used as an external corpus to extend API service document, and LF-LDA model is used to model its topic distribution. The corpus data is extracted from Wikipedia by wikiextractor, and the corpus is trained with Word2vec tool. The data comes from its word vector model. Use the trained Wikipedia Word Vector Model to extend API service description documents. In the extended API service documents, LF-LDA topic modeling technology is used to mine the implicit topic information and determine the optimal number of topics, so as to accurately measure the semantic similarity between API service documents. Finally, K-means algorithm is used to cluster Web services, and the validity of this method is verified by the real data of API services on the basis of programmability. The experimental results show that this method has better accuracy, recall rate and F value than the traditional Web service clustering method based on topic model algorithm.


Web services clustering Topic model Word embedding 



This work is partly supported by the Project Supported by Science and Technology Project in Shaanxi Province of China (Program No.2019ZDLGY07-08) and the International Science and Technology Cooperation Program of the Science and Technology Department of Shaanxi Province, China (Grant No.2018KW-049), and the Innovation Program of Xi’an University of Posts and Telecommunications, China (Grant No.CXJJLY2018049).


  1. 1.
    Jianhua, L., Xiaolei, W.: A unified identity authentication service architecture for public networks. J. Xi’an Univ. Posts Telecommun. 19(2), 98–101 (2014)Google Scholar
  2. 2.
    Jianxun, L., Min, S., Dong, Z., et al.: Mashup tag recommendation method based on topic model. J. Comput. Sci. 40(2), 520–534 (2017)Google Scholar
  3. 3.
    Shi, M., Liu, J., Zhou, D., Cao, B.: Diploma 1. web services clustering method based on multiple relational theme model. J. Comput. Sci. 42(04), 820–836 (2019)Google Scholar
  4. 4.
    Zheng, L., Jian, W., Neng, Z., et al.: A topic-oriented domain service clustering method. Comput. Res. Dev. 51(2), 408–419 (2014)Google Scholar
  5. 5.
    Mnih, A., Hinton, G.: A scalable hierarchical distributed language model. In: International Conference on Neural Information Processing Systems. Curran Associates Inc., vol. 200, pp. 1081–1088 (2009)Google Scholar
  6. 6.
    Shi, M., Liu, J., Zhou, D., Tang, M., Cao, B.: WE-LDA: a word embeddings augmented LDA model for web services clustering. In: 2017 IEEE International Conference on Web Services (ICWS), pp. 9–16, Honolulu (2017)Google Scholar
  7. 7.
    Yu, Q., Wang, H., Chen, L.: Learning sparse functional factors for large-scale service clustering. In: 2015 IEEE International Conference on Web Services, pp. 201–208, New York (2015)Google Scholar
  8. 8.
    Srivastava, N., Salakhutdinov, R.R., Hinton, G.E.: Modeling documents with deep boltzmann machines. In: Proceedings of the 29th Conference Uncertainty in Artificial Intelligence, UAI 2013 (2013)Google Scholar
  9. 9.
    Cao, Z., Li, S., Liu, Y., Li, W., Ji, H.: A novel neural topic model and its supervised extension. In: AAAI, pp. 2210–2216 (2015)Google Scholar
  10. 10.
    Kenter, T., de Rijke, M.: Short text similarity with word embeddings. In: 2015 International, pp. 1411–1420. ACM (2015).
  11. 11.
    Kusner, M., Sun, Y., Kolkin, N.I., Weinberger, K.: From word embeddings to document distances. In: Proceedings of the 32nd International Conference on Machine Learning (ICML 2015), pp. 957–966 (2015)Google Scholar
  12. 12.
    Zheng, G., Callan, J.: Learning to reweight terms with distributed representations. In: Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval - SIGIR 2015, Santiago, Chile, 9–13 August 2015, pp. 575–584. ACM Press (2015)Google Scholar
  13. 13.
    Mikolov, T., Chen, K., Corrado, G.S., Dean, J.: Efficient estimation of word representations in vector space. In: 2013 Proceedings of Workshop at ICLR (2013)Google Scholar
  14. 14.
    Elgazzar, K., Hassan, A.E., Martin, P.: Clustering WSDL documents to bootstrap the discovery of web services, pp. 147–154 (2010).
  15. 15.
    Cao, B., et al.: Mashup service clustering based on an integration of service content and network via exploiting a two-level topic model. In: 2016 IEEE International Conference on Web Services (ICWS), pp. 212–219, San Francisco (2016)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  • Yanping Chen
    • 1
    • 2
  • Xin Wang
    • 1
  • Hong Xia
    • 1
    • 2
    Email author
  • Zhongmin Wang
    • 1
    • 2
  • Zhong Yv
    • 3
  1. 1.School of Computer Science and TechnologyXi’an University of Posts and TelecommunicationsXi’anChina
  2. 2.Shaanxi Key Laboratory of Network Data Analysis and Intelligent ProcessingXi’an University of Posts and TelecommunicationsXi’anChina
  3. 3.School of Communication and Information EngineeringXi’an University of Posts and TelecommunicationsXi’anChina

Personalised recommendations