=Paper=
{{Paper
|id=Vol-2741/paper-05
|storemode=property
|title=Understanding Faceted Search from Information Retrieval,
                     Information Science and Data
                     Science Perspectives
|pdfUrl=https://ceur-ws.org/Vol-2741/paper-05.pdf
|volume=Vol-2741
|authors=Xi Niu
|dblpUrl=https://dblp.org/rec/conf/sigir/Niu20
}}
==Understanding Faceted Search from Information Retrieval,
                     Information Science and Data
                     Science Perspectives==
<pdf width="1500px">https://ceur-ws.org/Vol-2741/paper-05.pdf</pdf>
<pre>
   Invited Talk: Understanding Faceted Search
from Information Retrieval, Information Science,
          and Data Science Perspectives

                                      Xi Niu

                   University of North Carolina at Charlotte, USA



1     Abstract
I am honored to be invited to give a talk on faceted search at the BIRDS Work-
shop (Bridging the Gap between Information Science, Information Retrieval,
and Data Science) at SIGIR 2020. This talk reflects well my research area,
which uniquely connects Information Retrieval (IR), Information Science (IS),
and Data Science (DS). My research area is attributed to my educational and
working background: I obtained my Master’s degree in Software Engineering
and my Ph.D. degree in Information Science. Now I am a faculty member at a
computing department.
    Historically, there has been a divide between systems and users in the IR
research communities. I believe this divide reflects how researchers weigh the
relative importance between developing new retrieval algorithms compared to
understanding how people search for information. However, there is increasing
agreement that the interaction between the users and the search engine is a
fundamental part of the IR process. Due to my unique background, I am the
researcher who builds models, develops algorithms, as well as runs user studies
in order to understand how people seek information. My research has provided
evidence that more effective information access can be achieved by a system that
actively supports user interaction.
    IR researchers make modern search engines or recommender systems rank
better, retrieve better, or just function better, and most of today’s IR papers
are very well-defined or in other words, narrowly focused. I believe this BIRDS
workshop is eye-widening, and will provide thoughts from a bigger, richer, or
more comprehensive view of how information retrieval systems can better serve
people, not only for their short-term needs but also for their long-term benefits,
not only for the immediate relevance, but also for broader discovery.
    Our research project on faceted search is an example of how IR, IS, and
DS complement each other, offering a holistic approach that goes beyond each
discipline alone. Faceted search has become a common feature on most search
interfaces in e-commerce websites, digital libraries, government’s open informa-
tion portals, and so on. Beyond the existing studies on developing algorithms for
    Copyright © 2020 for this paper by its authors. Use permitted under Creative
    Commons License Attribution 4.0 International (CC BY 4.0). BIRDS 2020, 30 July
    2020, Xi’an, China (online).


                                        14
faceted search and empirical studies on facet usage, this talk investigated user
real-time interactions with facets over the course of a search from information
retrieval, data science and human factor perspectives. It adopted a Random For-
est (RF) model to successfully predict facet use using search dynamic variables.
In addition, the RF model provided a ranking of variables by their predictive
power, which suggests that the search process follows rhythmic flow of a sequence
within which facet addition is mostly influenced by its immediately preceding
action. In the follow-up user study, it is found that participants used facets at
critical points from the beginning to end of search sessions. Participants used
facets for distinctive reasons at different stages. They also used facets implicitly
without applying the facets to their search. Most participants liked the faceted
search, although a few participants were concerned about the choice overload
introduced by facets. The results of this research could be used to understand
information seekers and propose or refine a set of practical design guidelines for
faceted search. This research demonstrates how we could intersect Information
Retrieval, Information Science, and Data Science to better tackle the traditional
research questions in IR.

Keywords: Information Retrieval · Information Science · Data Science · faceted
search · machine learning · predictive analytics · user studies.




                                        15

</pre>