Construction of a Support System for Creating Regional Learning Materials through Cross-Use of Regional Digital Archives

2022 Fiscal Year Final Research Report

• Project/Area Number: 20K12547
• Research Category: Grant-in-Aid for Scientific Research (C)
• Allocation Type: Multi-year Fund
• Section: 一般
• Review Section: Basic Section 90020:Library and information science, humanistic and social informatics-related
• Research Institution: Future University-Hakodate
• Principal Investigator: Okuno Taku 公立はこだて未来大学, システム情報科学部, 教授 (30360936)
• Co-Investigator(Kenkyū-buntansha): 川嶋 稔夫 公立はこだて未来大学, システム情報科学部, 教授 (20152952)
• Project Period (FY): 2020-04-01 – 2023-03-31
• Keywords: 地域学習 / デジタルアーカイブ / 探索支援 / 可視化 / 自然言語処理 / 深層学習 / Webアプリケーション / スマートフォン

Outline of Final Research Achievements

In this study, for the purpose of supporting the creation of regional learning materials, we constructed a method to easily and comprehensively search for materials related to the theme of regional learning by cross-ambiguous search across multiple regional digital archives, and to automatically display the location of the subject of the materials on an old map. In addition, we have developed a method to support search of regional cultural heritage archives by visualization based on characteristic words of explanatory text to facilitate understanding of an overall picture of the archived items, a method to support search of image archives based on similarity of images and metadata, and a method to support the search for related materials in the digital archive from the exhibited materials in a museum.

Free Research Field

デジタルアーカイブ，観光情報学，ソフトウェア工学

Academic Significance and Societal Importance of the Research Achievements

デジタルアーカイブの資料の探索には，キーワード検索，階層的カテゴリ分類，タグ付けなどの方法が用いられるが，ユーザの知識を前提としたり，人手によるメンテナンスコストが高いという問題がある．本研究では，自然言語処理技術や深層学習技術を用いて，単語の意味的類似性を考慮した曖昧検索や．テキストや画像など資料の種類に応じた可視化手法を構築することにより，それらの問題の解決を試みているという点で学術的・社会的意義がある．