國立虎尾科技大學 |

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

Record Type:	Language materials, manuscript : Monograph/item
Title/Author:	Building Dynamic Ontological Models for Place Names Using Social Media Data from Twitter and Sina Weibo./
Author:	Zhang, Qingyun.
Description:	1 online resource (157 pages)
Notes:	Source: Masters Abstracts International, Volume: 57-02.
Contained By:	Masters Abstracts International57-02(E).
Subject:	Geographic information science and geodesy. -
Online resource:	click for full text (PQDT)
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. - 1 online resource (157 pages)

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

Thesis (M.S.)

Includes bibliographical references

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.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2018

Mode of access: World Wide Web

ISBN: 9780355538304Subjects--Topical Terms:

1148646
Geographic information science and geodesy.
Index Terms--Genre/Form:

554714
Electronic books.

Building Dynamic Ontological Models for Place Names Using Social Media Data from Twitter and Sina Weibo.
LDR:03762ntm a2200421Ki 4500 001 909968
005 20180426091051.5
006 m o u
007 cr mn||||a|a||
008 190606s2017 xx obm 000 0 eng d
020 $a 9780355538304
035 $a (MiAaPQ)AAI10689328
035 $a (MiAaPQ)sdsu:12074
035 $a AAI10689328
040 $a MiAaPQ $b eng $c MiAaPQ
099 $a TUL $f hyy $c available through World Wide Web
100 1 $a Zhang, Qingyun. $3 1181006
245 1 0 $a Building Dynamic Ontological Models for Place Names Using Social Media Data from Twitter and Sina Weibo.
264 0 $c 2017
300 $a 1 online resource (157 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Masters Abstracts International, Volume: 57-02.
500 $a Adviser: Ming-Hsiang Tsou.
502 $a Thesis (M.S.) $c San Diego State University $d 2017.
504 $a Includes bibliographical references
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.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2018
538 $a Mode of access: World Wide Web
650 4 $a Geographic information science and geodesy. $3 1148646
650 4 $a Remote sensing. $3 557272
650 4 $a Web studies. $3 1148502
655 7 $a Electronic books. $2 local $3 554714
690 $a 0370
690 $a 0799
690 $a 0646
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a San Diego State University. $b Geography. $3 1180991
773 0 $t Masters Abstracts International $g 57-02(E).
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10689328 $z click for full text (PQDT)