Developing Metadata-independent High Coverage Geolocation for Travelogues

2023 Fiscal Year Final Research Report

• Project/Area Number: 21K12137
• 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: University of Tsukuba
• Principal Investigator: INUI Takashi 筑波大学, システム情報系, 准教授 (60397031)
• Project Period (FY): 2021-04-01 – 2024-03-31
• Keywords: 文書ジオロケーション技術 / 地理的知識グラフ / 埋め込み表現学習 / ランドマーク抽出 / エンティティリンキング / Data Augmentation

Outline of Final Research Achievements

The goal of this research project is to develop technology that accurately identifies the geographical locations from the content of SNS posts in order to promote the utilization of travelogue SNS data as target data for comprehensive tourism needs surveys using tourism big data. The main research achievements include the following: (1) Developed an embedding representation learning method based on the TransE approach that maintains geographical proximity and constructed a geographical knowledge graph. (2) Developed a measure (geographical specificity index) that indicates the degree to which the geographical location of words can be identified based on Wikipedia anchor link information. (3) Conducted performance evaluations of the 47 prefecture-level document geolocation tasks and confirmed the effectiveness of the developed methods.

Free Research Field

自然言語処理

Academic Significance and Societal Importance of the Research Achievements

本研究課題は、地方都市部の観光振興事業において利活用が困難であった観光旅行記SNSビックデータに対して、当該データの利活用促進を実現するための高被覆地理的位置特定技術の開発を目的としたものである。本研究課題で得られた成果を活用することにより、包括的観光ニーズ調査の調査可能地点を地方都市部を含む全国各所の観光地へと拡大させ、従来よりも調査の質を向上させることができると期待される。