whose names it input into the system. As noted above Figure 7: Action towards Familiar and Unfamiliar 口 Unfamiliar several of our users complained about this aspect while 兽100 emendation(From Study2囗 Familiar ing Amazon. com. On the other hand, a user wh seeking "more like this" recommendations may feel 后80% thwarted by a system that does not return items similar to the nes he or she rates highly during the input step E40% System Transparency We were interested in exploring whether users perceive Bookmark No action recommender system logic to be transparent, or whether they /Download for feel that they lack insight into why an item has been recommended. Is perceived transparency related to a greater ratings. For example, many of our users were frustrated by likingfor the systems recommendations? Results showed that users perceived systems to be very different on Amazon s recommendations that were albums by the same ransparency. For Amazon, users thought they understood artists that the users had input into the system. "Theyre just system logic %2%o of the time, for MediaUnbound 76%of going to give me things with this guy [same artist he the time, and for MoodLogic 67% of the time( Study 2) named? one user commented. So while amazon Also users liked transparent recommendations more than not recommendations might remind users about a favorite song not heard recently, they did not help users expand their tastes ransparent recommendations(Figure &)for all five systems in new directions. This perception was also reflected in the Mean liking was significantly higher for transparent than mean useful ratings for various music systems. Users in our Figure 8: Mean Liking for Transparent study thought that MediaUnbound was a more useful system and Non Transparent than amazon because it introduced them to new items the Recommendation 口 Not Transpare hked and thereby allowed them to broaden their musical from Study 2) Design Suggestion: A recommender system needs to understand user needs with relation to familiarity. Users differ in the degree of familiarity they want from their recommendations. The system might ask users about how familiar they would like their recommendation set to be Amazon Cdnow Media Mood Song This would help systems cater to user needs more Unbound Logic Explorer ffectively. MediaUnbound, for examp des a slider From Study 2: Analysis of Music Recommender Systems bar for users to indicate how familiar the music suggested should be. during the evaluation session, users state non-transparent recommendations for all systems except that they liked this option CDNow all ts>1.7; all ps<.05. Furthermore, users more Our investigation into the effects of item familiarity on user equently indicated they would acquire a transparent satisfaction led us to some broader conclusions about rs recommendation(by buying or downloading it)than for a design. We observed that two users with the same musical not transparent recommendation ( see Figure 9) tastes often differ widely in what they expect and need from Figure 9: Action towards Transparent a recommender system. The range of user recommendation and Not Transparent Rec 囗 Not Transparent needs we have identified includes n120% From study 2) Reminder recommendations, mostly from within the same genre("I was planning to read this anyway, it's my typical kind of item) More like this"recommendations, from within genre, 20% similar to a particular item(I am in the mood for a 0% movie similar to GoodFellas) -20% New items, within a particular genre, just released, that /Download for y/their friends do not know about Broaden my horizon recommendations(might be Design Suggestions: This is an important finding from the from other genres) perspective of system designers. A good CF algorithm tha A user who is looking to discover new music might be generates accurate recommendations is not enough to frustrated by a system that keeps I nding artists constitute a useful system from the users' perspective. Theratings. For example, many of our users were frustrated by Amazon’s recommendations that were albums by the same artists that the users had input into the system. “They’re just going to give me things with this guy [same artist he named]?” one user commented. So while Amazon recommendations might remind users about a favorite song not heard recently, they did not help users expand their tastes in new directions. This perception was also reflected in the mean useful ratings for various music systems. Users in our study thought that MediaUnbound was a more useful system than Amazon because it introduced them to new items they liked and thereby allowed them to broaden their musical tastes. Design Suggestion: A recommender system needs to understand user needs with relation to familiarity. Users differ in the degree of familiarity they want from their recommendations. The system might ask users about how familiar they would like their recommendation set to be. This would help systems cater to user needs more effectively. MediaUnbound, for example, includes a slider bar for users to indicate how familiar the music suggested should be. During the evaluation session, several users stated that they liked this option. Our investigation into the effects of item familiarity on user satisfaction led us to some broader conclusions about RS design. We observed that two users with the same musical tastes often differ widely in what they expect and need from a recommender system. The range of user recommendation needs we have identified includes: · Reminder recommendations, mostly from within the same genre (“I was planning to read this anyway, it’s my typical kind of item”) · “More like this” recommendations, from within genre, similar to a particular item (“I am in the mood for a movie similar to GoodFellas”) · New items, within a particular genre, just released, that they / their friends do not know about · “Broaden my horizon” recommendations (might be from other genres) A user who is looking to discover new music might be frustrated by a system that keeps recommending artists whose names it input into the system. As noted above, several of our users complained about this aspect while using Amazon.com. On the other hand, a user who is seeking “more like this” recommendations may feel thwarted by a system that does not return items similar to the ones he or she rates highly during the input step. System Transparency We were interested in exploring whether users perceive recommender system logic to be transparent, or whether they feel that they lack insight into why an item has been recommended. Is perceived transparency related to a greater liking for the system’s recommendations? Results showed that users perceived systems to be very different on transparency. For Amazon, users thought they understood system logic 92% of the time, for MediaUnbound 76% of the time, and for MoodLogic 67% of the time (Study 2). Also users liked transparent recommendations more than not transparent recommendations (Figure 8) for all five systems. Mean liking was significantly higher for transparent than non-transparent recommendations for all systems except CDNow [all t’s > 1.7; all p’s<.05]. Furthermore, users more frequently indicated they would acquire a transparent recommendation (by buying or downloading it) than for a not transparent recommendation. (see Figure 9). Design Suggestions: This is an important finding from the perspective of system designers. A good CF algorithm that generates accurate recommendations is not enough to constitute a useful system from the users’ perspective. The Figure 7: Action towards Familiar and Unfamiliar Recommendation (From Study 2) 0% 20% 40% 60% 80% 100% Bookmark /Download for free Buy it No action % Recommendations Unfamiliar Familiar Figure 8: Mean Liking for Transparent and Non Transparent Recommendations (from Study 2) 0 1 2 3 4 5 Amazon Cdnow Media Unbound Mood Logic Song Explorer Mean Liking Not Transparent Transparent From Study 2: Analysis of Music Recommender Systems Figure 9: Action towards Transparent and Not Transparent Recs. (From Study 2) -20% 0% 20% 40% 60% 80% 100% 120% Bookmark /Download for free % Recommendations Buy it No action Not Transparent Transparent