Understanding choice overload in recommender systems

Even though people are attracted by large, high quality recommendation sets, psychological research on choice overload shows that choosing an item from recommendation sets containing many attractive items can be a very difficult task. A web-based user experiment using a matrix factorization algorithm applied to the MovieLens dataset was used to investigate the effect of recommendation set size (5 or 20 items) and set quality (low or high) on perceived variety, recommendation set attractiveness, choice difficulty and satisfaction with the chosen item. The results show that larger sets containing only good items do not necessarily result in higher choice satisfaction compared to smaller sets, as the increased recommendation set attractiveness is counteracted by the increased difficulty of choosing from these sets. These findings were supported by behavioral measurements revealing intensified information search and increased acquisition times for these large attractive sets. Important implications of these findings for the design of recommender system user interfaces will be discussed.

[1]  I. Simonson.  The Effect of Purchase Quantity and Timing on Variety-Seeking Behavior , 1990 .

[2]  R. Dhar.  The Effect of Decision Strategy on Deciding to Defer Choice , 1996 .

[3]  M. Lepper,et al.  The Construction of Preference: When Choice Is Demotivating: Can One Desire Too Much of a Good Thing? , 2006 .

[4]  Valerie J. Trifts,et al.  Consumer Decision Making in Online Shopping Environments: The Effects of Interactive Decision Aids , 2000 .

[5]  Sean M. McNee,et al.  On the recommending of citations for research papers , 2002, CSCW '02.

[6]  I HerpenvanH.W.,et al.  The Variety of An Assortment : An Extension to the Attribute-Based Approach , 2002 .

[7]  Jonathan L. Herlocker,et al.  Evaluating collaborative filtering recommender systems , 2004, TOIS.

[8]  B. Schwartz.  The tyranny of choice. , 2004, Scientific American.

[9]  Sean M. McNee,et al.  Improving recommendation lists through topic diversification , 2005, WWW '05.

[10]  Sean M. McNee,et al.  Being accurate is not enough: how accuracy metrics have hurt recommender systems , 2006, CHI Extended Abstracts.

[11]  G. Wolford,et al.  Buying Behavior as a Function of Parametric Variation of Number of Choices , 2007, Psychological science.

[12]  K. Diehl,et al.  Great Expectations?! Assortment Size, Expectations, and Satisfaction , 2008 .

[13]  R. Hogarth,et al.  Satisfaction in choice as a function of the number of alternatives: When “goods satiate” , 2009 .

[14]  Bart P. Knijnenburg,et al.  Understanding the effect of adaptive preference elicitation methods on user satisfaction of a recommender system , 2009, RecSys '09.

[15]  R. Hertwig,et al.  Size, entropy, and density : What is the difference that makes the difference between small and large real-world assortments? , 2009 .

[16]  Bart P. Knijnenburg,et al.  User-Centric Evaluation Framework for Multimedia Recommender Systems , 2009, UCMedia.

[17]  G. Haynes,et al.  Testing the boundaries of the choice overload phenomenon: The effect of number of options and time pressure on decision difficulty and satisfaction , 2009 .

[18]  P. Todd,et al.  What Moderates the Too-Much-Choice Effect? , 2009 .

[19]  P. Todd,et al.  Can There Ever Be Too Many Options? A Meta-Analytic Review of Choice Overload , 2010 .

[20]  Bart P. Knijnenburg,et al.  Receiving Recommendations and Providing Feedback: The User-Experience of a Recommender System , 2010, EC-Web.