Digitised human-like faces at supermarket self-service checkouts may reduce the risk of shoplifting, according to an Abertay University study.
Previous research has indicated that rising automation in retail has increased the likelihood of customers behaving dishonestly.
Experts at Abertay developed virtual characters to examine whether their presence at tills would affect shopper behavior.
They discovered that a realistic, human-like face resulted in fewer instances of dishonesty among customers than less human-like characters.
The study involved the simulation of a self-service checkout scenario, with participants being asked to scan or weigh items, before paying for them, providing them with the opportunity to select lesser weights or scan fewer items.
Susan Siebenaler, who conducted the research for her Ph.D., said: "The participants were placed in situations in which they could benefit financially through dishonest behavior.
"Participants appeared to be positively influenced by greater social presence, such as human-like features, which meant they were less likely to cheat."
Dr. Andrea Szymkowiak, senior lecturer in human computer interaction, added: "People are responsive to social human cues, and there seems to be an in-built mechanism that makes us respond to faces and eye contact."
"The idea here is that the presence of human-like digital characters may influence shopper behavior, but further research is required to determine the real-world benefit of such technology."
More information: Dishonesty and social presence in retail. rke.abertay.ac.uk/en/studentTh … l-presence-in-retail
Citation: Digitized faces reduce shoplifting risk at self-service checkouts (2020, January 6) retrieved 6 January 2020 from https://techxplore.com/news/2020-01-digitized-shoplifting-self-service-checkouts.html
This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no part may be reproduced without the written permission. The content is provided for information purposes only.