Flu Detector - Tracking Epidemics on Twitter

Lampos Vasileios; Bie Tijl De; Nello Cristianini

Flu Detector - Tracking Epidemics on Twitter

Lampos Vasileios, Bie Tijl De, Nello Cristianini

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

190 Citations (Scopus)

Abstract

We present an automated tool with a web interface for tracking the prevalence of Influenza-like Illness (ILI) in several regions of the United Kingdom using the contents of Twitter's microblogging service. Our data is comprised by a daily average of approximately 200,000 geolocated tweets collected by targeting 49 urban centres in the UK for a time period of 40 weeks. Official ILI rates from the Health Protection Agency (HPA) form our ground truth. Bolasso, the bootstrapped version of LASSO, is applied in order to extract a consistent set of features, which are then used for learning a regression model. Visit Flu Detector's website

Translated title of the contribution	Flu Detector - Tracking Epidemics on Twitter
Original language	English
Title of host publication	European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD)
Publisher	Springer
Publication status	Published - 2010

Bibliographical note

Other page information: 599-602
Conference Proceedings/Title of Journal: European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD)
Other identifier: 2001214

Access to Document

http://www.cs.bris.ac.uk/Publications/pub_master.jsp?id=2001214

Handle.net

Persistent link

Cite this

@inproceedings{35e065ae148b48a98f812d3a37541c3d,

title = "Flu Detector - Tracking Epidemics on Twitter",

abstract = " We present an automated tool with a web interface for tracking the prevalence of Influenza-like Illness (ILI) in several regions of the United Kingdom using the contents of Twitter's microblogging service. Our data is comprised by a daily average of approximately 200,000 geolocated tweets collected by targeting 49 urban centres in the UK for a time period of 40 weeks. Official ILI rates from the Health Protection Agency (HPA) form our ground truth. Bolasso, the bootstrapped version of LASSO, is applied in order to extract a consistent set of features, which are then used for learning a regression model. Visit Flu Detector's website ",

author = "Lampos Vasileios and \{Tijl De\}, Bie and Nello Cristianini",

note = "Other page information: 599-602 Conference Proceedings/Title of Journal: European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD) Other identifier: 2001214",

year = "2010",

language = "English",

booktitle = "European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD)",

publisher = "Springer",

address = "United States",

}

TY - GEN

T1 - Flu Detector - Tracking Epidemics on Twitter

AU - Vasileios, Lampos

AU - Tijl De, Bie

AU - Cristianini, Nello

N1 - Other page information: 599-602 Conference Proceedings/Title of Journal: European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD) Other identifier: 2001214

PY - 2010

Y1 - 2010

N2 - We present an automated tool with a web interface for tracking the prevalence of Influenza-like Illness (ILI) in several regions of the United Kingdom using the contents of Twitter's microblogging service. Our data is comprised by a daily average of approximately 200,000 geolocated tweets collected by targeting 49 urban centres in the UK for a time period of 40 weeks. Official ILI rates from the Health Protection Agency (HPA) form our ground truth. Bolasso, the bootstrapped version of LASSO, is applied in order to extract a consistent set of features, which are then used for learning a regression model. Visit Flu Detector's website

AB - We present an automated tool with a web interface for tracking the prevalence of Influenza-like Illness (ILI) in several regions of the United Kingdom using the contents of Twitter's microblogging service. Our data is comprised by a daily average of approximately 200,000 geolocated tweets collected by targeting 49 urban centres in the UK for a time period of 40 weeks. Official ILI rates from the Health Protection Agency (HPA) form our ground truth. Bolasso, the bootstrapped version of LASSO, is applied in order to extract a consistent set of features, which are then used for learning a regression model. Visit Flu Detector's website

M3 - Conference Contribution (Conference Proceeding)

BT - European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD)

PB - Springer

ER -

Flu Detector - Tracking Epidemics on Twitter

Abstract

Bibliographical note

Access to Document

Handle.net

Fingerprint

Cite this