別カテゴリ商品提示による好みの明確化を促す推薦システム [in Japanese] Recommender System for Clarifying User's Preference by Showing Other Categories' Items [in Japanese]
Access this Article
The paper proposes a novel recommender system which supports users to clarify the most appropriate preference by recommending <I> other categories' items</I> that almost meet the attributes selected by users. Such an advantage is achieved by both the <I> preference ncretization</I> of users and the <I> preference change</I> of users.To investigate the effectiveness of the proposed system, we conducted the human-subject experiments and found that the proposed system supports users to find their desirable items by clarifying their preference. Concretely, the following implications have been revealed: (1) the proposed recommender system with both the <I>serendipity</I> and <I> decision</I> buttons enables users to clarify their preference by comparing items which are classified in different categories; (2) in detail, the item recommendation based on the <I> selected item attributes</I> contributes to clarifying the users' preference through a change of their preference, while the item recommendation based on the <I> item characteristic</I> contributes to clarifying the users' preference through a concretization of their preference; and (3) the proposed recommender system with the <I> decision</I> button succeeds the further clarification of the preference of users who have already clarified it.
- Transactions of the Japanese Society for Artificial Intelligence
Transactions of the Japanese Society for Artificial Intelligence 28(2), 210-219, 2013
The Japanese Society for Artificial Intelligence