How Well Did You Locate Me? Effective Evaluation of Twitter User Geolocation

Ahmed Mourad; Falk Scholer; Mark Sanderson; Walid Magdy

doi:10.1109/ASONAM.2018.8508701

How Well Did You Locate Me? Effective Evaluation of Twitter User Geolocation

Ahmed Mourad, Falk Scholer, Mark Sanderson, Walid Magdy

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

Abstract / Description of output

We analyze fifteen Twitter user geolocation models and two baselines comparing how they are evaluated. Our results demonstrate that the choice of effectiveness metric can have a substantial impact on the conclusions drawn from an experiment. We show that for general evaluations, a range of metrics should be reported to ensure that a complete picture of system effectiveness is conveyed.

Original language	English
Title of host publication	2018 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM)
Publisher	Institute of Electrical and Electronics Engineers
Pages	437-440
Number of pages	4
ISBN (Electronic)	978-1-5386-6051-5
ISBN (Print)	978-1-5386-6052-2
DOIs	https://doi.org/10.1109/ASONAM.2018.8508701
Publication status	Published - 25 Aug 2018
Event	2018 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining - Barcelona, Spain Duration: 28 Aug 2018 → 31 Aug 2018 http://asonam.cpsc.ucalgary.ca/2018/index.php

Publication series

Name
Publisher	IEEE
ISSN (Print)	2473-9928
ISSN (Electronic)	2473-991X

Conference

Conference	2018 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining
Abbreviated title	ASONAM 2018
Country/Territory	Spain
City	Barcelona
Period	28/08/18 → 31/08/18
Internet address	http://asonam.cpsc.ucalgary.ca/2018/index.php

Access to Document

10.1109/ASONAM.2018.8508701Licence: All Rights Reserved

How Well Did You Locate MeAccepted author manuscript, 151 KB

https://ieeexplore.ieee.org/document/8508701Licence: All Rights Reserved

Cite this

@inproceedings{f7ab8ac89b3041cda862f722c8c77067,

title = "How Well Did You Locate Me? Effective Evaluation of Twitter User Geolocation",

abstract = "We analyze fifteen Twitter user geolocation models and two baselines comparing how they are evaluated. Our results demonstrate that the choice of effectiveness metric can have a substantial impact on the conclusions drawn from an experiment. We show that for general evaluations, a range of metrics should be reported to ensure that a complete picture of system effectiveness is conveyed.",

author = "Ahmed Mourad and Falk Scholer and Mark Sanderson and Walid Magdy",

year = "2018",

month = aug,

day = "25",

doi = "10.1109/ASONAM.2018.8508701",

language = "English",

isbn = "978-1-5386-6052-2",

publisher = "Institute of Electrical and Electronics Engineers",

pages = "437--440",

booktitle = "2018 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM)",

note = "2018 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2018 ; Conference date: 28-08-2018 Through 31-08-2018",

url = "http://asonam.cpsc.ucalgary.ca/2018/index.php",

}

Mourad, A, Scholer, F, Sanderson, M & Magdy, W 2018, How Well Did You Locate Me? Effective Evaluation of Twitter User Geolocation. in 2018 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM). Institute of Electrical and Electronics Engineers, pp. 437-440, 2018 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, Barcelona, Spain, 28/08/18. https://doi.org/10.1109/ASONAM.2018.8508701

How Well Did You Locate Me? Effective Evaluation of Twitter User Geolocation. / Mourad, Ahmed; Scholer, Falk; Sanderson, Mark et al.
2018 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM). Institute of Electrical and Electronics Engineers, 2018. p. 437-440.

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

TY - GEN

T1 - How Well Did You Locate Me? Effective Evaluation of Twitter User Geolocation

AU - Mourad, Ahmed

AU - Scholer, Falk

AU - Sanderson, Mark

AU - Magdy, Walid

PY - 2018/8/25

Y1 - 2018/8/25

N2 - We analyze fifteen Twitter user geolocation models and two baselines comparing how they are evaluated. Our results demonstrate that the choice of effectiveness metric can have a substantial impact on the conclusions drawn from an experiment. We show that for general evaluations, a range of metrics should be reported to ensure that a complete picture of system effectiveness is conveyed.

AB - We analyze fifteen Twitter user geolocation models and two baselines comparing how they are evaluated. Our results demonstrate that the choice of effectiveness metric can have a substantial impact on the conclusions drawn from an experiment. We show that for general evaluations, a range of metrics should be reported to ensure that a complete picture of system effectiveness is conveyed.

U2 - 10.1109/ASONAM.2018.8508701

DO - 10.1109/ASONAM.2018.8508701

M3 - Conference contribution

SN - 978-1-5386-6052-2

SP - 437

EP - 440

BT - 2018 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM)

PB - Institute of Electrical and Electronics Engineers

T2 - 2018 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining

Y2 - 28 August 2018 through 31 August 2018

ER -

How Well Did You Locate Me? Effective Evaluation of Twitter User Geolocation

Abstract / Description of output

Publication series

Conference

Access to Document

Fingerprint

Cite this