Wuhan University Journal of Natural Sciences

, Volume 23, Issue 1, pp 9–16 | Cite as

A framework for personalized adaptive user interest prediction based on topic model and forgetting mechanism

  • Sisi Gui
  • Wei Lu
  • Pengcheng Zhou
  • Zhan Zheng
Complex Science Management


User interest is not static and changes dynamically. In the scenario of a search engine, this paper presents a personalized adaptive user interest prediction framework. It represents user interest as a topic distribution, captures every change of user interest in the history, and uses the changes to predict future individual user interest dynamically. More specifically, it first uses a personalized user interest representation model to infer user interest from queries in the user’s history data using a topic model; then it presents a personalized user interest prediction model to capture the dynamic changes of user interest and to predict future user interest by leveraging the query submission time in the history data. Compared with the Interest Degree Multi-Stage Quantization Model, experiment results on an AOL Search Query Log query log show that our framework is more stable and effective in user interest prediction.


user interest user interest presentation user interest prediction topic model forgetting mechanism 

CLC number

TP 393 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    Carroll J. Interfacing Thought: Cognitive Aspects of Human-Computer Interaction [M]. Cambridge: MIT Press, 1987.Google Scholar
  2. [2]
    Claypool M, Brown D, Le P, et al. Inferring user Interest[J]. IEEE Internet Computing, 2001, 5(6): 32–39.CrossRefGoogle Scholar
  3. [3]
    Qiu F, Cho J. Automatic identification of user interest for personalized search[C] // Proceedings of the 15th International Conference on World Wide Web (WWW’ 06). New York: ACM, 2006: 727–736.CrossRefGoogle Scholar
  4. [4]
    Yin H, Cui B, Chen L, et al. Dynamic user modeling in social media systems[J]. ACM Transactions on Information Systems, 2015, 33(3): 10–44.CrossRefGoogle Scholar
  5. [5]
    Li M, Sagl G, Mburu L, et al. A Contextualized and personalized model to predict user interest using location-based social networks[J]. Computers, Environment and Urban Systems, 2016, 58: 97–106.CrossRefGoogle Scholar
  6. [6]
    Wu L, Wang D, Guo C, et al. User profiling by combining topic modeling and pointwise mutual information (TM-PMI) [C] // Proceedings of the 22th MultiMedia Modeling (MMM 2016), 2016:152–161.Google Scholar
  7. [7]
    Ahmed A, Low Y, Aly M, et al. Scalable distributed inference of dynamic user interests for behavioral targeting[C] // Proceedings of the 17th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (SIGIR’ 11). New York: ACM, 2011: 114–122.Google Scholar
  8. [8]
    Song T, Zhao H, Zheng S, et al. Construction of user interest model based on queries and concept[J]. Journal of Jilin University (Information Science Edition), 2015, 33(3): 310–314(Ch).Google Scholar
  9. [9]
    Veningston K, Shanmugalakshmi R. Combining user interested topic and document topic for personalized inform-ation retrieval [C] // Proceedings of the 3rd International Conference on Big Data Analytics (BDA 2014). 2014: 60–79.Google Scholar
  10. [10]
    Jiang J, Cheng P. Classifying user search intents for query auto-completion [C] // Proceedings of the 2016 ACM International Conference on the Theory of Information Retrieval (ICTIR’ 16). New York: ACM, 2016: 49–58.Google Scholar
  11. [11]
    Burges C. From RankNet to LambdaRank to LambdaMART: An overview[EB/OL]. [2017-10-31]. edu/viewdoc/download?doi= e=pdf.Google Scholar
  12. [12]
    Sadikov E, Madhavan J, Wang L, et al. Clustering query refinements by user intent[C]// Proceedings of the 19th International Conference on World Wide Web (WWW’10). New York: ACM, 2010: 841–850.Google Scholar
  13. [13]
    Duan H, Kiciman E, Zhai C. Click Patterns: An empirical representation of complex query intents[C] // Proceedings of the 21th ACM International Conference on Information and Knowledge Management (CIKM’ 12). New York: ACM, 2012: 1035–1044.Google Scholar
  14. [14]
    Ren X, Wang Y, Yu X, et al. Heterogeneous graph-based intent learning with queries, web pages and Wikipedia concepts[C] // Proceedings of the 7th ACM International Conference on Web Search and Data Mining (WSDM’ 14). New York: ACM, 2014: 23–32.CrossRefGoogle Scholar
  15. [15]
    Lee T, Park Y, Park Y. A time-based approach to effective recommender systems using implicit feedback [J]. Expert Systems with Applications, 2008, 34(4): 3055–3062.CrossRefGoogle Scholar
  16. [16]
    Lee T, Park Y, Park Y. An empirical study on effectiveness of temporal information as implicit ratings [J]. Expert Systems with Applications, 2009, 36(2): 1315–1321.CrossRefGoogle Scholar
  17. [17]
    Pham X, Jung J, Nam B, et al. User timeline and interestbased collaborative filtering on social network [J]. Context-Aware Systems and Applications. 2015, 165: 132–140.CrossRefGoogle Scholar
  18. [18]
    Maloof M, Michalski R. Selecting examples for partial memory learning[J]. Machine Learning, 2000, 41(1): 27–52.CrossRefGoogle Scholar
  19. [19]
    Zhang Y, Liu Y. A collaborative filtering algorithm based on time period partition[C]// Proceedings of the 3rd International Symposium on Intelligent Information Technology and Security Informatics (IITSI 2010). Piscataway: IEEE Computer Society, 2010: 777–780.Google Scholar
  20. [20]
    Chen Z, Jiang Y, Zhao Y. A collaborative filtering recommendation algorithm based on user interest change and trust evaluation [J]. International Journal of Digital Content Technology and its Applications, 2010, 4(9): 106–113.CrossRefGoogle Scholar
  21. [21]
    Wu Y, Wang Y, Tang Z. A collaborative filtering recommendation algorithm based on interest forgetting curve [J]. International Journal of Advancements in Computing Technology, 2012, 4(10): 148–157.CrossRefGoogle Scholar
  22. [22]
    Yu H, Cui R, Dong Q. Micro-blog user interest model based on forgetting curve [J]. Computer Engineering and Design, 2014, 35(10): 3367–3372(Ch).Google Scholar
  23. [23]
    Ding W, Chen C. Dynamic topic detection and tracking: A comparison of HDP, C-word, and co-citation methods [J]. Journal of the Association for Information Science and Technology, 2014, 65(10): 2084–2097.CrossRefGoogle Scholar
  24. [24]
    Ding Y, Li X. Time weight collaborative filtering[C] // Proceedings of the 14th ACM International Conference on Information and Knowledge Management (CIKM’ 05). New York: ACM, 2005: 485–492.Google Scholar
  25. [25]
    Jeong D, Song M. Time gap analysis by the topic modelbased temporal technique [J]. Journal of Informetrics, 2014, 8(3): 776–790.CrossRefGoogle Scholar
  26. [26]
    Wu D, Zhao D, Zhang X. An adaptive user profile based on memory model [C] // Proceedings of the 9th International Conference on Web-Age Information Management (WAIM’08). Piscataway: IEEE Computer Society, 2008: 461–468.Google Scholar

Copyright information

© Wuhan University and Springer-Verlag GmbH Germany, part of Springer Nature 2018

Authors and Affiliations

  1. 1.School of Information ManagementWuhan UniversityHubeiChina
  2. 2.School of Media and CommunicationWuhan Textile UniversityHubeiChina

Personalised recommendations