Influenza patients are invisible in the web: Traditional model still improves the state-of-the-art web based influenza surveillance

Eiji Aramaki, Sachiko Maskawa, Mizuki Morita

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Although web-based information extraction systems draw much attention, most of such systems assume that the web directly reflects the real world. For instance, Google flu trend, which is one of the-state-of-the-art influenza surveillance systems, relies on the basic idea that the amount of the influenza related search queries directly correlates with the number of the influenza patients. However, the real patients suffering from influenza symptoms are invisible in the web, because they do not use Internet. Considering this gap, this paper employs an infectious model, assuming that a potential patient utilizes Internet at the first sign of flu. The proposed model improves two types of the state-of-the-art systems, Google based system (from 0.837 correlation to 0.928) and Twitter based system (from 0.898 correlation to 0.918). This study demonstrated that a simple model could easily improve the web-based surveillance.

Original languageEnglish
Title of host publicationSelf-Tracking and Collective Intelligence for Personal Wellness - Papers from the AAAI Spring Symposium
Pages5-8
Number of pages4
VolumeSS-12-05
Publication statusPublished - 2012
Externally publishedYes
Event2012 AAAI Spring Symposium - Stanford, CA, United States
Duration: Mar 26 2012Mar 28 2012

Other

Other2012 AAAI Spring Symposium
CountryUnited States
CityStanford, CA
Period3/26/123/28/12

Fingerprint

Internet

ASJC Scopus subject areas

  • Artificial Intelligence

Cite this

Aramaki, E., Maskawa, S., & Morita, M. (2012). Influenza patients are invisible in the web: Traditional model still improves the state-of-the-art web based influenza surveillance. In Self-Tracking and Collective Intelligence for Personal Wellness - Papers from the AAAI Spring Symposium (Vol. SS-12-05, pp. 5-8)

Influenza patients are invisible in the web : Traditional model still improves the state-of-the-art web based influenza surveillance. / Aramaki, Eiji; Maskawa, Sachiko; Morita, Mizuki.

Self-Tracking and Collective Intelligence for Personal Wellness - Papers from the AAAI Spring Symposium. Vol. SS-12-05 2012. p. 5-8.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Aramaki, E, Maskawa, S & Morita, M 2012, Influenza patients are invisible in the web: Traditional model still improves the state-of-the-art web based influenza surveillance. in Self-Tracking and Collective Intelligence for Personal Wellness - Papers from the AAAI Spring Symposium. vol. SS-12-05, pp. 5-8, 2012 AAAI Spring Symposium, Stanford, CA, United States, 3/26/12.
Aramaki E, Maskawa S, Morita M. Influenza patients are invisible in the web: Traditional model still improves the state-of-the-art web based influenza surveillance. In Self-Tracking and Collective Intelligence for Personal Wellness - Papers from the AAAI Spring Symposium. Vol. SS-12-05. 2012. p. 5-8
Aramaki, Eiji ; Maskawa, Sachiko ; Morita, Mizuki. / Influenza patients are invisible in the web : Traditional model still improves the state-of-the-art web based influenza surveillance. Self-Tracking and Collective Intelligence for Personal Wellness - Papers from the AAAI Spring Symposium. Vol. SS-12-05 2012. pp. 5-8
@inproceedings{1040f41866ca4d4da1723425d2b5e3a2,
title = "Influenza patients are invisible in the web: Traditional model still improves the state-of-the-art web based influenza surveillance",
abstract = "Although web-based information extraction systems draw much attention, most of such systems assume that the web directly reflects the real world. For instance, Google flu trend, which is one of the-state-of-the-art influenza surveillance systems, relies on the basic idea that the amount of the influenza related search queries directly correlates with the number of the influenza patients. However, the real patients suffering from influenza symptoms are invisible in the web, because they do not use Internet. Considering this gap, this paper employs an infectious model, assuming that a potential patient utilizes Internet at the first sign of flu. The proposed model improves two types of the state-of-the-art systems, Google based system (from 0.837 correlation to 0.928) and Twitter based system (from 0.898 correlation to 0.918). This study demonstrated that a simple model could easily improve the web-based surveillance.",
author = "Eiji Aramaki and Sachiko Maskawa and Mizuki Morita",
year = "2012",
language = "English",
isbn = "9781577355540",
volume = "SS-12-05",
pages = "5--8",
booktitle = "Self-Tracking and Collective Intelligence for Personal Wellness - Papers from the AAAI Spring Symposium",

}

TY - GEN

T1 - Influenza patients are invisible in the web

T2 - Traditional model still improves the state-of-the-art web based influenza surveillance

AU - Aramaki, Eiji

AU - Maskawa, Sachiko

AU - Morita, Mizuki

PY - 2012

Y1 - 2012

N2 - Although web-based information extraction systems draw much attention, most of such systems assume that the web directly reflects the real world. For instance, Google flu trend, which is one of the-state-of-the-art influenza surveillance systems, relies on the basic idea that the amount of the influenza related search queries directly correlates with the number of the influenza patients. However, the real patients suffering from influenza symptoms are invisible in the web, because they do not use Internet. Considering this gap, this paper employs an infectious model, assuming that a potential patient utilizes Internet at the first sign of flu. The proposed model improves two types of the state-of-the-art systems, Google based system (from 0.837 correlation to 0.928) and Twitter based system (from 0.898 correlation to 0.918). This study demonstrated that a simple model could easily improve the web-based surveillance.

AB - Although web-based information extraction systems draw much attention, most of such systems assume that the web directly reflects the real world. For instance, Google flu trend, which is one of the-state-of-the-art influenza surveillance systems, relies on the basic idea that the amount of the influenza related search queries directly correlates with the number of the influenza patients. However, the real patients suffering from influenza symptoms are invisible in the web, because they do not use Internet. Considering this gap, this paper employs an infectious model, assuming that a potential patient utilizes Internet at the first sign of flu. The proposed model improves two types of the state-of-the-art systems, Google based system (from 0.837 correlation to 0.928) and Twitter based system (from 0.898 correlation to 0.918). This study demonstrated that a simple model could easily improve the web-based surveillance.

UR - http://www.scopus.com/inward/record.url?scp=84864972031&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84864972031&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84864972031

SN - 9781577355540

VL - SS-12-05

SP - 5

EP - 8

BT - Self-Tracking and Collective Intelligence for Personal Wellness - Papers from the AAAI Spring Symposium

ER -