TY - JOUR
T1 - Effects of Personalized and Aggregate Top-N Recommendation Lists on User Preference Ratings
AU - Adomavicius, Gediminas
AU - Bockstedt, Jesse
AU - Curley, Shawn
AU - Zhang, Jingjing
N1 - Publisher Copyright:
© 2021 ACM.
PY - 2021/3/1
Y1 - 2021/3/1
N2 - Prior research has shown a robust effect of personalized product recommendations on user preference judgments for items. Specifically, the display of system-predicted preference ratings as item recommendations has been shown in multiple studies to bias users' preference ratings after item consumption in the direction of the predicted rating. Top-N lists represent another common approach for presenting item recommendations in recommender systems. Through three controlled laboratory experiments, we show that top-N lists do not induce a discernible bias in user preference judgments. This result is robust, holding for both lists of personalized item recommendations and lists of items that are top-rated based on averages of aggregate user ratings. Adding numerical ratings to the list items does generate a bias, consistent with earlier studies. Thus, in contexts where preference biases are of concern to an online retailer or platform, top-N lists, without numerical predicted ratings, would be a promising format for displaying item recommendations.
AB - Prior research has shown a robust effect of personalized product recommendations on user preference judgments for items. Specifically, the display of system-predicted preference ratings as item recommendations has been shown in multiple studies to bias users' preference ratings after item consumption in the direction of the predicted rating. Top-N lists represent another common approach for presenting item recommendations in recommender systems. Through three controlled laboratory experiments, we show that top-N lists do not induce a discernible bias in user preference judgments. This result is robust, holding for both lists of personalized item recommendations and lists of items that are top-rated based on averages of aggregate user ratings. Adding numerical ratings to the list items does generate a bias, consistent with earlier studies. Thus, in contexts where preference biases are of concern to an online retailer or platform, top-N lists, without numerical predicted ratings, would be a promising format for displaying item recommendations.
KW - Recommender systems
KW - decision biases
KW - personalization
KW - top-N recommendations
KW - user preferences
UR - http://www.scopus.com/inward/record.url?scp=85103570029&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85103570029&partnerID=8YFLogxK
U2 - 10.1145/3430028
DO - 10.1145/3430028
M3 - Article
AN - SCOPUS:85103570029
SN - 1046-8188
VL - 39
JO - ACM Transactions on Information Systems
JF - ACM Transactions on Information Systems
IS - 2
M1 - 13
ER -