In order to join virtual sessions, you must be registered and logged-in(Were you registered for the in-person meeting in Denver? if yes, just log in.) 
Note: All session times are in Mountain Daylight Time.

A Machine Learning Enabled GIS&T Knowledge Graph

Authors: Yuanyuan Tian*, Arizona State University, Wenwen Li, Arizona State University, Sizhe Wang, Arizona State University
Topics: Cyberinfrastructure, Geographic Information Science and Systems
Keywords: knowledge graph, geographic information retrieval, machine learning
Session Type: Paper
Presentation File: No File Uploaded


This work is to apply the machine learning method and knowledge graph technology to discover geography wisdom buried under the Geographic Information Science & Technology Body of Knowledge (GIS&T BoK) text. With the growth of big data, there is a gap between data and knowledge, which means turning the data into information that is friendly for humans to acquire, or into the knowledge that humans can digest more easily. A new technology named “knowledge graph” has the advantage of linking entities, uncovering the semantic meaning of entities, and even deriving new knowledge. This technology has already succeeded in computer science such as information retrieval. The GIS&T BoK is a resource of authoritative information about topics within the broad domain of geographic information science. The first edition of the GIS&T BoK was published in 2006 as a book, while the digital version online is available in 2016. Although the online version looks like Wikipedia in geography and it provides convenience for people to search the geography domain notions and technologies, it is not straightforward to find similar topics and connections between different topics, or even gain insights and wisdom out of the textual information. For now, there is little attention and research work on the knowledge graph of GIS&T BoK. The solution to this problem is to apply AI technologies to this new online GIS&T BoK. The novel finding is a model that can transfer the geography domain documents into a knowledge graph that provides new wisdom for geography knowledge seekers.

Abstract Information

This abstract is already part of a session. View the session here.

To access contact information login