Understanding image quality and trust in peer-to-peer marketplaces
Research output: Contribution to journal › Conference article › Research › peer-review
Standard
Understanding image quality and trust in peer-to-peer marketplaces. / Ma, Xiao; Mezghani, Lina; Wilber, Kimberly; Hong, Hui; Piramuthu, Robinson; Naaman, Mor; Belongie, Serge.
In: Proceedings - 2019 IEEE Winter Conference on Applications of Computer Vision, WACV 2019, 04.03.2019, p. 511-520.Research output: Contribution to journal › Conference article › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - Understanding image quality and trust in peer-to-peer marketplaces
AU - Ma, Xiao
AU - Mezghani, Lina
AU - Wilber, Kimberly
AU - Hong, Hui
AU - Piramuthu, Robinson
AU - Naaman, Mor
AU - Belongie, Serge
N1 - Funding Information: This work is partly funded by a Facebook equipment donation to Cornell University and by AOL through the Connected Experiences Laboratory. We additionally wish to thank our crowd workers on Mechanical Turk and our colleagues from eBay. Publisher Copyright: © 2019 IEEE
PY - 2019/3/4
Y1 - 2019/3/4
N2 - As any savvy online shopper knows, second-hand peer-to-peer marketplaces are filled with images of mixed quality. How does image quality impact marketplace outcomes, and can quality be automatically predicted? In this work, we conducted a large-scale study on the quality of user-generated images in peer-to-peer marketplaces. By gathering a dataset of common second-hand products (˜75,000 images) and annotating a subset with human-labeled quality judgments, we were able to model and predict image quality with decent accuracy (˜87%). We then conducted two studies focused on understanding the relationship between these image quality scores and two marketplace outcomes: sales and perceived trustworthiness. We show that image quality is associated with higher likelihood that an item will be sold, though other factors such as view count were better predictors of sales. Nonetheless, we show that high quality user-generated images selected by our models outperform stock imagery in eliciting perceptions of trust from users. Our findings can inform the design of future marketplaces and guide potential sellers to take better product images.
AB - As any savvy online shopper knows, second-hand peer-to-peer marketplaces are filled with images of mixed quality. How does image quality impact marketplace outcomes, and can quality be automatically predicted? In this work, we conducted a large-scale study on the quality of user-generated images in peer-to-peer marketplaces. By gathering a dataset of common second-hand products (˜75,000 images) and annotating a subset with human-labeled quality judgments, we were able to model and predict image quality with decent accuracy (˜87%). We then conducted two studies focused on understanding the relationship between these image quality scores and two marketplace outcomes: sales and perceived trustworthiness. We show that image quality is associated with higher likelihood that an item will be sold, though other factors such as view count were better predictors of sales. Nonetheless, we show that high quality user-generated images selected by our models outperform stock imagery in eliciting perceptions of trust from users. Our findings can inform the design of future marketplaces and guide potential sellers to take better product images.
UR - http://www.scopus.com/inward/record.url?scp=85063587994&partnerID=8YFLogxK
U2 - 10.1109/WACV.2019.00060
DO - 10.1109/WACV.2019.00060
M3 - Conference article
AN - SCOPUS:85063587994
SP - 511
EP - 520
JO - Proceedings - 2019 IEEE Winter Conference on Applications of Computer Vision, WACV 2019
JF - Proceedings - 2019 IEEE Winter Conference on Applications of Computer Vision, WACV 2019
T2 - 19th IEEE Winter Conference on Applications of Computer Vision, WACV 2019
Y2 - 7 January 2019 through 11 January 2019
ER -
ID: 301824730