2020 Fiscal Year Final Research Report
Analysis of lifestyle and health texts on the WWW consisting of text and numeric data.
Project/Area Number |
18K11549
|
Research Category |
Grant-in-Aid for Scientific Research (C)
|
Allocation Type | Multi-year Fund |
Section | 一般 |
Review Section |
Basic Section 62020:Web informatics and service informatics-related
|
Research Institution | The University of Tokushima |
Principal Investigator |
YOSHIDA Minoru 徳島大学, 大学院社会産業理工学研究部(理工学域), 講師 (40361688)
|
Co-Investigator(Kenkyū-buntansha) |
北 研二 徳島大学, 大学院社会産業理工学研究部(理工学域), 教授 (10243734)
松本 和幸 徳島大学, 大学院社会産業理工学研究部(理工学域), 准教授 (90509754)
|
Project Period (FY) |
2018-04-01 – 2021-03-31
|
Keywords | テキスト中の数値表現 / 健康情報検索 |
Outline of Final Research Achievements |
We investigated the relations between numerical information and linguistic expressions and proposed a method to convert numeric data into linguistic expressions that can contribute to accessing the scientific documents about healthcare. We considered two situations: one is the case where the numeric data were provided in text, and the other is the case where they were provided as metadata, e.g., the posting time of tweets. We also developed the data sets that consist of (text, image) pairs from Twitter by searching food-related keywords for the purpose of analyzing the relations between food images and associated text. Our data sets can contribute to analyzing eating habits of people by complementarily using text and images about users' eating reports.
|
Free Research Field |
テキストマイニング
|
Academic Significance and Societal Importance of the Research Achievements |
数値表現と言語表現、あるいは、画像と言語表現の関連を分析し、相互変換を行うことで、従来実現できなかった、「数値表現をもとに、適切な文書を検索する」というシステムの実現が可能になった。また、SNS上でのユーザーの健康に関する文書を分析するための基盤を構築したことで、公的機関等による文書と、一般ユーザーの健康に対する報告を結びつける手法の実現に向けての環境が整った。
|