• norsk
    • English
  • English 
    • norsk
    • English
  • Login
View Item 
  •   Home
  • Øvrige samlinger
  • Publikasjoner fra CRIStin - NTNU
  • View Item
  •   Home
  • Øvrige samlinger
  • Publikasjoner fra CRIStin - NTNU
  • View Item
JavaScript is disabled for your browser. Some features of this site may not work without it.

How Quickly Can We Predict Users’ Ratings on Aesthetic Evaluations of Websites? Employing Machine Learning on Eye-Tracking Data

Pappas, Ilias; Sharma, Kshitij; Mikalef, Patrick; Giannakos, Michail
Peer reviewed, Journal article
Accepted version
Thumbnail
View/Open
Pappas (2.504Mb)
URI
https://hdl.handle.net/11250/2650875
Date
2020
Metadata
Show full item record
Collections
  • Institutt for datateknologi og informatikk [4881]
  • Publikasjoner fra CRIStin - NTNU [26591]
Original version
Lecture Notes in Computer Science (LNCS). 2020, 12067 429-440.   https://doi.org/10.1007/978-3-030-45002-1
Abstract
Abstract. This study examines how quickly we can predictusers’ ratings on vis-ual aesthetics in terms of simplicity, diversity, colorfulness, craftsmanship.To predict users’ ratings, first we capturegaze behaviorwhile looking at high, neu-tral, and lowvisuallyappealing websites, followed by a survey regarding user perceptions on visual aesthetics towards the samewebsites.We conduct an ex-periment with 23 experienced users in online shopping, capture gaze behavior andthrough employing machine learning weexamine how fast we can accurately predict their ratings. The findings showthat after 25 seconds we can predict rat-ings with an error rate ranging from 9% to 11% dependingon which facet of visual aesthetic is examined. Furthermore, within the first 15 seconds we can have a goodand sufficientprediction for simplicity and colorfulness, with error rates 11% and 12% respectively.For diversity and craftsmanship, 20 seconds are needed to get a good and sufficient prediction similar to the one from 25 seconds.The findings indicate that we need more than 10 secondsof viewing timeto be able to accurately capture perceptions on visual aesthetics. The study contributes by offering new ways fordesigningsystems that will take into account users’ gaze behavior in an unobtrusive manner and will be able inform researchers and designers about their perceptions of visual aesthetics.
Publisher
Springer
Journal
Lecture Notes in Computer Science (LNCS)

Contact Us | Send Feedback

Privacy policy
DSpace software copyright © 2002-2019  DuraSpace

Service from  Unit
 

 

Browse

ArchiveCommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsDocument TypesJournalsThis CollectionBy Issue DateAuthorsTitlesSubjectsDocument TypesJournals

My Account

Login

Statistics

View Usage Statistics

Contact Us | Send Feedback

Privacy policy
DSpace software copyright © 2002-2019  DuraSpace

Service from  Unit