情報処理学会 第78回全国大会講演要旨
5K-04
A Method of Temporal Feature Characterization with Application to Tourism Recommender Systems
In order to realize more intelligent context-aware recommender systems, we focus on the temporally variable features of objects and propose a method to characterize them as vectors for those objects. The
basic idea of the proposed method is: 1) to identify the vocabulary concerned with objects through Wikipedia; 2) to identify the trend over all objects through Twitter; and 3) to highlight the weight of words contained in each identified trend to obtain temporal feature vectors for each object.The effectiveness of the proposed method is evaluated by constructing a tourism recommender system.
basic idea of the proposed method is: 1) to identify the vocabulary concerned with objects through Wikipedia; 2) to identify the trend over all objects through Twitter; and 3) to highlight the weight of words contained in each identified trend to obtain temporal feature vectors for each object.The effectiveness of the proposed method is evaluated by constructing a tourism recommender system.
