05月25日(Thu) 15:50〜17:30 G会場(ウインクあいち-9F 906会議室)
| 演題番号 | 3G2-1 |
|---|---|
| 題目 | 閲覧実績を用いたニュース記事の地域性抽出 |
| 著者 | 大倉 俊平(ヤフー株式会社 データ＆サイエンス統括本部) |
| 時間 | 05月25日(Thu) 15:50〜16:10 |
| 概要 | News articles often deal with topics related to a speci c 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 ltering method based on a place name in its text. |
| 論文 | PDFファイル |