Limits of use of social media for monitoring biosecurity events

Marijke Welvaert, Omar Al-Ghattas, Mark Cameron, Peter Caley

Research output: Contribution to journalArticle

4 Citations (Scopus)
12 Downloads (Pure)

Abstract

Compared to applications that trigger massive information streams, like earthquakes and
human disease epidemics, the data input for agricultural and environmental biosecurity
events (ie. the introduction of unwanted exotic pests and pathogens), is expected to be
sparse and less frequent. To investigate if Twitter data can be useful for the detection and
monitoring of biosecurity events, we adopted a three-step process. First, we confirmed that
sightings of two migratory species, the Bogong moth (Agrotis infusa) and the Common Koel
(Eudynamys scolopaceus) are reported on Twitter. Second, we developed search queries
to extract the relevant tweets for these species. The queries were based on either the taxonomic
name, common name or keywords that are frequently used to describe the species
(symptomatic or syndromic). Third, we validated the results using ground truth data. Our
results indicate that the common name queries provided a reasonable number of tweets
that were related to the ground truth data. The taxonomic query resulted in too small datasets,
while the symptomatic queries resulted in large datasets, but with highly variable signal-to-noise
ratios. No clear relationship was observed between the tweets from the
symptomatic queries and the ground truth data. Comparing the results for the two species
showed that the level of familiarity with the species plays a major role. The more familiar the
species, the more stable and reliable the Twitter data. This clearly presents a problem for
using social media to detect the arrival of an exotic organism of biosecurity concern for
which public is unfamiliar
Original languageEnglish
Article numbere0172457
Pages (from-to)1-17
Number of pages17
JournalPLoS One
Volume12
Issue number2
DOIs
Publication statusPublished - 23 Feb 2017
Externally publishedYes

Cite this

Welvaert, M., Al-Ghattas, O., Cameron, M., & Caley, P. (2017). Limits of use of social media for monitoring biosecurity events. PLoS One, 12(2), 1-17. [e0172457]. https://doi.org/10.1371/journal.pone.0172457
Welvaert, Marijke ; Al-Ghattas, Omar ; Cameron, Mark ; Caley, Peter. / Limits of use of social media for monitoring biosecurity events. In: PLoS One. 2017 ; Vol. 12, No. 2. pp. 1-17.
@article{5908c7280dbd4fb6904b0549633f7141,
title = "Limits of use of social media for monitoring biosecurity events",
abstract = "Compared to applications that trigger massive information streams, like earthquakes andhuman disease epidemics, the data input for agricultural and environmental biosecurityevents (ie. the introduction of unwanted exotic pests and pathogens), is expected to besparse and less frequent. To investigate if Twitter data can be useful for the detection andmonitoring of biosecurity events, we adopted a three-step process. First, we confirmed thatsightings of two migratory species, the Bogong moth (Agrotis infusa) and the Common Koel(Eudynamys scolopaceus) are reported on Twitter. Second, we developed search queriesto extract the relevant tweets for these species. The queries were based on either the taxonomicname, common name or keywords that are frequently used to describe the species(symptomatic or syndromic). Third, we validated the results using ground truth data. Ourresults indicate that the common name queries provided a reasonable number of tweetsthat were related to the ground truth data. The taxonomic query resulted in too small datasets,while the symptomatic queries resulted in large datasets, but with highly variable signal-to-noiseratios. No clear relationship was observed between the tweets from thesymptomatic queries and the ground truth data. Comparing the results for the two speciesshowed that the level of familiarity with the species plays a major role. The more familiar thespecies, the more stable and reliable the Twitter data. This clearly presents a problem forusing social media to detect the arrival of an exotic organism of biosecurity concern forwhich public is unfamiliar",
author = "Marijke Welvaert and Omar Al-Ghattas and Mark Cameron and Peter Caley",
year = "2017",
month = "2",
day = "23",
doi = "10.1371/journal.pone.0172457",
language = "English",
volume = "12",
pages = "1--17",
journal = "PLoS One",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "2",

}

Welvaert, M, Al-Ghattas, O, Cameron, M & Caley, P 2017, 'Limits of use of social media for monitoring biosecurity events', PLoS One, vol. 12, no. 2, e0172457, pp. 1-17. https://doi.org/10.1371/journal.pone.0172457

Limits of use of social media for monitoring biosecurity events. / Welvaert, Marijke; Al-Ghattas, Omar; Cameron, Mark; Caley, Peter.

In: PLoS One, Vol. 12, No. 2, e0172457, 23.02.2017, p. 1-17.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Limits of use of social media for monitoring biosecurity events

AU - Welvaert, Marijke

AU - Al-Ghattas, Omar

AU - Cameron, Mark

AU - Caley, Peter

PY - 2017/2/23

Y1 - 2017/2/23

N2 - Compared to applications that trigger massive information streams, like earthquakes andhuman disease epidemics, the data input for agricultural and environmental biosecurityevents (ie. the introduction of unwanted exotic pests and pathogens), is expected to besparse and less frequent. To investigate if Twitter data can be useful for the detection andmonitoring of biosecurity events, we adopted a three-step process. First, we confirmed thatsightings of two migratory species, the Bogong moth (Agrotis infusa) and the Common Koel(Eudynamys scolopaceus) are reported on Twitter. Second, we developed search queriesto extract the relevant tweets for these species. The queries were based on either the taxonomicname, common name or keywords that are frequently used to describe the species(symptomatic or syndromic). Third, we validated the results using ground truth data. Ourresults indicate that the common name queries provided a reasonable number of tweetsthat were related to the ground truth data. The taxonomic query resulted in too small datasets,while the symptomatic queries resulted in large datasets, but with highly variable signal-to-noiseratios. No clear relationship was observed between the tweets from thesymptomatic queries and the ground truth data. Comparing the results for the two speciesshowed that the level of familiarity with the species plays a major role. The more familiar thespecies, the more stable and reliable the Twitter data. This clearly presents a problem forusing social media to detect the arrival of an exotic organism of biosecurity concern forwhich public is unfamiliar

AB - Compared to applications that trigger massive information streams, like earthquakes andhuman disease epidemics, the data input for agricultural and environmental biosecurityevents (ie. the introduction of unwanted exotic pests and pathogens), is expected to besparse and less frequent. To investigate if Twitter data can be useful for the detection andmonitoring of biosecurity events, we adopted a three-step process. First, we confirmed thatsightings of two migratory species, the Bogong moth (Agrotis infusa) and the Common Koel(Eudynamys scolopaceus) are reported on Twitter. Second, we developed search queriesto extract the relevant tweets for these species. The queries were based on either the taxonomicname, common name or keywords that are frequently used to describe the species(symptomatic or syndromic). Third, we validated the results using ground truth data. Ourresults indicate that the common name queries provided a reasonable number of tweetsthat were related to the ground truth data. The taxonomic query resulted in too small datasets,while the symptomatic queries resulted in large datasets, but with highly variable signal-to-noiseratios. No clear relationship was observed between the tweets from thesymptomatic queries and the ground truth data. Comparing the results for the two speciesshowed that the level of familiarity with the species plays a major role. The more familiar thespecies, the more stable and reliable the Twitter data. This clearly presents a problem forusing social media to detect the arrival of an exotic organism of biosecurity concern forwhich public is unfamiliar

UR - http://www.scopus.com/inward/record.url?scp=85013986496&partnerID=8YFLogxK

UR - http://www.mendeley.com/research/limits-social-media-monitoring-biosecurity-events

U2 - 10.1371/journal.pone.0172457

DO - 10.1371/journal.pone.0172457

M3 - Article

VL - 12

SP - 1

EP - 17

JO - PLoS One

JF - PLoS One

SN - 1932-6203

IS - 2

M1 - e0172457

ER -

Welvaert M, Al-Ghattas O, Cameron M, Caley P. Limits of use of social media for monitoring biosecurity events. PLoS One. 2017 Feb 23;12(2):1-17. e0172457. https://doi.org/10.1371/journal.pone.0172457