On Search Powered Navigation

Our paper "On Search Powered Navigation", with Glorianna Jagfeld, Hosein Azarbonyad, Alex Olieman, Jaap Kamps, Maarten Marx, has been accepted as a short paper at . \o/
Knowledge graphs and other hierarchical domain ontologies hold great promise for complex information seeking tasks, yet their massive size defies the standard and effective way smaller hierarchies are used as a static navigation structure in faceted search or standard website navigation. As a result, we see the only limited use of knowledge bases in entity surfacing for navigational queries, and fail to realize their full potential to empower search. Seeking information in structured environments consists of two main activities: exploratory browsing and focused searching.
Exploratory browsing refers to activities aimed at better defining the information need and increasing the level of understanding of the information space, while focused searching includes activities such as query rewriting and comparison of results, which are performed after the information need has been made more concrete. Based on the interplay of these two actions, a search system is supposed to provide a connected space of information for the users to navigate, as well as search to adjust the focus of their browsing towards useful content.

In our paper, we introduce the concept of Search Powered Navigation (SPN), which enables users to combine navigation with the query based searching in a structured information space, and offers a way to find a balance between exploration and exploitation. We hypothesize that SPN enables users to exploit the semantic structure of a large knowledge base in an effective way. We test this hypothesis by conducting a user study in which users are engaged in exploratory search activities and investigate the effect of SPN on the variability in users’ behavior and experience. We employed an exploratory search system on parliamentary data in two modes, pure navigation and search powered navigation, and tested two types of tasks, broad- and focused-topic tasks.
In our study, the primary goal is to investigate information seeking behavior and user experience when navigation is empowered by a search functionality. We break it down into the following two research questions:

  • RQ1: What is the effect of search powered navigation on user behavior in different types of exploratory search tasks?
  • RQ2: Does empowering navigation with search improve user experience in different types of exploratory search tasks?

This work is an extension of our previous paper: "Telling How to Narrow It Down: Browsing Path Recommendation for Exploratory Search".  For more details on our new results, please take a look at our paper:

  • Mostafa Dehghani, G. Jagfeld, A. Olieman, H. Azarbonyad J. Kamps, and M. Marx. "On Search Powered Navigation'', In Proceedings of the ACM International Conference on the Theory of Information Retrieval (ICTIR'17). [Poster]