JACIII Vol.24 No.3 pp. 316-325
doi: 10.20965/jaciii.2020.p0316


Estimation of Search Intents from Query to Context Search Engine

Yasufumi Takama*, Takuya Tezuka*, Hiroki Shibata*, and Lieu-Hen Chen**

*Graduate School of Systems Design, Tokyo Metropolitan University
6-6 Asahigaoka, Hino, Tokyo 191-0065, Japan

**College of Science and Technology, National Chi Nan University
No.1 University Road, Puli, Nantou 54561, Taiwan

September 28, 2019
February 18, 2020
May 20, 2020
search engine, time series data, search intent, learning to rank

This paper estimates users’ search intents when using the context search engine (CSE) by analyzing submitted queries. Recently, due to the increase in the amount of information on the Web and the diversification of information needs, the gap between user’s information needs and a basic search function provided by existing web search engines becomes larger. As a solution to this problem, the CSE that limits its tasks to answer questions about temporal trends has been proposed. It provides three primitive search functions, which users can use in accordance with their purposes. Furthermore, if the system can estimate users’ search intents, it can provide more user-friendly services that contribute the improvement of search efficiency. Aiming at estimating users’ search intents only from submitted queries, this paper analyzes the characteristics of queries in terms of typical search intents when using CSE, and defines classification rules. To show the potential use of the estimated search intents, this paper introduces a learning to rank into CSE. Experimental results show that MAP (mean average precision) is improved by learning rank models separately for different search intents.

Screenshot of Context Search Engine (CSE) result page

Screenshot of Context Search Engine (CSE) result page

Cite this article as:
Y. Takama, T. Tezuka, H. Shibata, and L. Chen, “Estimation of Search Intents from Query to Context Search Engine,” J. Adv. Comput. Intell. Intell. Inform., Vol.24 No.3, pp. 316-325, 2020.
Data files:
  1. [1] S. Kori, Y. Zhu, K. Yamaguchi, S. Takiguchi, and Y. Takama, “Analysis of User’s Behaviour Based on Search Intentions for Information Retrieval Using Search Engines,” Proc. of 2015 Conf. on Technologies and Applications of Artificial Intelligence (TAAI2015), pp. 64-70, 2015.
  2. [2] Y. Takama, Y. Zhu, S. Kori, K. Yamaguchi, L.-H. Chen, and H. Ishikawa, “Design of Context Search Engine Based on Analysis of User’s Search Intentions,” J. Adv. Comput. Intell. Intell. Inform., Vol.20, No.6, pp. 910-918, 2016.
  3. [3] Y. Zhu, Y. Takama, Y. Kato, S. Kori, and H. Ishikawa, “Introduction of Search Engine Focusing on Trend-Related Queries to Market of Data,” Proc. of 14th IEEE Int. Conf. on Data Mining Workshop (ICDMW 2014), pp. 511-516, 2014.
  4. [4] Z. Cao, T. Qin, T.-Y. Liu, M.-F. Tsai, and H. Li, “Learning to Rank: From Pairwise Approach to Listwise Approach,” Proc. of the 24th Int. Conf. on Machine Learning (ICML’07), pp. 129-136, 2007.
  5. [5] J. L. Elsas, V. R. Carvalho, and J. G. Carbonell, “Fast Learning of Document Ranking Functions with the Committee Perceptron,” Proc. of the 2008 Int. Conf. on Web Search and Data Mining (WSDM’08), pp. 55-64, 2008.
  6. [6] T. Joachims, “Optimizing Search Engines Using Clickthrough Data,” Proc. of the 8th ACM SIGKDD Int. Conf. on Knowledge Discovery and Data Mining (KDD’02), pp. 133-142, 2002.
  7. [7] D. Metzler and W. B. Croft, “Linear Feature-Based Models for Information Retrieval,” Information Retrieval, Vol.10, No.3, pp. 257-274, 2007.
  8. [8] J. Xu and H. Li, “AdaRank: A Boosting Algorithm for Information Retrieval,” Proc. of the 30th Annual Int. ACM SIGIR Conf. on Research and Development in Information Retrieval (SIGIR 2007), pp. 391-398, 2007.
  9. [9] A. Broder, “A Taxonomy of Web Search,” ACM SIGIR Forum, Vol.36, No.2, pp. 3-10, 2002.
  10. [10] E. Agichtein, R. W. White, S. T. Dumais, and P. N. Bennett, “Search, Interrupted: Understanding and Predicting Search Task Continuation,” Proc. of the 35th Int. ACM SIGIR Conf. on Research and Development in Information Retrieval (SIGIR’12), pp. 315-324, 2012.
  11. [11] M. van der Heijden, M. Hinne, S. Verberne, E. Hoenkamp, T. van der Weide, and W. Kraaij, “When is a query a question? Reconstructing wh-requests from ad hoc-queries,” SIGIR Workshop on Query Representation and Understanding, pp. 17-20, 2010.
  12. [12] W. Kong, R. Li, J. Luo, A. Zhang, Y. Chang, and J. Allan, “Predicting Search Intent Based on Pre-Search Context,” Proc. of the 38th Int. ACM SIGIR Conf. on Research and Development in Information Retrieval (SIGIR’15), pp. 503-512, 2015.
  13. [13] Z. Cheng, B. Gao, and T.-Y. Liu, “Actively Predicting Diverse Search Intent from User Browsing Behaviors,” Proc. of the 19th Int. Conf. on World Wide Web (WWW’10), pp. 221-230, 2010.
  14. [14] M. Koskela, P. Luukkonen, T. Ruotsalo, M. Sjöberg, and P. Florèen, “Proactive Information Retrieval by Capturing Search Intent from Primary Task Context,” ACM Trans. on Interactive Intelligent Systems, Vol.8, No.3, Article No.20, 2018.
  15. [15] N. Dragovic, I. M. Azpiazu, and M. S. Pera, ““Is Sven Seven?”: A Search Intent Module for Children,” Proc. of the 39th Int. ACM SIGIR Conf. on Research and Development in Information Retrieval (SIGIR’16), pp. 885-888, 2016.
  16. [16] K. Crammer and Y. Singer, “Pranking with Ranking,” Proc. of the 14th Int. Conf. on Neural Information Processing Systems: Natural ans Synthetic (NIPS’01), pp. 641-647, 2001.
  17. [17] P. Li, C. J. C. Burges, and Q. Wu, “McRank: Learning to Rank Using Multiple Classification and Gradient Boosting,” Proc. of the 20th Int. Conf. on Neural Information Processing Systems (NIPS’07), pp. 897-904, 2007.
  18. [18] S. J. Taylor and B. Letham, “Forecasting at Scale,” PeerJ Preprints, doi: 10.7287/peerj.preprints.3190v2, 2017.

*This site is desgined based on HTML5 and CSS3 for modern browsers, e.g. Chrome, Firefox, Safari, Edge, Opera.

Last updated on Jul. 19, 2024