This study analyzes the effects that the position of the alternatives ranked by a search engine and the relative impatience of users have on their information retrieval behavior. We design a stochastic information retrieval algorithm calibrated to mimic the click-through rates (CTRs) of users observed in real-life environments. We introduce two versions of the mimicking algorithm designed to demonstrate the importance of impatience as a determinant of CTRs conditioned by the alternatives’ ranking position. The first version assumes that users proceed sequentially through the ranking until they find an alternative satisficing their expectations. Once they find a satisficing alternative, they continue retrieving information until they observe an alternative that violates their expectations. The second version increases users’ impatience, who stop retrieving information as soon as an alternative does not satisfy their expectations – even if it is the top-ranked one. All three algorithmic structures are sufficiently malleable to incorporate any potential modification to users’ beliefs and preferences. We simulate sets of 1,000,000 queries to illustrate how the CTRs of the top three ranked alternatives remain stable as users grow impatient, with differences widening as growingly impatient users proceed halfway through the ranking.

An information retrieval benchmarking model of satisficing and impatient users’ behavior in online search environments / Di Caprio, D.; Santos-Arteaga, F. J.; Tavana, M.. - In: EXPERT SYSTEMS WITH APPLICATIONS. - ISSN 0957-4174. - 191:(2022), p. 116352. [10.1016/j.eswa.2021.116352]

An information retrieval benchmarking model of satisficing and impatient users’ behavior in online search environments

Di Caprio D.;
2022-01-01

Abstract

This study analyzes the effects that the position of the alternatives ranked by a search engine and the relative impatience of users have on their information retrieval behavior. We design a stochastic information retrieval algorithm calibrated to mimic the click-through rates (CTRs) of users observed in real-life environments. We introduce two versions of the mimicking algorithm designed to demonstrate the importance of impatience as a determinant of CTRs conditioned by the alternatives’ ranking position. The first version assumes that users proceed sequentially through the ranking until they find an alternative satisficing their expectations. Once they find a satisficing alternative, they continue retrieving information until they observe an alternative that violates their expectations. The second version increases users’ impatience, who stop retrieving information as soon as an alternative does not satisfy their expectations – even if it is the top-ranked one. All three algorithmic structures are sufficiently malleable to incorporate any potential modification to users’ beliefs and preferences. We simulate sets of 1,000,000 queries to illustrate how the CTRs of the top three ranked alternatives remain stable as users grow impatient, with differences widening as growingly impatient users proceed halfway through the ranking.
2022
Di Caprio, D.; Santos-Arteaga, F. J.; Tavana, M.
An information retrieval benchmarking model of satisficing and impatient users’ behavior in online search environments / Di Caprio, D.; Santos-Arteaga, F. J.; Tavana, M.. - In: EXPERT SYSTEMS WITH APPLICATIONS. - ISSN 0957-4174. - 191:(2022), p. 116352. [10.1016/j.eswa.2021.116352]
File in questo prodotto:
File Dimensione Formato  
DiCaprio et al 2022 - ESWA.pdf

Solo gestori archivio

Tipologia: Versione editoriale (Publisher’s layout)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 2.37 MB
Formato Adobe PDF
2.37 MB Adobe PDF   Visualizza/Apri
DiCaprio et al 2022 - ESWA.docx

Solo gestori archivio

Tipologia: Altro materiale allegato (Other attachments)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 204.75 kB
Formato Microsoft Word XML
204.75 kB Microsoft Word XML   Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11572/327342
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 9
  • ???jsp.display-item.citation.isi??? 8
social impact