Kyushu University Academic Staff Educational and Research Activities Database
Researcher information (To researchers) Need Help? How to update
Emi Ishita Last modified date:2019.07.01

Associate Professor / Library


Graduate School
Other Organization


Academic Degree
Ph.D in of Information Science
Country of degree conferring institution (Overseas)
No
Field of Specialization
Library and Information Science, Text Classification, Computational Social Science,
Total Priod of education and research career in the foreign country
00years00months
Research
Research Interests
  • Semi-automatic content analysis for human values
    keyword : Human values, Automated content analysis, Categorization,
    2018.04.
  • Development of research platform and open data for digital humanities
    keyword : Digital humanities, open data, open science, research platform
    2015.10~2017.03.
  • Automatic classification of human values
    keyword : human values, automatic classification
    2013.04~2017.03.
  • Non-topical text classification
    keyword : Non-topical text classification
    2010.04~2013.03.
Academic Activities
Papers
1. Emi Ishita, Satoshi Fukuda, Toru Oga, Douglas W. Oard, Kenneth R. Fleischmann, Yoichi Tomiura, An Shou Cheng, Toward Three-Stage Automation of Annotation for Human Values, 14th International Conference on Information in Contemporary Society, iConference 2019 Information in Contemporary Society - 14th International Conference, iConference 2019, Proceedings, 10.1007/978-3-030-15742-5_18, 188-199, 2019.01, Prior work on automated annotation of human values has sought to train text classification techniques to label text spans with labels that reflect specific human values such as freedom, justice, or safety. This confounds three tasks: (1) selecting the documents to be labeled, (2) selecting the text spans that express or reflect human values, and (3) assigning labels to those spans. This paper proposes a three-stage model in which separate systems can be optimally trained for each of the three stages. Experiments from the first stage, document selection, indicate that annotation diversity trumps annotation quality, suggesting that when multiple annotators are available, the traditional practice of adjudicating conflicting annotations of the same documents is not as cost effective as an alternative in which each annotator labels different documents. Preliminary results for the second stage, selecting value sentences, indicate that high recall (94%) can be achieved on that task with levels of precision (above 80%) that seem suitable for use as part of a multi-stage annotation pipeline. The annotations created for these experiments are being made freely available, and the content that was annotated is available from commercial sources at modest cost..
2. Emi Ishita, Toru Oga, Yasuhiro Takayama, An-Shou Cheng, Douglas W. Oard, Kenneth Fleischmann, Yoichi Tomiura., Toward automating detection of human values in the nuclear power debate, Proceedings of the Association for Information Science and Technology, 10.1002/pra2.2017.14505401127, 54, 1, 714-715, 2017.11, This paper describes the creation of a corpus of newspaper articles about the Fukushima nuclear disaster, a coding frame for content analysis of human values expressed or reflected in that corpus and preliminary results for automation of the content analysis. Understanding the human values that motivate sentiment towards an idea can help to characterize the basis for that sentiment, and this work is a first step toward applying that approach to positions on controversial events reported in the news.
原発に関する新聞記事に人の価値観を付与したテストコレクションを構築した。その後、それらを用いて自動コーディングを試み、コーディングの自動化の可能性について検討した。.
3. Emi Ishita, Yosuke Miyata, Shuichi Ueda, Keiko Kurata, A Structural Equation Model of Information Retrieval Skills, Proceedings of the 2017 Conference on Conference Human Information Interaction and Retrieval (CHIIR'2017), 317-320, 2017.03.
4. Emi Ishita, Tetsuya Nakatoh, Kohei Hatano, Michiaki TAKAYAMA, An Attempt to Promote Open Data for Digital Humanities in Japanese University Libraries, Proceedings of the 18th International Conference on Asia-Pacific Digital Libraries (ICADL 2016), 10.1007/978-3-319-49304-6_32, LNCS 10075, 269-274, 2016.12, Many universities have declared open access policies in response to increasing interest in open access in the academic world. The next developments will be focused on open data. Huge data repositories are already used in specific fields. However, the discussion regarding open data in universities has just begun. We attempted to promote open data for digital humanities in a university library. University libraries hold rare collections, which are generally highly valued research resources. We selected a rare collection in a library, and then digitized and published it. We investigated additional data that aids a reader’s understanding of the material. To promote the open data, we produced images of the resources and multiple types of interpretation texts. We displayed the digital images in an exhibition and obtained an evaluation using a survey of visitors.
デジタルヒューマニティーズのためのオープンデータを促進するために、日本の大学図書館において貴重資料を電子化し、促進のためのデジタル展示を試みたことを報告した。.
5. Emi Ishita, Yukiko Watanabe, Naoya Mitani, Miki Horiuchi, Yuiko Higa, Takako Oda, Ai Yamaguchi, Citation Analysis of the Availability of Conference Proceedings Cited in Doctoral Dissertations, The 5th International Conference on Asia-Pacific Library and Information Education and Practice (A-LIEP2013), 272-282, 2013.07.
6. Emi Ishita, Douglas W. Oard, Kenneth R. Fleischmann, An-Shou Cheng and Thomas Clay Templeton, Investigating Multi-Label Classification for Human Values, Proceedings of the American Society for Information Science and Technology(ASIST2010), 47, 1, 1-4, 2010.10.
Membership in Academic Society
  • ACM SIGIR
  • Information Processing Society of Japan
  • Mita Society for Library and Information Science
  • The Japan Society of Library and Information Science