Topic Models Considering the Meteorological Context and Users' Preference

• Item type: International Conference(1)
• 公開日: 2016-09-27
• タイトル: Topic Models Considering the Meteorological Context and Users' Preference
• タイトル / 言語: en
• タイトル: Topic Models Considering the Meteorological Context and Users' Preference
• 言語: eng
• キーワード / 主題Scheme: Other
• キーワード / 主題: Poster and Demo
• 資源タイプ / 資源タイプ識別子: http://purl.org/coar/resource_type/c_5794
• 資源タイプ: conference paper
• 著者所属: The University of Tokyo
• 著者所属: NTT DOCOMO, Inc.
• 著者所属: China University of Petroleum
• 著者所属: The University of Tokyo
• 著者所属(英): en
• 著者所属(英): The University of Tokyo
• 著者所属(英): en
• 著者所属(英): NTT DOCOMO, Inc.
• 著者所属(英): en
• 著者所属(英): China University of Petroleum
• 著者所属(英): en
• 著者所属(英): The University of Tokyo
• 著者名: Taku, Ito; Yusuke, Fukazawa; Dandan, Zhu; Jun, Ota
• 著者名(英): Taku, Ito; Yusuke, Fukazawa; Dandan, Zhu; Jun, Ota
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: In this paper, we focus on the weather and seasonal contexts, and we proposed topic models considering the weather /seasonal contexts and users' preference. We compare two topic models. One is a model not considering users' preference, and the other is a model considering it. By evaluating models from view point of word prediction performance (Perplexity), we discovered the importance of topics associated with users' preference.
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: In this paper, we focus on the weather and seasonal contexts, and we proposed topic models considering the weather /seasonal contexts and users' preference. We compare two topic models. One is a model not considering users' preference, and the other is a model considering it. By evaluating models from view point of word prediction performance (Perplexity), we discovered the importance of topics associated with users' preference.
• 書誌情報: Proceedings of The Ninth International Conference on Mobile Computing and Ubiquitous Networking; 巻 2016, 号 3, p. 1-2, 発行日 2016-09-27
• 出版者 / 言語: ja
• 出版者: 情報処理学会