Improving Geospatial Data Search Ranking using Deep Learning and User Behaviour Data

Authors: Yun Li*, george mason university, Yongyao Jiang, george mason univerity
Topics: Geographic Information Science and Systems
Keywords: deep learning, data discovery, ranking
Session Type: Paper
Day: 4/3/2019
Start / End Time: 12:40 PM / 2:20 PM
Room: Virginia B, Marriott, Lobby Level
Presentation File: No File Uploaded


Given both the volume and variety of geospatial data available to the public, accurately and efficiently finding the required data has been a challenging problem. Previous work has leveraged machine learning methods to improve geospatial data search ranking, however, the algorithms rely on training data labeled by domain experts, which makes them difficult and expensive to apply and fails in scenarios where the relevance of data to a query can change over time. With users interacting with search engines, sufficient information is already hidden in the log files, which is virtually free and substantially more timely. In this research, we propose an online deep learning framework that can quickly update the learning function based on real-time user clickstream data.

Abstract Information

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

To access contact information login