Exploring Composite Retrieval from the Users’ Perspective

  • Horaţiu Bota
  • Ke Zhou
  • Joemon J. Jose
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9022)


Aggregating results from heterogeneous sources and presenting them in a blended interface – aggregated search – has become standard practice for most commercial Web search engines. Composite retrieval is emerging as a new search paradigm, where users are presented with semantically aggregated information objects, called bundles, containing results originating from different verticals. In this paper we study composite retrieval from the user perspective. We conducted an exploratory user study where 40 participants were required to manually generate bundles that satisfy various information needs, using heterogeneous results retrieved by modern search engines. Our main objective was to analyse the contents and characteristics of user-generated bundles. Our results show that users generate bundles on common subtopics, centred around pivot documents, and that they favour bundles that are relevant, diverse and cohesive.


Composite retrieval bundle vertical diversity relevance cohesion 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Angel, A., Chaudhuri, S., Das, G., Koudas, N.: Ranking objects based on relationships and fixed associations. In: EDBT 2009, pp. 910–921 (2009)Google Scholar
  2. 2.
    Arguello, J., Capra, R.: The effect of aggregated search coherence on search behavior. In: CIKM 2012, pp. 1293–1302 (2012)Google Scholar
  3. 3.
    Bailey, P., Craswell, N., White, R.W., Chen, L., Satyanarayana, A., Tahaghoghi, S.M.: Evaluating search systems using result page context. In: IIiX 2010, pp. 105-114 (2010)Google Scholar
  4. 4.
    Bota, H., Zhou, K., Jose, J.M., Lalmas, M.: Composite retrieval of heterogeneous web search. In: WWW 2014, pp. 119–130 (2014)Google Scholar
  5. 5.
    Bron, M., van Gorp, J., Nack, F., Baltussen, L.B., de Rijke, M.: Aggregated search interface preferences in multi-session search tasks. In: SIGIR 2013, pp. 123–132 (2013)Google Scholar
  6. 6.
    Corley, C., Mihalcea, R.: Measuring the semantic similarity of texts. In: EMSEE 2005, pp. 13–18 (2005)Google Scholar
  7. 7.
    Demeester, T., Trieschnigg, D., Nguyen, D., Hiemstra, D.: Overview of the trec 2013 federated web search track. In: Proceedings of the Text Retrieval Conference, pp. 1–11 (2013)Google Scholar
  8. 8.
    Deng, T., Fan, W., Geerts, F.: On the complexity of package recommendation problems. In: PODS 2012, pp. 261-272 (2012)Google Scholar
  9. 9.
    Diaz, F., Lalmas, M., Shokouhi, M.: From federated to aggregated search. In: SIGIR 2010, p. 910 (2010)Google Scholar
  10. 10.
    Golbus, P.B., Zitouni, I., Kim, J.Y., Hassan, A., Diaz, F.: Contextual and dimensional relevance judgments for reusable serp-level evaluation. In: WWW 2014, pp. 131–142 (2014)Google Scholar
  11. 11.
    Guo, X., Ishikawa, Y.: Multi-objective optimal combination queries. In: Hameurlain, A., Liddle, S.W., Schewe, K.-D., Zhou, X. (eds.) DEXA 2011, Part I. LNCS, vol. 6860, pp. 47–61. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  12. 12.
    Jansen, B.J., Pooch, U.: A review of web searching studies and a framework for future research. J. Am. Soc. Inf. Sci. Technol. 52(3), 235–246 (2001)CrossRefGoogle Scholar
  13. 13.
    Jiang, J.J., Conrath, D.W.: Semantic similarity based on corpus statistics and lexical taxonomy. CoRR, cmp-lg/9709008 (1997)Google Scholar
  14. 14.
    Käki, M.: Findex: Search result categories help users when document ranking fails. In: CHI 2005, pp. 131–140 (2005)Google Scholar
  15. 15.
    Mendez-Diaz, I., Zabala, P., Bonchi, F., Castillo, C., Feuerstein, E., Amer-Yahia, S.: Composite retrieval of diverse and complementary bundles. IEEE Transactions on Knowledge and Data Engineering 99(preprints), 1 (2014)Google Scholar
  16. 16.
    Miller, G.A.: Wordnet: A lexical database for english. Commun. ACM 38(11), 39–41 (1995)CrossRefGoogle Scholar
  17. 17.
    Rose, D.E., Levinson, D.: Understanding user goals in web search. In: WWW 2004, pp. 13-19 (2004)Google Scholar
  18. 18.
    Spink, A., Jansen, B.J., Wolfram, D., Saracevic, T.: From e-sex to e-commerce: Web search changes. Computer 35(3), 107–109 (2002)CrossRefGoogle Scholar
  19. 19.
    Sushmita, S., Joho, H., Lalmas, M., Villa, R.: Factors affecting click-through behavior in aggregated search interfaces. In: CIKM 2010, pp. 519–528 (2010)Google Scholar
  20. 20.
    Wilson, M.L., Kules, B., Schraefel, M.C., Shneiderman, B.: Designing future search interfaces for the web. Found. Trends Web Sci. 2(1), 1–97 (2010)CrossRefzbMATHGoogle Scholar
  21. 21.
    Yue, Z., Han, S., He, D.: Modeling search processes using hidden states in collaborative exploratory web search. In: CSCW 2014, pp. 820–830 (2014)Google Scholar
  22. 22.
    Zhou, K., Cummins, R., Lalmas, M., Jose, J.M.: Evaluating aggregated search pages. In: SIGIR 2012, pp. 115–124. ACM (2012)Google Scholar
  23. 23.
    Zhou, K., Cummins, R., Lalmas, M., Jose, J.M.: Which vertical search engines are relevant? In: WWW 2013, pp. 1557-1568 (2013)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Horaţiu Bota
    • 1
  • Ke Zhou
    • 2
  • Joemon J. Jose
    • 1
  1. 1.University of GlasgowGlasgowUK
  2. 2.Yahoo Labs LondonLondonUK

Personalised recommendations