Finding Healthcare Issues with Search Engine Queries and Social Network Data

Finding Healthcare Issues with Search Engine Queries and Social Network Data

M. Ikram Ullah Lali (Department of Computer Science & IT, University of Sargodha, Sargodha, Pakistan), Raza Ul Mustafa (Department of Computer Science, COMSATS Institute of Information Technology, Sahiwal, Pakistan), Kashif Saleem (Centre of Excellence in Information Assurance (CoEIA), King Saud University, Riyadh, Saudi Arabia), M. Saqib Nawaz (Department of Information Science, School of Mathematical Sciences, Peking University, Beijing, China), Tehseen Zia (Department of Computer Science, COMSATS Institute of Information Technology, Islamabad, Pakistan) and Basit Shahzad (College of Computer and Information Sciences, King Saud University, Riyadh, Saudi Arabia)
Copyright: © 2017 |Pages: 15
DOI: 10.4018/IJSWIS.2017010104
OnDemand PDF Download:
$37.50

Abstract

Search engines and social networks are two entirely different data sources that can provide valuable information about Influenza. While search engine hosts can deliver popular queries (or terms) used for searching the Influenza related information, the social networks contain useful links of information sources that people have found valuable. The authors hypothesize that such data sources can provide vital first-hand information. In this article, they have proposed a methodology for detecting the information sources from social networks, particularly Twitter. The data filtering and source finding tasks are posed as classification tasks. Search engine queries are used for extracting related dataset. Results have shown that propose approach can be beneficial for extracting useful information regarding side effects, medications and to track geographical location of epidemics affected area.
Article Preview

1. Introduction

Influenza is a contagious viral infection that globally affects 20–30% children and 5-10% adults each year. This disease causes 3-5 Million cases of illness and approximately 0.25-0.5 Million deaths (Influenza Fact Sheet, 2015). Centre for Disease Control (CDC) in U.S and European Influenza Surveillance Scheme (EISS) in Europe are used to collect Influenza data from clinical diagnosis. However, CDC and EISS systems are almost entirely manual and it takes time leg of two weeks for acquisition of clinical data. CDC and EISS identify and categorize diseases as or after the occurrence of disease and do not provide any kind of advance warnings for disease outbreak. Moreover, their Influenza related data are no longer current when the data is released to public and healthcare professionals. Public health institutions and authorities are required to predict the breakout of Influenza at the earliest time in order to ensure effective prevention mechanism.

Nowadays, Internet is affecting and facilitating nearly every aspect of modern life, from healthcare and education to government and business. In a survey (Health Fact Sheet, 2015), 72% internet users have tried to avail the health information online in 2015. Furthermore, the online health seekers of about 75% utilized the search engines like Google, Bing, or Yahoo and of about 15% looked for health related sites, such as WebMD. 3% users looked for healthcare information on Wikipedia and 2% started through social networks like Facebook, Twitter, etc. Queries entered in search engines or posted on social media provide valuable information related to detection of infectious diseases. Twitter is an online social networking site that offers users a platform for writing and posting messages up to 140 characters. Twitter effectively takes part in any mega event happening around the world and is used before, during and after live events (Bollen et al., 2011).

Studies in (Ginsberg et al., 2009; Hulth et al., 2009; Palet et al., 2009; Achrekar et al, 2011, Aramaki et al., 2011; Polgreen et al., 2008) show that epidemics trend can be detected with information available on Web and a strong correlation exists in the frequency of online search queries and tweets with epidemics events (Xu et al., 2011). Therefore, the patterns of people’s behavior in searching, sharing and posting on internet may give us early indications about the people expectations and concerns in future. For example, an analysis was conducted by Ettredge et al. (Ettredge et al., 2005) on online job search, which generated an informative statistics on the rate of unemployment. The studies on healthcare information searches can also offer useful statistics. Eysenbach (2006) showed that most of the clicks on a sponsored link via AdSense (a free advertisement placement platform provided by Google) by search terms “flu” or “flu symptoms” from a person in Canada accurately forecasted the Canada Public Health Agency Flu Watch reports. Keyword selection is one of the most difficult task (Mustafa et al., 2015). Therefore, search query logs investigation for keywords or terms related to infectious disease can offer a novel approach for internet based detection, monitoring and surveillance of infectious disease.

Complete Article List

Search this Journal:
Reset
Open Access Articles
Volume 13: 4 Issues (2017): 3 Released, 1 Forthcoming
Volume 12: 4 Issues (2016)
Volume 11: 4 Issues (2015)
Volume 10: 4 Issues (2014)
Volume 9: 4 Issues (2013)
Volume 8: 4 Issues (2012)
Volume 7: 4 Issues (2011)
Volume 6: 4 Issues (2010)
Volume 5: 4 Issues (2009)
Volume 4: 4 Issues (2008)
Volume 3: 4 Issues (2007)
Volume 2: 4 Issues (2006)
Volume 1: 4 Issues (2005)
View Complete Journal Contents Listing