東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

Building Dynamic Ontological Models ...

Zhang, Qingyun.

Linked to FindBook

Google Book

Amazon

博客來

Building Dynamic Ontological Models for Place Names Using Social Media Data from Twitter and Sina Weibo.

Record Type:	Electronic resources : Monograph/item
Title/Author:	Building Dynamic Ontological Models for Place Names Using Social Media Data from Twitter and Sina Weibo./
Author:	Zhang, Qingyun.
Published:	Ann Arbor : ProQuest Dissertations & Theses, : 2017,
Description:	157 p.
Notes:	Source: Masters Abstracts International, Volume: 57-02.
Contained By:	Masters Abstracts International57-02(E).
Subject:	Geographic information science and geodesy. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10689328
ISBN:	9780355538304

Building Dynamic Ontological Models for Place Names Using Social Media Data from Twitter and Sina Weibo.
Zhang, Qingyun.

Building Dynamic Ontological Models for Place Names Using Social Media Data from Twitter and Sina Weibo. - Ann Arbor : ProQuest Dissertations & Theses, 2017 - 157 p.

Source: Masters Abstracts International, Volume: 57-02.

Thesis (M.S.)--San Diego State University, 2017.

Place holds human thoughts and experiences. Space is defined with geometric measurement and coordinate systems. Social media data can analyze the connection between place and space.

ISBN: 9780355538304Subjects--Topical Terms:

2122917
Geographic information science and geodesy.

Building Dynamic Ontological Models for Place Names Using Social Media Data from Twitter and Sina Weibo.
LDR:03424nmm a2200373 4500 001 2155607
005 20180426091051.5
008 190424s2017 ||||||||||||||||| ||eng d
020 $a 9780355538304
035 $a (MiAaPQ)AAI10689328
035 $a (MiAaPQ)sdsu:12074
035 $a AAI10689328
040 $a MiAaPQ $c MiAaPQ
100 1 $a Zhang, Qingyun. $3 3343344
245 1 0 $a Building Dynamic Ontological Models for Place Names Using Social Media Data from Twitter and Sina Weibo.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2017
300 $a 157 p.
500 $a Source: Masters Abstracts International, Volume: 57-02.
500 $a Adviser: Ming-Hsiang Tsou.
502 $a Thesis (M.S.)--San Diego State University, 2017.
520 $a Place holds human thoughts and experiences. Space is defined with geometric measurement and coordinate systems. Social media data can analyze the connection between place and space.
520 $a This research uses two case studies to illustrate the building of dynamic ontological models for places. The first case collected Twitter data with nine key place names in San Diego. The second case study collected Sina Weibo data with eight key place names in Chinese in Beijing. Only geotagged social media data from the two social media platforms were collected through their APIs.
520 $a This research utilized three spatial analysis methods in order to analyze the dynamic ontological representations of place names: 1). Kernel Density Estimation (KDE); 2) Density-based spatial clustering of applications with noise (DBSCAN); and 3) hierarchal clustering. The normalized KDE approach is the best algorithm to generate appropriate boundaries or footprints for place names. DBSCAN and hierarchal clustering cannot deliver desirable ontological boundary outcomes. This research classified polyline and non-polyline type of place name ontologies by comparing their default search radius of KDE of geotagged points.
520 $a With the dynamic characteristics of social media, this research provided dynamic spatiotemporal analysis. By viewing the seasonal changes of highly dynamic nonadministrative places, it reflects the seasonal change of human activities. Besides spatial analysis, this research also investigates the semantic meaning associated with each place name. By looking at Pointwise Mutual Information (PMI) scores and wordclouds, PMI can be used to measure the most significant keywords from the social media message associated with place names.
520 $a There are several constraints and challenges in this research. For example, GIS Software may not handle large numbers of social media data points. Also, the data may include some noise or have uneven amount of volume.
520 $a The major contribution of this research is to link and analyze the inter-relationships between place, space, and their attributes in the field of geography. Researchers can use the "bottom-up" approach and crowd-sourced data (social media) to study the ontology of places v rather than relying on traditional gazetteers. The dynamic ontology has many actual applications in industry as well such as urban planning and re-zoning.
590 $a School code: 0220.
650 4 $a Geographic information science and geodesy. $3 2122917
650 4 $a Remote sensing. $3 535394
650 4 $a Web studies. $3 2122754
690 $a 0370
690 $a 0799
690 $a 0646
710 2 $a San Diego State University. $b Geography. $3 3177545
773 0 $t Masters Abstracts International $g 57-02(E).
790 $a 0220
791 $a M.S.
792 $a 2017
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10689328