Understanding the overvaluation of facial trustworthiness in Airbnb host images
作者：
Highlights：
• Original theoretical model examining the overvaluation of online facial assessments.
• Research model based on the original application of dangerous decisions theory.
• Application of trained convolutional neural network to assess facial characteristics.
• Model supported by host data from 78,386 hosts across 10 US cities.
• Facial cues must be combined with other reputational sources to be effective.
摘要
•Original theoretical model examining the overvaluation of online facial assessments.•Research model based on the original application of dangerous decisions theory.•Application of trained convolutional neural network to assess facial characteristics.•Model supported by host data from 78,386 hosts across 10 US cities.•Facial cues must be combined with other reputational sources to be effective.
论文关键词：Host,Face,Perceived trustworthiness,Dangerous decisions theory,Deep learning
论文评审过程：Received 29 July 2020, Revised 26 October 2020, Accepted 26 October 2020, Available online 5 November 2020, Version of Record 10 December 2020.
论文官网地址：https://doi.org/10.1016/j.ijinfomgt.2020.102265
