Information scent, searching and stopping: modelling SERP level stopping behaviour

David Maxwell, Leif Azzopardi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Current models and measures of the \emph{Interactive Information Retrieval (IIR)} process typically assume that a searcher will always examine the first snippet in a given \emph{Search Engine Results Page (SERP)}, and then with some probability or cutoff, he or she will stop examining snippets and/or documents in the ranked list (snippet level stopping). Prior work has however shown that searchers will form an initial impression of the SERP, and will often abandon a page without clicking on or inspecting in detail any snippets or documents. That is, the \emph{information scent} affects their decision to continue. In this work, we examine whether considering the information scent of a page leads to better predictions of stopping behaviour. In a simulated analysis, grounded with data from a prior user study, we show that introducing a SERP level stopping strategy can improve the performance attained by simulated users, resulting in an increase in gain across most snippet level stopping strategies. When compared to actual search and stopping behaviour, incorporating SERP level stopping offers a closer approximation than without. These findings show that models and measures that na\"{i}vely assume snippets and documents in a ranked list are actually examined in detail are less accurate, and that modelling SERP level stopping is required to create more realistic models of the search process.
LanguageEnglish
Title of host publicationAdvances in Information Retrieval - 40th European Conference on IR Research, ECIR 2018, Proceedings
Subtitle of host publicationLecture Notes in Computer Science
Place of PublicationBerlin
PublisherSpringer-Verlag
Pages210-222
Number of pages13
Volume10772
ISBN (Print)9783319769400
DOIs
StatePublished - 30 Apr 2018

Fingerprint

Search engines
Information retrieval

Keywords

  • information retrieval
  • SERP
  • Search Engine Results Page
  • stopping behaviour

Cite this

Maxwell, D., & Azzopardi, L. (2018). Information scent, searching and stopping: modelling SERP level stopping behaviour. In Advances in Information Retrieval - 40th European Conference on IR Research, ECIR 2018, Proceedings: Lecture Notes in Computer Science (Vol. 10772, pp. 210-222). Berlin: Springer-Verlag. DOI: 10.1007/978-3-319-76941-7_16
Maxwell, David ; Azzopardi, Leif. / Information scent, searching and stopping : modelling SERP level stopping behaviour. Advances in Information Retrieval - 40th European Conference on IR Research, ECIR 2018, Proceedings: Lecture Notes in Computer Science. Vol. 10772 Berlin : Springer-Verlag, 2018. pp. 210-222
@inproceedings{05d5ba6d01d547d795059433844e9479,
title = "Information scent, searching and stopping: modelling SERP level stopping behaviour",
abstract = "Current models and measures of the \emph{Interactive Information Retrieval (IIR)} process typically assume that a searcher will always examine the first snippet in a given \emph{Search Engine Results Page (SERP)}, and then with some probability or cutoff, he or she will stop examining snippets and/or documents in the ranked list (snippet level stopping). Prior work has however shown that searchers will form an initial impression of the SERP, and will often abandon a page without clicking on or inspecting in detail any snippets or documents. That is, the \emph{information scent} affects their decision to continue. In this work, we examine whether considering the information scent of a page leads to better predictions of stopping behaviour. In a simulated analysis, grounded with data from a prior user study, we show that introducing a SERP level stopping strategy can improve the performance attained by simulated users, resulting in an increase in gain across most snippet level stopping strategies. When compared to actual search and stopping behaviour, incorporating SERP level stopping offers a closer approximation than without. These findings show that models and measures that na\{"}{i}vely assume snippets and documents in a ranked list are actually examined in detail are less accurate, and that modelling SERP level stopping is required to create more realistic models of the search process.",
keywords = "information retrieval, SERP, Search Engine Results Page, stopping behaviour",
author = "David Maxwell and Leif Azzopardi",
year = "2018",
month = "4",
day = "30",
doi = "10.1007/978-3-319-76941-7_16",
language = "English",
isbn = "9783319769400",
volume = "10772",
pages = "210--222",
booktitle = "Advances in Information Retrieval - 40th European Conference on IR Research, ECIR 2018, Proceedings",
publisher = "Springer-Verlag",

}

Maxwell, D & Azzopardi, L 2018, Information scent, searching and stopping: modelling SERP level stopping behaviour. in Advances in Information Retrieval - 40th European Conference on IR Research, ECIR 2018, Proceedings: Lecture Notes in Computer Science. vol. 10772, Springer-Verlag, Berlin, pp. 210-222. DOI: 10.1007/978-3-319-76941-7_16

Information scent, searching and stopping : modelling SERP level stopping behaviour. / Maxwell, David; Azzopardi, Leif.

Advances in Information Retrieval - 40th European Conference on IR Research, ECIR 2018, Proceedings: Lecture Notes in Computer Science. Vol. 10772 Berlin : Springer-Verlag, 2018. p. 210-222.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Information scent, searching and stopping

T2 - modelling SERP level stopping behaviour

AU - Maxwell,David

AU - Azzopardi,Leif

PY - 2018/4/30

Y1 - 2018/4/30

N2 - Current models and measures of the \emph{Interactive Information Retrieval (IIR)} process typically assume that a searcher will always examine the first snippet in a given \emph{Search Engine Results Page (SERP)}, and then with some probability or cutoff, he or she will stop examining snippets and/or documents in the ranked list (snippet level stopping). Prior work has however shown that searchers will form an initial impression of the SERP, and will often abandon a page without clicking on or inspecting in detail any snippets or documents. That is, the \emph{information scent} affects their decision to continue. In this work, we examine whether considering the information scent of a page leads to better predictions of stopping behaviour. In a simulated analysis, grounded with data from a prior user study, we show that introducing a SERP level stopping strategy can improve the performance attained by simulated users, resulting in an increase in gain across most snippet level stopping strategies. When compared to actual search and stopping behaviour, incorporating SERP level stopping offers a closer approximation than without. These findings show that models and measures that na\"{i}vely assume snippets and documents in a ranked list are actually examined in detail are less accurate, and that modelling SERP level stopping is required to create more realistic models of the search process.

AB - Current models and measures of the \emph{Interactive Information Retrieval (IIR)} process typically assume that a searcher will always examine the first snippet in a given \emph{Search Engine Results Page (SERP)}, and then with some probability or cutoff, he or she will stop examining snippets and/or documents in the ranked list (snippet level stopping). Prior work has however shown that searchers will form an initial impression of the SERP, and will often abandon a page without clicking on or inspecting in detail any snippets or documents. That is, the \emph{information scent} affects their decision to continue. In this work, we examine whether considering the information scent of a page leads to better predictions of stopping behaviour. In a simulated analysis, grounded with data from a prior user study, we show that introducing a SERP level stopping strategy can improve the performance attained by simulated users, resulting in an increase in gain across most snippet level stopping strategies. When compared to actual search and stopping behaviour, incorporating SERP level stopping offers a closer approximation than without. These findings show that models and measures that na\"{i}vely assume snippets and documents in a ranked list are actually examined in detail are less accurate, and that modelling SERP level stopping is required to create more realistic models of the search process.

KW - information retrieval

KW - SERP

KW - Search Engine Results Page

KW - stopping behaviour

U2 - 10.1007/978-3-319-76941-7_16

DO - 10.1007/978-3-319-76941-7_16

M3 - Conference contribution

SN - 9783319769400

VL - 10772

SP - 210

EP - 222

BT - Advances in Information Retrieval - 40th European Conference on IR Research, ECIR 2018, Proceedings

PB - Springer-Verlag

CY - Berlin

ER -

Maxwell D, Azzopardi L. Information scent, searching and stopping: modelling SERP level stopping behaviour. In Advances in Information Retrieval - 40th European Conference on IR Research, ECIR 2018, Proceedings: Lecture Notes in Computer Science. Vol. 10772. Berlin: Springer-Verlag. 2018. p. 210-222. Available from, DOI: 10.1007/978-3-319-76941-7_16