Limits of use of social media for monitoring biosecurity events.

Marijke Welvaert,Mark Cameron,Peter Caley,Omar Al-Ghattas,Alejandro Raul Hernandez Montoya

doi:10.1371/journal.pone.0172457

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.

Highlights

IntroductionMonitoring of human health based on internet search queries, known as syndromic surveillance, has gained popularity over the past decade following successful case studies like Google Flu (www.google.org/flutrends/about; following the footsteps of [1]) and Flu Detector [2]
Monitoring of human health based on internet search queries, known as syndromic surveillance, has gained popularity over the past decade following successful case studies like Google Flu and Flu Detector [2]
In the Results, we describe the findings for our three main research questions: (1) Are the species reported on Twitter?; (2) Can we extract the relevant tweets for these species?; and (3) Are the Twitter data related to ground truth data? the Discussion extrapolates our results to the broader implications for biosecurity surveillance using social media

Summary

Introduction

Monitoring of human health based on internet search queries, known as syndromic surveillance, has gained popularity over the past decade following successful case studies like Google Flu (www.google.org/flutrends/about; following the footsteps of [1]) and Flu Detector [2]. Syndromic surveillance has been discussed in the context of bio-terrorism (see [4] for an example). With the public health in mind, bio-terrorism investigators are looking for a real-time systematic collection of reliable indicators of disease in PLOS ONE | DOI:10.1371/journal.pone.0172457. The successes of syndromic surveillance in human health offer new perspectives for biosecurity surveillance, in which detecting exotic pests and pathogens of concern to the environment and agriculture in particular are the focus. It has been suggested that syndromic-type surveillance techniques applied to social media data streams could provide effective biosecurity surveillance, though this has not been tested far

Methods

Results

Conclusion