TY - JOUR
T1 - Reducing recommender system biases
T2 - An investigation of rating display designs
AU - Adomavicius, Gediminas
AU - Bockstedt, Jesse C.
AU - Curley, Shawn P.
AU - Zhang, Jingjing
N1 - Publisher Copyright:
© 2019 University of Minnesota. All rights reserved.
PY - 2019
Y1 - 2019
N2 - Prior research has shown that online recommendations have a significant influence on consumers' preference ratings and economic behavior. Specifically, biases induced by observing personalized system recommendations can lead to distortions in users' self-reported preference ratings after consumption of an item, thus contaminating the users' subsequent inputs to the recommender system. This, in turn, provides the system with an inaccurate view of user preferences and opens up possibilities of rating manipulation. As recommender systems continue to become increasingly popular in today's online environments, preventing or reducing such system-induced biases constitutes a highly important and practical research problem. In this paper, we address this problem via the analysis of different rating display designs for the purpose of proactively preventing biases before they occur (i.e., at rating collection time). We use randomized laboratory experimentation to test how the presentation format of personalized recommendations affects the biases generated in post-consumption preference ratings. We demonstrate that graphical rating display designs of recommender systems are more advantageous than numerical designs in reducing the biases, although none are able to remove biases completely. We also show that scale compatibility is a contributing mechanism operating to create these biases, although not the only one. Together, the results have practical implications for the design and implementation of recommender systems as well as theoretical implications for the study of recommendation biases.
AB - Prior research has shown that online recommendations have a significant influence on consumers' preference ratings and economic behavior. Specifically, biases induced by observing personalized system recommendations can lead to distortions in users' self-reported preference ratings after consumption of an item, thus contaminating the users' subsequent inputs to the recommender system. This, in turn, provides the system with an inaccurate view of user preferences and opens up possibilities of rating manipulation. As recommender systems continue to become increasingly popular in today's online environments, preventing or reducing such system-induced biases constitutes a highly important and practical research problem. In this paper, we address this problem via the analysis of different rating display designs for the purpose of proactively preventing biases before they occur (i.e., at rating collection time). We use randomized laboratory experimentation to test how the presentation format of personalized recommendations affects the biases generated in post-consumption preference ratings. We demonstrate that graphical rating display designs of recommender systems are more advantageous than numerical designs in reducing the biases, although none are able to remove biases completely. We also show that scale compatibility is a contributing mechanism operating to create these biases, although not the only one. Together, the results have practical implications for the design and implementation of recommender systems as well as theoretical implications for the study of recommendation biases.
KW - Decision bias
KW - Experimental research
KW - Interface design
KW - Preference ratings
KW - Recommender systems
KW - Scale compatibility
UR - http://www.scopus.com/inward/record.url?scp=85078915590&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85078915590&partnerID=8YFLogxK
U2 - 10.25300/MISQ/2019/13949
DO - 10.25300/MISQ/2019/13949
M3 - Article
AN - SCOPUS:85078915590
SN - 0276-7783
VL - 43
SP - 1321
EP - 1341
JO - MIS Quarterly: Management Information Systems
JF - MIS Quarterly: Management Information Systems
IS - 4
ER -