A Study on Information Alignment by Composite Generative Model

• Project/Area Number: 23300040
• Research Category: Grant-in-Aid for Scientific Research (B)
• Allocation Type: Single-year Grants
• Section: 一般
• Research Field: Media informatics/Database
• Research Institution: National Institute of Informatics
• Principal Investigator: TAKASU Atsuhiro 国立情報学研究所, コンテンツ科学研究系, 教授 (90216648)
• Co-Investigator(Kenkyū-buntansha): MASADA Tomonari 長崎大学, 工学研究科, 准教授 (60413928)
• Co-Investigator(Renkei-kenkyūsha): FUKAGAWA Daiji 同志社大学, 文化情報学部, 助教 (10442518)
• Project Period (FY): 2011-04-01 – 2015-03-31
• Project Status: Completed (Fiscal Year 2014)
• Budget Amount: ¥19,890,000 (Direct Cost: ¥15,300,000、Indirect Cost: ¥4,590,000); Fiscal Year 2013: ¥6,500,000 (Direct Cost: ¥5,000,000、Indirect Cost: ¥1,500,000); Fiscal Year 2012: ¥6,240,000 (Direct Cost: ¥4,800,000、Indirect Cost: ¥1,440,000); Fiscal Year 2011: ¥7,150,000 (Direct Cost: ¥5,500,000、Indirect Cost: ¥1,650,000)
• Keywords: トピックモデル / 情報推薦 / 機械学習 / テキストマイニング / 潜在トピックモデル / 情報統合 / 情報検索 / 確率モデル

Outline of Final Research Achievements

The purpose of this study is to develop topic models for analyzing information in various aspects. We first develop a topic model for handling time as well as text, where we add timestamps to each document. The model generates both text and timestamps simultaneously. Next we extend the model to treat networked documents where documents are linked each other like citations of academic papers. We apply the models to researcher recommendation systems and empirically show that features extracted by the models are effective for recommendation.

Research Products

• [Journal Article] Steering Time-Dependent Estimation of Posteriors with Hyperparameter Indexing in Bayesian Topic Models (2011)
  • Author(s): Tomonari Masada, Atsuhiro Takasu, Yuichiro Shibata, Kiyoshi Oguri
  • Journal Title: Advances in Knowledge Discovery and Data Mining, Lecture Note in Artificial Intelligence Volume: 6634 Pages: 435-447
  • DOI: 10.1007/978-3-642-20841-6_36
  • NAID: 120006985071
  • ISBN: 9783642208409, 9783642208416
  • Peer Reviewed
• [Journal Article] Semi-supervised Bibliographic Element Segmentation with Latent Permutations (2011)
  • Author(s): Tomonari Masada, Atsuhiro Takasu, Yuichiro Shibata, Kiyoshi Oguri
  • Journal Title: Digital Libraries: For Cultural Heritage, Knowledge Dissemination, and Future Creation, Lecture Note in Computer Science Volume: 7008 Pages: 60-69
  • DOI: 10.1007/978-3-642-24826-9_11
  • NAID: 120006985230
  • ISBN: 9783642248252, 9783642248269
  • Peer Reviewed
• [Presentation] Collaborator Recommendation for Isolated Researchers (2014)
  • Author(s): Tin Huynh, Atsuhiro Takasu, Tomonari Masada, Kiem Hoang
  • Organizer: The 7th International Symposium on Mining and Web (MAW14)
  • Place of Presentation: Victoria, Canada
  • Year and Date: 2014-05-13 – 2014-05-16
• [Presentation] Empirical Evaluation of CRF-Based Bibliography Extraction from Reference Strings (2014)
  • Author(s): Manabu Ohta, Daiki Arauchi, Atsuhiro Takasu, Jun Adachi
  • Organizer: IAPR International Workshop on Document Analysis Systems (DAS 2014)
  • Place of Presentation: Tours, France
  • Year and Date: 2014-04-07 – 2014-04-10
• [Presentation] Latent Probabilistic Model for Context-Aware Recommendations (2013)
  • Author(s): Padipat Sitkrongwong, Saranya Maneeroj, Atsuhiro Takasu
  • Organizer: IEEE/WIC/ACM International Conferences on Web Intelligence (WI2013)
  • Place of Presentation: Atlanta, GA, USA
  • Year and Date: 2013-11-17 – 2013-11-20
• [Presentation] Rating Pattern Formation for Better Recommendation (2013)
  • Author(s): Warat Chalermpornpong, Saranya Maneeroj, Atsuhiro Takasu
  • Organizer: DEXA Workshop on Recommender Systems meet Databases (rsmd2013)
  • Place of Presentation: Prague, Czech
  • Year and Date: 2013-08-26 – 2013-08-30
• [Presentation] Bayesian Model for a Multicriteria Recommender System with Support Vector Regression (2013)
  • Author(s): Pannawit Samatthiyadikun, Atsuhiro Takasu, Saranya Maneeroj
  • Organizer: IEEE International Conference on Information Reuse and Integration (IEEE IRI 2013)
  • Place of Presentation: San Fransisco, CA, USA
  • Year and Date: 2013-08-14 – 2013-08-16
• [Presentation] Extended Bayesian Model for Multi-criteria Recommender System (2013)
  • Author(s): Pannawit Samatthiyadikun, Atsuhiro Takasu
  • Organizer: 情報基礎とアクセス技術研究会
  • Place of Presentation: 宮崎JA-AZMホール、宮崎市
• [Presentation] Bayesian Model for a Multicriteria Recommender System with Support Vector Regression (2013)
  • Author(s): Pannawit Samatthiyadikun, Atsuhiro Takasu, Saranya Maneeroj
  • Organizer: IEEE International Conference on Information Reuse and Integration (IEEE IRI 2013)
  • Place of Presentation: San Francisco, USA
• [Presentation] Multicriteria Collaborative Filtering by Bayesian Saranya Maneeroj-based User Profiling (2012)
  • Author(s): Pannawit Samatthiyadikun, Atsuhiro Takasu,
  • Organizer: 13th International Conference on Information Reuse and Integration
  • Place of Presentation: Las Vegas, USA
• [Presentation] Extraction of Topic Evolutions from References in Scientific Articles and Its GPU Acceleration (2012)
  • Author(s): Tomonari Masada, Atsuhiro Takasu
  • Organizer: 21st ACM Conference on Information and Knowledge Management
  • Place of Presentation: Maui, Hawaii, USA
• [Presentation] A Multicriteria Recommendation Method for Data with Missing Rating Scores (2011)
  • Author(s): Atsuhiro Takasu
  • Organizer: International Conference on Data and Knowledge Engineering (ICDKE 2011)
  • Place of Presentation: Milan, Italy