閲覧実績を用いたニュース記事の地域性抽出

抄録

News articles often deal with topics related to a specific location. Therefore, they are valuable when they are correctly delivered to users in the area, whereas wortheless for users in other areas. In this paper, we propose a method to detect such locality of a news article. This method learns a recurrent neural network using users' click logs rather than human annotated data. Experimental result shows the proposed method achieves better detection accuracy than a filtering method based on a place name in its text.