The Development of a Search Engine for Academic Papers in Web

2011 Fiscal Year Final Research Report

• Project/Area Number: 21300095
• Research Category: Grant-in-Aid for Scientific Research (B)
• Allocation Type: Single-year Grants
• Section: 一般
• Research Field: Library and information science/Humanistic social informatics
• Research Institution: Keio University
• Principal Investigator: UEDA Shuichi 慶應義塾大学, 文学部, 教授 (50134218)
• Co-Investigator(Kenkyū-buntansha): AGATA Teru 亜細亜大学, 国際関係学部, 准教授 (80306505) ; EIKEUCHI Atsushi 筑波大学, 図書館情報メディア研究科, 准教授 (80338607)
• Co-Investigator(Renkei-kenkyūsha): ISHIDA Emi 九州大学, 附属図書館, 准教授 (50364815) ; NOZUE Michiko (財)鉄道総合技術研究所, その他部局等, 研究員 (40426044)
• Project Period (FY): 2009 – 2011
• Keywords: 学術論文 / 検索エンジン / ウェブ構造 / 情報検索 / 自動分類 / 機械学習

Research Abstract

Open access scientific papers available on the Web could be searched through several search engines. For example, Google scholar has higher coverage of literature, although it does not necessarily guarantee free access to full text. We have developed and evaluated the "Aletheia" search engine for full text academic papers. The system obtains PDF files on a broad range of topics and automatically detects academic papers using classifiers based on text and structure features. We have built PDF database collection containing 3 million Japanese PDF files, five types of Weka classifiers(AdaBoost, Decision Tree(C4. 5), Naive Bayes, Random Forest, and Support Vector Machine) were separately trained for 20, 000 test collection using 10-fold cross-validation to automatically detect academic papers. The features were generated using hand-built rules and consisted by the three types of features : structure, URL, and content.

Research Products

• [Journal Article] 深層ウェブの実態とその要因:機関リポジトリに登録された文献を用いた調査 (2012)
  • Author(s): 宮田洋輔, 安形輝, 池内淳, 石田栄美, 上田修一
  • Journal Title: 日本図書館情報学会誌 Volume: Vol.58, No.2
  • Peer Reviewed
• [Presentation] 学術論文の構成要素と構造宮田洋輔 (2012)
  • Author(s): 石田栄美, 池内淳, 安形輝, 上田修一
  • Organizer: 2012年度日本図書館情報学会春季研究集会
  • URL: http://web.keio.jp/～uedas/papers/webir121.pdf
  • Place of Presentation: 三重大学
  • Year and Date: 2012-05-12
• [Presentation] 学術論文に特化した検索エンジンの構築と評価 (2012)
  • Author(s): 石田栄美, 安形輝, 宮田洋輔, 池内淳, 上田修一
  • Organizer: 2012年度日本図書館情報学会春季研究集会
  • URL: http://web.keio.jp/～uedas/papers/webir122.pdf
  • Place of Presentation: 三重大学
  • Year and Date: 2012-05-12
• [Presentation] Detecting Academic Papers on the Web (2011)
  • Author(s): Emi Ishita, Teru Agata, Atsushi Ikeuchi, Yosuke Miyata, Shuichi Ueda
  • Organizer: JCDL11
  • URL: http://web.keio.jp/～uedas/papers/webir112.pdf
  • Place of Presentation: Ontario, Canada
  • Year and Date: 20110613-17
• [Presentation] 大規模日本語PDFファイル集合からの学術論文の自動判定 (2011)
  • Author(s): 石田栄美, 安形輝, 宮田洋輔, 池内淳, 上田修一
  • Organizer: 2011年度日本図書館情報学会春季研究集会
  • URL: http://web.keio.jp/～uedas/papers/webir111.pdf
  • Place of Presentation: 東京学芸大学
  • Year and Date: 2011-05-14
• [Presentation] The Deep Web in Institutional Repositories in Japan (2010)
  • Author(s): Teru Agata, Yosuke Miyata, Atsushi Ikeuchi, Shuichi Ueda
  • Organizer: ASIST 2010
  • Place of Presentation: Pittsburgh Pennsylvania, USA
  • Year and Date: 20101022-27
• [Presentation] 学術情報に特化した検索エンジンの開発:機械学習による英語論文の自動判定 (2010)
  • Author(s): 安形輝, 池内淳, 石田栄美, 宮田洋輔, 上田修一
  • Organizer: 2009年日本図書館情報学会研究大会発表要綱
  • Place of Presentation: 藤女子大学
  • Year and Date: 20101009-10
• [Presentation] A Search Engine for Japanese Academic Papers (2010)
  • Author(s): Emi Ishita, Teru Agata, Atsushi Ikeuchi, Michiko Nozue, Yosuke Miyata, Shuichi Ueda
  • Organizer: JCDL 2010
  • Place of Presentation: Gold Coast Queensland, Australia
  • Year and Date: 20100621-25
• [Presentation] 学術論文PDFの自動判定:学習用集合が判定性能に与える影響 (2010)
  • Author(s): 宮田洋輔, 安形輝, 池内淳, 石田栄美, 上田修一
  • Organizer: 2010年度日本図書館情報学会春季研究集会
  • Place of Presentation: 同志社大学
  • Year and Date: 2010-05-29
• [Presentation] Analyzing OPAC Use with Screen Views and Eye Tracking (2009)
  • Author(s): Ishita, Emi, Mine, Shinji ; Koizumi, Masanori ; Miyata, Yosuke ; Kunimoto, Chihiro ; Shiozaki, Junko ; Kurata, Keiko ; Ueda, Shuichi
  • Organizer: ACM/IEEE Joint Conference on Digital libraries : Designing tomorrow, preserving the past-today(JCDL09)
  • Place of Presentation: University of Texas
  • Year and Date: 20090615-19
• [Presentation] 学術情報流通における深層ウェブの実態-機関リポジトリに登録された文献を用いた調査 (2009)
  • Author(s): 安形輝, 宮田洋輔, 池内淳, 上田修一
  • Organizer: 2009年度三田図書館・情報学会研究大会発表論文集
  • Place of Presentation: 慶應義塾大学
  • Year and Date: 2009-09-26