Comprehensive research on content analysis and semi-automated content analysis for human values in texts

• Project/Area Number: 18H03495
• Research Category: Grant-in-Aid for Scientific Research (B)
• Allocation Type: Single-year Grants
• Section: 一般
• Review Section: Basic Section 90020:Library and information science, humanistic and social informatics-related
• Research Institution: Kyushu University
• Principal Investigator: Ishita Emi 九州大学, データ駆動イノベーション推進本部, 教授 (50364815)
• Co-Investigator(Kenkyū-buntansha): 冨浦 洋一 九州大学, システム情報科学研究院, 教授 (10217523) ; 福田 悟志 中央大学, 理工学部, 助教 (10817555) ; 大賀 哲 九州大学, 法学研究院, 准教授 (90445718)
• Project Period (FY): 2018-04-01 – 2022-03-31
• Project Status: Completed (Fiscal Year 2022)
• Budget Amount: ¥15,600,000 (Direct Cost: ¥12,000,000、Indirect Cost: ¥3,600,000); Fiscal Year 2021: ¥3,250,000 (Direct Cost: ¥2,500,000、Indirect Cost: ¥750,000); Fiscal Year 2020: ¥3,770,000 (Direct Cost: ¥2,900,000、Indirect Cost: ¥870,000); Fiscal Year 2019: ¥4,030,000 (Direct Cost: ¥3,100,000、Indirect Cost: ¥930,000); Fiscal Year 2018: ¥4,550,000 (Direct Cost: ¥3,500,000、Indirect Cost: ¥1,050,000)
• Keywords: 内容分析 / 自動分類 / 人の価値観 / 原発事故 / コーディングの質向上 / バンデットアルゴリズム / 効果的な学習用集合の分析 / 効率的な学習用集合の分析 / 価値観フレームの構築支援 / 内容分析の半自動化 / 分類器の適用

Outline of Final Research Achievements

To develop a semi-automatic content analysis of human values appearing in newspaper editorials related to the nuclear power plant disaster, we divided the content analysis into three stages and proposed to use a classifier for each stage. Manual coding results were used to train the classifiers for the content analysis. We developed a method for efficiently improving the quality of the manual coding results. We also developed a method for selecting training data for classifiers efficiently. Finally, we studied methods to find new human value categories.

Academic Significance and Societal Importance of the Research Achievements

質的な研究手法である内容分析に対して、内容分析の質を極力落とさずに、できるだけ自動的な手法を取り入れ、人の労力を減らすためのアプローチ、手法の開発・提案に取り組んだ。主に、内容分析を3ステージに分け、それぞれに分類器を用いる半自動化の方法の提案、分類器に必要な質の高いデータを効率的に構築する手法、分類器が効率的に学習するための学習用データの選択手法等を開発することで、内容分析の効率化に貢献したといえる。

Research Products

• [Int'l Joint Research] メリーランド大学(米国)
• [Int'l Joint Research] University of Maryland, College Park(米国)
• [Int'l Joint Research] University of Maryland, College Park/University of Texas, Austin(米国)
• [Int'l Joint Research] University of Maryland/University of Texas, Austin(米国)
• [Int'l Joint Research] National Sun Yat-sen University(台湾)
• [Journal Article] Automating the Choice Between Single or Dual Annotation for Classifier Training (2021)
  • Author(s): Satoshi Fukuda, Emi Ishita, Yoichi Tomiura, Douglas W. Oard
  • Journal Title: Proceedings of the 23rd International Conference on Asia-Pacific Digital Libraries (ICADL 2021)( Lecture Notes in Computer Science) Volume: 13133 Pages: 233-248
  • DOI: 10.1007/978-3-030-91669-5_19
  • ISBN: 9783030916688, 9783030916695
  • Peer Reviewed / Int'l Joint Research
• [Journal Article] Using text classification to improve annotation quality by improving annotator consistency (2020)
  • Author(s): Emi Ishita, Satoshi Fukuda, Yoichi Tomiura, Douglas W. Oard
  • Journal Title: Proceedings of the Association for Information Science and Technology Volume: 57 Issue: 1
  • DOI: 10.1002/pra2.301
  • NAID: 120007174659
  • Peer Reviewed / Int'l Joint Research
• [Journal Article] Cost-effective learning for classifying human values (2020)
  • Author(s): Ishita, Emi; Fukuda, Satoshi; Oga, Toru; Tomiura, Yoichi; Oard, Douglas W.; Fleischmann, Kenneth R.
  • Journal Title: Proceedings of iConference 2020 Volume: 2020
  • NAID: 120007053150
  • Peer Reviewed / Open Access / Int'l Joint Research
• [Journal Article] Content Analysis of Library Use on Microblog: Pre-coding Results. (2019)
  • Author(s): Kodama, Mei; Abe, Kaori; Fukushima, Kana; Hayashi, Eri; Hua, Zhiyi; Jiang, Min; Kang, Ping; Nishida, Emi; Sakai, Shinji; Tomiura, Yoichi; Watanabe, Yukiko; Ishita, Emi;
  • Journal Title: Proceedings of the 9th Asia-Pacific Conference on Library & Library Education and Practice (A-LIEP 2019) Volume: 2019 Pages: 423-428
  • Peer Reviewed / Open Access
• [Journal Article] Toward Three-Stage Automation of Annotation for Human Values (2019)
  • Author(s): Emi Ishita, Satoshi Fukuda, Toru Oga, Douglas W. Oard, Kenneth R. Fleischmann, Yoichi Tomiura, An-Shou Cheng
  • Journal Title: Proceedings of 14th iConference 2019 (Lecture Notes in Computer Science) Volume: 11420 Pages: 188-199
  • DOI: 10.1007/978-3-030-15742-5_18
  • ISBN: 9783030157418, 9783030157425
  • Peer Reviewed / Int'l Joint Research
• [Presentation] 新たな価値観ラベルの発見に対する支援方法の検討 (2023)
  • Author(s): 福田悟志, 石田栄美
  • Organizer: 言語処理学会第29回年次大会
• [Presentation] 価値観ラベルに対するトピック分析とラベル間の関係分析 (2023)
  • Author(s): 福田悟志, 石田栄美
  • Organizer: 情報処理学会 第149回 情報基礎とアクセス技術研究発表会
• [Presentation] 原発事故における「責任」言説の変容―毎日新聞社説を事例として (2019)
  • Author(s): 大賀哲
  • Organizer: 政治社会学会研究大会
• [Presentation] 福島原発事故をめぐる「危機」と「責任」に関するメディア言説の分析―『朝日新聞』の社説を事例として (2019)
  • Author(s): 山腰修三、三谷文榮
  • Organizer: 政治社会学会研究大会
• [Presentation] 福島原発事故をめぐる「危機」と「責任」をめぐるメディア言説の分析―読売新聞社説を事例として (2019)
  • Author(s): 加藤朋江
  • Organizer: 政治社会学会研究大会
• [Presentation] Developing Semi-Automatic Content Analysis for Studying Human Values in the Nuclear Power Debate (2018)
  • Author(s): Emi Ishita, Toru Oga, Satoshi Fukuda, Yoichi Tomiura
  • Organizer: 10th Asia Library and Information Research Group Workshop (ALIRG2018)
  • Int'l Joint Research