Neural Network Based Popularity Prediction by Linking Online Content with Knowledge Bases

  • Wayne Xin ZhaoEmail author
  • Hongjian Dou
  • Yuanpei Zhao
  • Daxiang Dong
  • Ji-Rong Wen
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11440)


Predicting the popularity of online items has been an important task to understand and model online popularity dynamics. Feature-based methods are one of the mainstream approaches to tackle this task. However, most of the existing studies focus on some specific kind of auxiliary data, which is usually platform- or domain- dependent. In existing works, the incorporation of auxiliary data has put limits on the applicability of the prediction model itself. These methods may not be applicable to multiple domains or platforms. To address these issues, we propose to link online items with existing knowledge base (KB) entities, and leverage KB information as the context for improving popularity prediction. We represent the KB entity by a latent vector, encoding the related KB information in a compact way. We further propose a novel prediction model based on LSTM networks, adaptively incorporating KB embedding of the target entity and popularity dynamics from items with similar entity information. Extensive experiments on three real-world datasets demonstrate the effectiveness of the proposed model.


Deep learning Popularity prediction Knowledge base 



This work was partially supported by National Natural Science Foundation of China under the grant numbers 61872369 and 61832017, and the Science and Technology Project of Beijing (Z181100003518001).


  1. 1.
    Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. Computer Science (2014)Google Scholar
  2. 2.
    Bordes, A., Usunier, N., García-Durán, A., Weston, J., Yakhnenko, O.: Translating embeddings for modeling multi-relational data. In: NIPS, pp. 2787–2795 (2013)Google Scholar
  3. 3.
    Cao, Q., Shen, H., Cen, K., Ouyang, W., Cheng, X.: Deephawkes: bridging the gap between prediction and understanding of information cascades. In: CIKM, pp. 1149–1158 (2017)Google Scholar
  4. 4.
    Chang, B., Zhu, H., Ge, Y., Chen, E., Xiong, H., Tan, C.: Predicting the popularity of online serials with autoregressive models. In: CIKM, pp. 1339–1348 (2014)Google Scholar
  5. 5.
    Cheng, J., Adamic, L., Dow, P.A., Kleinberg, J.M., Leskovec, J.: Can cascades be predicted? In: WWW, pp. 925–936 (2014)Google Scholar
  6. 6.
    Ding, X., Zhang, Y., Liu, T., Duan, J.: Deep learning for event-driven stock prediction. In: IJCAI, pp. 2327–2333 (2015)Google Scholar
  7. 7.
    Google: Freebase data dumps (2016).
  8. 8.
    Grover, A., Kapoor, A., Horvitz, E.: A deep hybrid model for weather forecasting. In: SIGKDD, pp. 379–386 (2015)Google Scholar
  9. 9.
    Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)CrossRefGoogle Scholar
  10. 10.
    Huang, J., Zhao, W.X., Dou, H., Wen, J.R., Chang, E.Y.: Improving sequential recommendation with knowledge-enhanced memory networks. In: The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval, pp. 505–514. ACM (2018)Google Scholar
  11. 11.
    Imamori, D., Tajima, K.: Predicting popularity of twitter accounts through the discovery of link-propagating early adopters. In: CIKM, pp. 639–648 (2016)Google Scholar
  12. 12.
    Jia, X., et al.: Incremental dual-memory LSTM in land cover prediction. In: SIGKDD (2017)Google Scholar
  13. 13.
    Khosla, A., Sarma, A.D., Hamid, R.: What makes an image popular? In: WWW, pp. 867–876 (2014)Google Scholar
  14. 14.
    Li, C., Ma, J., Guo, X., Mei, Q.: Deepcas: an end-to-end predictor of information cascades. In: WWW, pp. 577–586 (2017)Google Scholar
  15. 15.
    Ma, C., Yan, Z., Chen, C.W.: LARM: a lifetime aware regression model for predicting youtube video popularity. In: CIKM, pp. 467–476 (2017)Google Scholar
  16. 16.
    Pinto, H., Almeida, J.M.: Using early view patterns to predict the popularity of youtube videos. In: WSDM, pp. 365–374 (2013)Google Scholar
  17. 17.
    Proskurnia, J., Grabowicz, P.A., Kobayashi, R., Castillo, C., Cudré-Mauroux, P., Aberer, K.: Predicting the success of online petitions leveraging multidimensional time-series. In: WWW, pp. 755–764 (2017)Google Scholar
  18. 18.
    Qin, Y., Song, D., Chen, H., Cheng, W., Jiang, G., Cottrell, G.: A dual-stage attention-based recurrent neural network for time series prediction. In: IJCAI, pp. 2627–2633 (2017)Google Scholar
  19. 19.
    Roy, S.D., Mei, T., Zeng, W., Li, S.: Towards cross-domain learning for social video popularity prediction. IEEE Trans. Multimed. 15(6), 1255–1267 (2013)CrossRefGoogle Scholar
  20. 20.
    Shen, H.W., Wang, D., Song, C., Barabsi, A.: Modeling and predicting popularity dynamics via reinforced poisson processes. In: AAAI, pp. 291–297 (2014)Google Scholar
  21. 21.
    Shi, X., et al.: Deep learning for precipitation nowcasting: a benchmark and a new model (2017)Google Scholar
  22. 22.
    Suchanek, F.M., Kasneci, G., Weikum, G.: YAGO: a core of semantic knowledge. In: WWW, pp. 697–706 (2007)Google Scholar
  23. 23.
    Szabo, G., Huberman, B.A.: Predicting the popularity of online content. Commun. ACM 53(8), 80–88 (2008)CrossRefGoogle Scholar
  24. 24.
    Tatar, A., de Amorim, M.D., Fdida, S., Antoniadis, P.: A survey on predicting the popularity of web content. J. Internet Serv. Appl. 5(1), 8:1–8:20 (2014)CrossRefGoogle Scholar
  25. 25.
    Wang, Y., Liu, S., Shen, H., Gao, J., Cheng, X.: Marked temporal dynamics modeling based on recurrent neural network. In: Kim, J., Shim, K., Cao, L., Lee, J.-G., Lin, X., Moon, Y.-S. (eds.) PAKDD 2017. LNCS (LNAI), vol. 10234, pp. 786–798. Springer, Cham (2017). Scholar
  26. 26.
    Wu, B., Cheng, W., Zhang, Y., Huang, Q., Li, J., Mei, T.: Sequential prediction of social media popularity with deep temporal context networks. In: IJCAI, pp. 3062–3068 (2017)Google Scholar
  27. 27.
    Wu, B., Mei, T., Cheng, W.H., Zhang, Y.: Unfolding temporal dynamics: predicting social media popularity using multi-scale temporal decomposition. In: AAAI, pp. 272–278 (2016)Google Scholar
  28. 28.
    Zhang, L., Aggarwal, C., Qi, G.J.: Stock price prediction via discovering multi-frequency trading patterns. In: SIGKDD (2017)Google Scholar
  29. 29.
    Zhao, W.X., He, G., Dou, H., Huang, J., Ouyang, S., Wen, J.R.: Kb4rec: a dataset for linking knowledge bases with recommender systems. arXiv preprint arXiv:1807.11141 (2018)

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Wayne Xin Zhao
    • 1
    Email author
  • Hongjian Dou
    • 1
  • Yuanpei Zhao
    • 1
  • Daxiang Dong
    • 2
  • Ji-Rong Wen
    • 1
  1. 1.School of InformationRenmin University of ChinaBeijingChina
  2. 2.Baidu Inc.BeijingChina

Personalised recommendations