Leveraging advances in natural language processing to better understand tobler's first law of geography

Toby Jia Jun Li; Shilad Sen; Brent Hecht

doi:10.1145/2666310.2666493

Leveraging advances in natural language processing to better understand tobler's first law of geography

Toby Jia Jun Li, Shilad Sen, Brent Hecht

Computer Science and Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

19 Scopus citations

Abstract

Tobler's First Law of Geography (TFL) is one of the key reasons why "spatial is special". The law, which states that "everything is related to everything else, but near things are more related than distant things", is central to the management, presentation, and analysis of geographic information. However, despite the importance of TFL, we have a limited general understanding of its domain-neutral properties. In this paper, we leverage recent advances in the natural language processing domain of semantic relatedness estimation to, for the first time, robustly evaluate the extent to which relatedness between spatial entities decreases over distance in a domain-neutral fashion. Our results reveal that, in general, TFL can indeed be considered a globally recognized domain-neutral property of geographic information but that there is a distance beyond which being nearer, on average, no longer means being more related.

Original language	English (US)
Title of host publication	22nd ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM SIGSPATIAL GIS 2014
Editors	Markus Schneider, Michael Gertz, Yan Huang, Jagan Sankaranarayanan, John Krumm
Publisher	Association for Computing Machinery
Pages	513-516
Number of pages	4
ISBN (Electronic)	9781450331319
DOIs	https://doi.org/10.1145/2666310.2666493
State	Published - Nov 4 2014
Event	22nd ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM SIGSPATIAL GIS 2014 - Dallas, United States Duration: Nov 4 2014 → Nov 7 2014

Publication series

Name	GIS: Proceedings of the ACM International Symposium on Advances in Geographic Information Systems
Volume	04-07-November-2014

Other

Other	22nd ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM SIGSPATIAL GIS 2014
Country/Territory	United States
City	Dallas
Period	11/4/14 → 11/7/14

Bibliographical note

Publisher Copyright:
© Copyright 2014 ACM.

Keywords

Distance
Semantic relatedness
Tobler's First Law of Geography

Publisher link

10.1145/2666310.2666493

Find It

Find It at U of M Libraries

Cite this

Li, T. J. J., Sen, S., & Hecht, B. (2014). Leveraging advances in natural language processing to better understand tobler's first law of geography. In M. Schneider, M. Gertz, Y. Huang, J. Sankaranarayanan, & J. Krumm (Eds.), 22nd ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM SIGSPATIAL GIS 2014 (pp. 513-516). (GIS: Proceedings of the ACM International Symposium on Advances in Geographic Information Systems; Vol. 04-07-November-2014). Association for Computing Machinery. https://doi.org/10.1145/2666310.2666493

Leveraging advances in natural language processing to better understand tobler's first law of geography. / Li, Toby Jia Jun; Sen, Shilad; Hecht, Brent.
22nd ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM SIGSPATIAL GIS 2014. ed. / Markus Schneider; Michael Gertz; Yan Huang; Jagan Sankaranarayanan; John Krumm. Association for Computing Machinery, 2014. p. 513-516 (GIS: Proceedings of the ACM International Symposium on Advances in Geographic Information Systems; Vol. 04-07-November-2014).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Li, TJJ, Sen, S & Hecht, B 2014, Leveraging advances in natural language processing to better understand tobler's first law of geography. in M Schneider, M Gertz, Y Huang, J Sankaranarayanan & J Krumm (eds), 22nd ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM SIGSPATIAL GIS 2014. GIS: Proceedings of the ACM International Symposium on Advances in Geographic Information Systems, vol. 04-07-November-2014, Association for Computing Machinery, pp. 513-516, 22nd ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM SIGSPATIAL GIS 2014, Dallas, United States, 11/4/14. https://doi.org/10.1145/2666310.2666493

Li TJJ, Sen S, Hecht B. Leveraging advances in natural language processing to better understand tobler's first law of geography. In Schneider M, Gertz M, Huang Y, Sankaranarayanan J, Krumm J, editors, 22nd ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM SIGSPATIAL GIS 2014. Association for Computing Machinery. 2014. p. 513-516. (GIS: Proceedings of the ACM International Symposium on Advances in Geographic Information Systems). doi: 10.1145/2666310.2666493

Li, Toby Jia Jun ; Sen, Shilad ; Hecht, Brent. / Leveraging advances in natural language processing to better understand tobler's first law of geography. 22nd ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM SIGSPATIAL GIS 2014. editor / Markus Schneider ; Michael Gertz ; Yan Huang ; Jagan Sankaranarayanan ; John Krumm. Association for Computing Machinery, 2014. pp. 513-516 (GIS: Proceedings of the ACM International Symposium on Advances in Geographic Information Systems).

@inproceedings{0e0ee76061244016afac41b4b9b6a229,

title = "Leveraging advances in natural language processing to better understand tobler's first law of geography",

abstract = "Tobler's First Law of Geography (TFL) is one of the key reasons why {"}spatial is special{"}. The law, which states that {"}everything is related to everything else, but near things are more related than distant things{"}, is central to the management, presentation, and analysis of geographic information. However, despite the importance of TFL, we have a limited general understanding of its domain-neutral properties. In this paper, we leverage recent advances in the natural language processing domain of semantic relatedness estimation to, for the first time, robustly evaluate the extent to which relatedness between spatial entities decreases over distance in a domain-neutral fashion. Our results reveal that, in general, TFL can indeed be considered a globally recognized domain-neutral property of geographic information but that there is a distance beyond which being nearer, on average, no longer means being more related.",

keywords = "Distance, Semantic relatedness, Tobler's First Law of Geography",

author = "Li, {Toby Jia Jun} and Shilad Sen and Brent Hecht",

note = "Publisher Copyright: {\textcopyright} Copyright 2014 ACM.; 22nd ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM SIGSPATIAL GIS 2014 ; Conference date: 04-11-2014 Through 07-11-2014",

year = "2014",

month = nov,

day = "4",

doi = "10.1145/2666310.2666493",

language = "English (US)",

series = "GIS: Proceedings of the ACM International Symposium on Advances in Geographic Information Systems",

publisher = "Association for Computing Machinery",

pages = "513--516",

editor = "Markus Schneider and Michael Gertz and Yan Huang and Jagan Sankaranarayanan and John Krumm",

booktitle = "22nd ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM SIGSPATIAL GIS 2014",

}

TY - GEN

T1 - Leveraging advances in natural language processing to better understand tobler's first law of geography

AU - Li, Toby Jia Jun

AU - Sen, Shilad

AU - Hecht, Brent

PY - 2014/11/4

Y1 - 2014/11/4

N2 - Tobler's First Law of Geography (TFL) is one of the key reasons why "spatial is special". The law, which states that "everything is related to everything else, but near things are more related than distant things", is central to the management, presentation, and analysis of geographic information. However, despite the importance of TFL, we have a limited general understanding of its domain-neutral properties. In this paper, we leverage recent advances in the natural language processing domain of semantic relatedness estimation to, for the first time, robustly evaluate the extent to which relatedness between spatial entities decreases over distance in a domain-neutral fashion. Our results reveal that, in general, TFL can indeed be considered a globally recognized domain-neutral property of geographic information but that there is a distance beyond which being nearer, on average, no longer means being more related.

AB - Tobler's First Law of Geography (TFL) is one of the key reasons why "spatial is special". The law, which states that "everything is related to everything else, but near things are more related than distant things", is central to the management, presentation, and analysis of geographic information. However, despite the importance of TFL, we have a limited general understanding of its domain-neutral properties. In this paper, we leverage recent advances in the natural language processing domain of semantic relatedness estimation to, for the first time, robustly evaluate the extent to which relatedness between spatial entities decreases over distance in a domain-neutral fashion. Our results reveal that, in general, TFL can indeed be considered a globally recognized domain-neutral property of geographic information but that there is a distance beyond which being nearer, on average, no longer means being more related.

KW - Distance

KW - Semantic relatedness

KW - Tobler's First Law of Geography

UR - http://www.scopus.com/inward/record.url?scp=84961204002&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84961204002&partnerID=8YFLogxK

U2 - 10.1145/2666310.2666493

DO - 10.1145/2666310.2666493

M3 - Conference contribution

AN - SCOPUS:84961204002

T3 - GIS: Proceedings of the ACM International Symposium on Advances in Geographic Information Systems

SP - 513

EP - 516

BT - 22nd ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM SIGSPATIAL GIS 2014

A2 - Schneider, Markus

A2 - Gertz, Michael

A2 - Huang, Yan

A2 - Sankaranarayanan, Jagan

A2 - Krumm, John

PB - Association for Computing Machinery

T2 - 22nd ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM SIGSPATIAL GIS 2014

Y2 - 4 November 2014 through 7 November 2014

ER -

Leveraging advances in natural language processing to better understand tobler's first law of geography

Abstract

Publication series

Other

Bibliographical note

Keywords

Publisher link

Find It

Other files and links

Fingerprint

Cite this