also like to look at the album cover This often serves as a decide if they should act upon the systems visual reminder for any previous experience with the item recommendations(e. g, buy /download the music, read the (e.g, they had seen that album in the store or at a friends book or watch the movie)? Two factors emerged as strongly Exper and Commmity Ratings: Reviews and ratings by items and transparency of system logic. indicated that ratings and reviews by other users helped them The Advantages and Disadvantages of Familiar ig. 5: Useful Recs. for Both Versions of RatingZone(From Study Recommender systems differ in the proportions of Useful commendations that have been previously experienced by Recommendatio users. For some systems, a large proportion of recommended items are familiar to the user, while other systems 30 recommend mostly unfamiliar items. For example, 72% of Amazons, 60% of Media s, and 45% of MoodLogic's recommendations were familiar( Study 2) Users like and prefer to buy previously familiar recommendations: In our first study we found preliminary Version 1: Without Version 2: With dications that the presence Descnption Description enforces trust in the recommender system We examined this issue in greater depth in Study 2, and found that mean in their decision-making In Study 2, 75% of the users indicated that community ratings in Amazon were helpful in Figure 6: Mean Liking for Familiar Not deciding whether to trust the recommendations (From Study 2) naking up their minds about the recommended songs. In the case of Song Explorer, one of the reasons users were dissatisfied with the system was that it was difficult to find the audio clip "Of limited use, because no description of the Red dots predicted ratings] don't tell me anything Amazon Cdnow Media want to know what the movie' s about. Comment about Unbound Movie Critic) ."I liked seeing cover of box in initial list of result. The liking for familiar recommendations was higher than that for nage helps. ( Comment about Amazon) unfamiliar recommendations(Figure 6). The pairwise differences were significant for all systems except for Design Suggestion: We recommend providing clear paths to CDNow [all ts'>1.8; all ps <051 detailed item information, validated through user testing. Familiar items appear to play a crucial role in establishing Simple changes to the navigational structure can have a large trust in the system. Previous positive experience with a impact on user satisfaction If the designer does not have recommended item increases trust in the system while access to lots of detailed item information(e.g. reviews by previous negative experience causes trust in the system to itics, plot synopses), offering some kind of a community forum for users to post comments can be a relatively easy decrease. Most of our users agreed that the inclusion of previously liked items in the recommendation set icreased ay to dramatically increase the system' s efficacy ted in buying, downloading for free, or bookmarking THE GESTALT VIEW: WHAT MAKES GOOD RECOMMENDER SYSTEMS? a recommended item. Figure 7 shows that users expressed greater willingness to buy familiar than unfamiliar Earlier we identified specific aspects of the interface that can recommended items(Note: Error Bars in figure represent affect the success of recommender systems we focused standard errors). Most(70%)of the items that users upon mostly concrete dimensions of the user's interaction expressed an interest in buying were familiar items. This akes sense since a familiar item is a less risky purcha scales and recommendations. Next, we consider more decision. Does too much familiarity breed contempt? While users did work. What leads to trust in a systems recommendations, show a preference for familiar items, they did not like and what kind of systems do users prefer? How do users recommendations that were too directly related to their inputalso like to look at the album cover. This often serves as a visual reminder for any previous experience with the item (e.g., they had seen that album in the store or at a friend’s house). Expert and Community Ratings: Reviews and ratings by other users seemed to be especially important. Several users indicated that ratings and reviews by other users helped them in their decision-making. In Study 2, 75% of the users indicated that community ratings in Amazon were helpful in deciding whether to trust the recommendations. Item Sample:Users indicated that this was very helpful in making up their minds about the recommended songs. In the case of SongExplorer, one of the reasons users were dissatisfied with the system was that it was difficult to find the audio clip. · “Of limited use, because no description of the books.”(Comment about RatingZone, Version 1) · “Red dots [Predicted ratings] don't tell me anything. I want to know what the movie's about.”(Comment about MovieCritic) · “I liked seeing cover of box in initial list of result… The image helps.”(Comment about Amazon) Design Suggestion: We recommend providing clear paths to detailed item information, validated through user testing. Simple changes to the navigational structure can have a large impact on user satisfaction. If the designer does not have access to lots of detailed item information (e.g. reviews by critics, plot synopses), offering some kind of a community forum for users to post comments can be a relatively easy way to dramatically increase the system’s efficacy. 3) THE GESTALT VIEW: WHAT MAKES GOOD RECOMMENDER SYSTEMS? Earlier we identified specific aspects of the interface that can affect the success of recommender systems. We focused upon mostly concrete dimensions of the user’s interaction with the system: number of input items required, rating scales and recommendations. Next, we consider more holistic questions about what makes recommender systems work. What leads to trust in a system’s recommendations, and what kind of systems do users prefer? How do users decide if they should act upon the system’s recommendations (e.g., buy / download the music, read the book or watch the movie)? Two factors emerged as strongly affecting levels of user trust: familiarity with recommended items and transparency of system logic. The Advantages and Disadvantages of Familiar Recommendations Recommender systems differ in the proportions of recommendations that have been previously experienced by users. For some systems, a large proportion of recommended items are familiar to the user, while other systems recommend mostly unfamiliar items. For example, 72% of Amazon’s, 60% of MediaUnbound’s, and 45% of MoodLogic’s recommendations were familiar (Study 2). Users like and prefer to buy previously familiar recommendations: In our first study we found preliminary indications that the presence of already-known items reinforces trust in the recommender system. We examined this issue in greater depth in Study 2, and found that mean liking for familiar recommendations was higher than that for unfamiliar recommendations (Figure 6). The pairwise differences were significant for all systems except for CDNow [all ts’ > 1.8; all p’s <.05]. Familiar items appear to play a crucial role in establishing trust in the system. Previous positive experience with a recommended item increases trust in the system while previous negative experience causes trust in the system to decrease. Most of our users agreed that the inclusion of previously liked items in the recommendation set increased their trust. We also asked users whether they would be interested in buying, downloading for free, or bookmarking a recommended item. Figure 7 shows that users expressed greater willingness to buy familiar than unfamiliar recommended items (Note: Error Bars in figure represent standard errors). Most (70%) of the items that users expressed an interest in buying were familiar items. This makes sense since a familiar item is a less risky purchase decision. Does too much familiarity breed contempt? While users did show a preference for familiar items, they did not like recommendations that were too directly related to their input Fig. 5: % Useful Recs. for Both Versions of RatingZone (From Study 2) 0 5 10 15 20 25 30 35 40 45 Version 1: Without Description Version 2: With Description % Useful Recommendations % Useful Recommendations Figure 6: Mean Liking for Familiar & Not Familiar Recommendations (From Study 2) 0 1 2 3 4 5 Amazon Cdnow Media Unbound Mood Logic Song Explorer Mean Liking Unfamiliar Familiar