Mapping spatiotemporal patterns of events using social media: a case study of influenza trends

Yizhao Gao, Shaowen Wang, Anand Padmanabhan, Junjun Yin, Guofeng Cao

Research output: Contribution to journalArticle

Abstract

Tracking spatial and temporal trends of events (e.g. disease outbreaks and natural disasters) is important for situation awareness and timely response. Social media, with increasing popularity, provide an effective way to collect event-related data from massive populations and thus a significant opportunity to dynamically monitor events as they emerge and evolve. While existing research has demonstrated the value of social media as sensors in event detection, estimating potential time spans and influenced areas of an event from social media remains challenging. Challenges include the unstable volumes of available data, the spatial heterogeneity of event activities and social media data, and the data sparsity. This paper describes a systematic approach to detecting potential spatiotemporal patterns of events by resolving these challenges through several interrelated strategies: using kernel density estimation for smoothed social media intensity surfaces; utilizing event-unrelated social media posts to help map relative event prevalence; and normalizing event indicators based on historical fluctuation. This approach generates event indicator maps and significance maps explaining spatiotemporal variations of event prevalence to identify space-time regions with potentially abnormal event activities. The approach has been applied to detect influenza activity patterns in the conterminous US using Twitter data. A set of experiments demonstrated that our approach produces high-resolution influenza activity maps that could be explained by available ground truth data.

Original languageEnglish (US)
Pages (from-to)425-449
Number of pages25
JournalInternational Journal of Geographical Information Science
Volume32
Issue number3
DOIs
StatePublished - Mar 4 2018

Fingerprint

influenza
social media
contagious disease
event
trend
Disasters
activity pattern
natural disaster
Sensors
sensor
Experiments
twitter
fluctuation
popularity
experiment

Keywords

  • CyberGIS
  • event detection
  • influenza surveillance
  • social media
  • spatiotemporal analysis

ASJC Scopus subject areas

  • Information Systems
  • Geography, Planning and Development
  • Library and Information Sciences

Cite this

Mapping spatiotemporal patterns of events using social media : a case study of influenza trends. / Gao, Yizhao; Wang, Shaowen; Padmanabhan, Anand; Yin, Junjun; Cao, Guofeng.

In: International Journal of Geographical Information Science, Vol. 32, No. 3, 04.03.2018, p. 425-449.

Research output: Contribution to journalArticle

@article{4f1d494848ee43edb99c8507b02efeb4,
title = "Mapping spatiotemporal patterns of events using social media: a case study of influenza trends",
abstract = "Tracking spatial and temporal trends of events (e.g. disease outbreaks and natural disasters) is important for situation awareness and timely response. Social media, with increasing popularity, provide an effective way to collect event-related data from massive populations and thus a significant opportunity to dynamically monitor events as they emerge and evolve. While existing research has demonstrated the value of social media as sensors in event detection, estimating potential time spans and influenced areas of an event from social media remains challenging. Challenges include the unstable volumes of available data, the spatial heterogeneity of event activities and social media data, and the data sparsity. This paper describes a systematic approach to detecting potential spatiotemporal patterns of events by resolving these challenges through several interrelated strategies: using kernel density estimation for smoothed social media intensity surfaces; utilizing event-unrelated social media posts to help map relative event prevalence; and normalizing event indicators based on historical fluctuation. This approach generates event indicator maps and significance maps explaining spatiotemporal variations of event prevalence to identify space-time regions with potentially abnormal event activities. The approach has been applied to detect influenza activity patterns in the conterminous US using Twitter data. A set of experiments demonstrated that our approach produces high-resolution influenza activity maps that could be explained by available ground truth data.",
keywords = "CyberGIS, event detection, influenza surveillance, social media, spatiotemporal analysis",
author = "Yizhao Gao and Shaowen Wang and Anand Padmanabhan and Junjun Yin and Guofeng Cao",
year = "2018",
month = "3",
day = "4",
doi = "10.1080/13658816.2017.1406943",
language = "English (US)",
volume = "32",
pages = "425--449",
journal = "International Journal of Geographical Information Science",
issn = "1365-8816",
publisher = "Taylor and Francis Ltd.",
number = "3",

}

TY - JOUR

T1 - Mapping spatiotemporal patterns of events using social media

T2 - a case study of influenza trends

AU - Gao, Yizhao

AU - Wang, Shaowen

AU - Padmanabhan, Anand

AU - Yin, Junjun

AU - Cao, Guofeng

PY - 2018/3/4

Y1 - 2018/3/4

N2 - Tracking spatial and temporal trends of events (e.g. disease outbreaks and natural disasters) is important for situation awareness and timely response. Social media, with increasing popularity, provide an effective way to collect event-related data from massive populations and thus a significant opportunity to dynamically monitor events as they emerge and evolve. While existing research has demonstrated the value of social media as sensors in event detection, estimating potential time spans and influenced areas of an event from social media remains challenging. Challenges include the unstable volumes of available data, the spatial heterogeneity of event activities and social media data, and the data sparsity. This paper describes a systematic approach to detecting potential spatiotemporal patterns of events by resolving these challenges through several interrelated strategies: using kernel density estimation for smoothed social media intensity surfaces; utilizing event-unrelated social media posts to help map relative event prevalence; and normalizing event indicators based on historical fluctuation. This approach generates event indicator maps and significance maps explaining spatiotemporal variations of event prevalence to identify space-time regions with potentially abnormal event activities. The approach has been applied to detect influenza activity patterns in the conterminous US using Twitter data. A set of experiments demonstrated that our approach produces high-resolution influenza activity maps that could be explained by available ground truth data.

AB - Tracking spatial and temporal trends of events (e.g. disease outbreaks and natural disasters) is important for situation awareness and timely response. Social media, with increasing popularity, provide an effective way to collect event-related data from massive populations and thus a significant opportunity to dynamically monitor events as they emerge and evolve. While existing research has demonstrated the value of social media as sensors in event detection, estimating potential time spans and influenced areas of an event from social media remains challenging. Challenges include the unstable volumes of available data, the spatial heterogeneity of event activities and social media data, and the data sparsity. This paper describes a systematic approach to detecting potential spatiotemporal patterns of events by resolving these challenges through several interrelated strategies: using kernel density estimation for smoothed social media intensity surfaces; utilizing event-unrelated social media posts to help map relative event prevalence; and normalizing event indicators based on historical fluctuation. This approach generates event indicator maps and significance maps explaining spatiotemporal variations of event prevalence to identify space-time regions with potentially abnormal event activities. The approach has been applied to detect influenza activity patterns in the conterminous US using Twitter data. A set of experiments demonstrated that our approach produces high-resolution influenza activity maps that could be explained by available ground truth data.

KW - CyberGIS

KW - event detection

KW - influenza surveillance

KW - social media

KW - spatiotemporal analysis

UR - http://www.scopus.com/inward/record.url?scp=85041135960&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85041135960&partnerID=8YFLogxK

U2 - 10.1080/13658816.2017.1406943

DO - 10.1080/13658816.2017.1406943

M3 - Article

AN - SCOPUS:85041135960

VL - 32

SP - 425

EP - 449

JO - International Journal of Geographical Information Science

JF - International Journal of Geographical Information Science

SN - 1365-8816

IS - 3

ER -