AMUR - User Guidance and System Tuning for Search Sessions

Team: Wilko van Hoek, Ameni Sahraoui, Vu Tran (Universität Duisburg-Essen, Informationsysteme)
Leader: Dr. Philipp Mayr, Prof. Dr. Norbert Fuhr (Universität Duisburg-Essen, Informationsysteme)
Scientific unit: Knowledge Technologies for the Social Sciences (WTS)

Abstract

Today retrieval environments do not provide adequate support for interactive retrieval sessions consisting of several progressively modified queries. The classical retrieval measures also fail in interactive retrieval scenarios with multiple queries. The AMUR project aims at improving the support of interactive retrieval sessions following two major goals:

Improving user guidance: based on the user’s search history the retrieval system recommends search activities. Current methods are often limited to the current situation and recommend content instead of possible actions.

System tuning: methods will be developed that improve the overall effectiveness of retrieval sessions. Current methods either focus on specific aspects and hold no information about the effects on the whole retrieval process or assess the whole session but are unable to assess the influence of specific system components.

Achieving these goals requires a close collaboration between empirical practice and theory modeling.

On the empirical side, we would like to consider subject-specific searches using the example of the social scientists specialist portal sowiport, since retrieval sessions in such environments are more likely to be observed in these specialized search engines than in the web search. This also creates a greater need for appropriate support. Furthermore, it is expected that in this context the searching competence is more distinctive on average, so that higher searching activities could be observed more often. On the theory side, the probabilistic ranking principle for interactive information retrieval (IPRP), developed by our project partner, and the modeling of retrieval sessions as Markov process should be the starting point, in order to develop better models for user guidance, on the one hand, and to use novel simulation approaches to form the basis for targeted system improvements on the other hand. In accordance with this general objective, empirical data should first be collected and analyzed in sowiport and ezdl, which should serve as the basis for improved modeling.

Runtime

01.07.2015 - 31.03.2018

Sponsored by

Partner

  • Universität Duisburg-Essen

Publications

  • Kacem, A., & Mayr, P. (2018). Analysis of Search Stratagem Utilisation. Scientometrics, 116(2), 1383–1400. doi.org/10.1007/s11192-018-2821-8
  • Carevic, Z., Schüller, S., Mayr, P., & Fuhr, N. (2018). Contextualised Browsing in a Digital Library’s Living Lab. Proceedings of the 18th ACM/IEEE on Joint Conference on Digital Libraries, 89–98. doi.org/10.1145/3197026.3197054
  • Hienert, D., Mitsui, M., Mayr, P., Shah, C., & Belkin, N. J. (2018). The Role of the Task Topic in Web Search of Different Task Types. Proceedings of the 2018 Conference on Human Information Interaction&Retrieval - CHIIR ’18, 72–81. doi.org/10.1145/3176349.3176382
  • Hienert, D. (2017). User Interests in German Social Science Literature Search: A Large Scale Log Analysis. Proceedings of the 2017 Conference on Conference Human Information Interaction and Retrieval - CHIIR ’17, 7–16. doi.org/10.1145/3020165.3020168
  • Hienert, D., & Kern, D. (2017). Term-Mouse-Fixations as an Additional Indicator for Topical User Interests in Domain-Specific Search. Proceedings of the ACM SIGIR International Conference on Theory of Information Retrieval - ICTIR ’17, 249–252. doi.org/10.1145/3121050.3121088
  • Hienert, D., & Lusky, M. (2017). Where Do All These Search Terms Come From? – Two Experiments in Domain-Specific Search. In J. M. Jose, C. Hauff, I. S. Altıngovde, D. Song, D. Albakour, S. Watt, & J. Tait (Eds.), Advances in Information Retrieval (Vol. 10193, pp. 15–26). doi.org/10.1007/978-3-319-56608-5_2
  • Belkin, N. J., Hienert, D., Mayr, P., & Shah, C. (2017). Data Requirements for Evaluation of Personalization of Information Retrieval - A Position Paper. In Working Notes of CLEF 2017 - Conference and Labs of the Evaluation Forum. Dublin, Ireland: CEUR-WS.org. Retrieved from http://ceur-ws.org/Vol-1866/paper_193.pdf
  • Carevic, Z., Lusky, M., van Hoek, W., & Mayr, P. (2017). Investigating exploratory search activities based on the stratagem level in digital libraries. International Journal on Digital Libraries. https://doi.org/10.1007/s00799-017-0226-6
  • Kacem, A., & Mayr, P. (2017). Analysis of Footnote Chasing and Citation Searching in an Academic Search Engine. In Proceedings of the 2nd Joint Workshop on Bibliometric-enhanced Information Retrieval and Natural Language Processing for Digital Libraries (BIRNDL 2017) co-located with the 40th International ACM SIGIR Conference on Research and Development in Information (pp. 91–100). Tokyo, Japan. Retrieved from https://arxiv.org/abs/1707.02494 http://ceur-ws.org/Vol-1888/paper8.pdf
  • Mayr, P., & Kacem, A. (2017). A Complete Year of User Retrieval Sessions in a Social Sciences Academic Search Engine. In TPDL 2017: Research and Advanced Technology for Digital Libraries (pp. 560–565). https://doi.org/10.1007/978-3-319-67008-9_46
  • Hienert, D., & Mutschke, P. (2016). A Usefulness-based Approach for Measuring the Local and Global Effect of IIR Services. Proceedings of the 2016 ACM on Conference on Human Information Interaction and Retrieval - CHIIR ’16, 153–162. doi.org/10.1145/2854946.2854962
  • Mayr, P. (2016). How do practitioners, PhD students and postdocs in the social sciences assess topic-specific recommendations? In Proc. of the Joint Workshop on Bibliometric-enhanced Information Retrieval and Natural Language Processing for Digital Libraries (BIRNDL2016) (pp. 84–92). Newark, New Jersey, USA: CEUR-WS.org. Retrieved from http://ceur-ws.org/Vol-1610/paper10.pdf
  • Carevic, Z., & Mayr, P. (2016). Survey on High-level Search Activities Based on the Stratagem Level in Digital Libraries. In 20th International Conference on Theory and Practice of Digital Libraries (TPDL 2016) (pp. 54–66). https://doi.org/10.1007/978-3-319-43997-6_5
  • Mayr, P. (2016). Sowiport User Search Sessions Data Set (SUSS). GESIS, Datorium. https://doi.org/10.7802/1380
  • Mayr, P. (2016). Sowiport user queries sample (SQS). GESIS, Datorium. https://doi.org/10.7802/1372
  • Carevic, Z., & Mayr, P. (2015). Extending search facilities via bibliometric-enhanced stratagems. In Proc. of the 2nd Workshop on Bibliometric-enhanced Information Retrieval (BIR2015) (pp. 40–46). Vienna, Austria: CEUR-WS.org. Retrieved from http://ceur-ws.org/Vol-1344/paper5.pdf
  • Hienert, D., Sawitzki, F., & Mayr, P. (2015). Digital Library Research in Action – Supporting Information Retrieval in Sowiport. D-Lib Magazine, 21(3/4). https://doi.org/10.1045/march2015-hienert