徐 銘蔓
首都大学東京 / 情報通信システム
逐次推薦状況におけるプロービングアイテ決定戦略に関する研究
This paper compares several strategies for determining probing items. Probing items are presented to users especially at their sign-up process to get their feedback, from which user profiles are constructed. Therefore, how to select probing items are important for designing recommender systems. This paper reports the results of comparing several strategies by simulating user behaviors using a dataset.