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

Autor/in	Jiang, Yongyao
Titel	Improving Geospatial Data Search Ranking Using Deep Learning and User Behaviour Data
Quelle	(2018), (107 Seiten) PDF als Volltext Verfügbarkeit Ph.D. Dissertation, George Mason University
Sprache	englisch
Dokumenttyp	gedruckt; online; Monographie
ISBN	978-0-4387-3883-6
Schlagwörter	Hochschulschrift; Dissertation; Geographic Information Systems; Users (Information); Data Collection; Online Searching; Oceanography; Information Retrieval; Earth Science; Mathematics; Artificial Intelligence + Suchen Sie Ihr Suchwort? Thesis; Dissertations; Academic thesis; Benutzerprofil; Nutzer; Data capture; Datensammlung; Online-Recherche; Ozeanografie; Earth sciences; Geowissenschaften; Mathematik; Künstliche Intelligenz
Abstract	Finding Earth science data has been a challenging problem given both the quantity of data available and the heterogeneity of the data across a wide variety of domains. Current search engines in most geospatial data portals tend to induce end users to focus on one single data attribute. This approach largely fails to take account of users' multiple and dynamic preferences for geospatial data, and hence may likely result in a less than optimal user experience in discovering the most applicable dataset out of a vast range of available datasets. With users interacting with search engines, sufficient information is already hidden in the log files. Compared with explicit feedback data, information that can be derived/extracted from log files is virtually free and substantially more timely. In this dissertation, I propose a deep learning based ranking framework that can learn and update the ranking function based on user behavior data. The contributions of this framework include 1) a log processor that that can ingest, extract user access pattern and create training data from Web log in a batch mode/real-time; 2) a query understanding module to better interpret users' search intent using web log processing results and metadata; 3) a feature extractor that identifies ranking features representing users' search interests of geospatial data; and 4) a deep learning based ranking algorithm that automatically learns and updates a ranking function based on user behavior. The search ranking results will be evaluated using precision at K and normalized discounted cumulative gain (NDCG). This research will strengthen ties between Earth observations and user communities by addressing the ranking challenge, the fundamental obstacle in geospatial data discovery. As a proof of concept, I focus on a well-defined domain -- Oceanographic Science, and using NASA JPL's PO. DAAC as an example. [The dissertation citations contained here are published with the permission of ProQuest LLC. Further reproduction is prohibited without permission. Copies of dissertations may be obtained by Telephone (800) 1-800-521-0600. Web page: http://www.proquest.com/en-US/products/dissertations/individuals.shtml.] (As Provided).
Anmerkungen	ProQuest LLC. 789 East Eisenhower Parkway, P.O. Box 1346, Ann Arbor, MI 48106. Tel: 800-521-0600; Web site: http://www.proquest.com/en-US/products/dissertations/individuals.shtml
Erfasst von	ERIC (Education Resources Information Center), Washington, DC
Update	2020/1/01