Abstract

Syndromic surveillance of emerging diseases is crucial for timely planning and execution of epidemic response from both local and global authorities. Traditional sources of information employed by surveillance systems are not only slow but also impractical for developing countries. Internet and social media provide a free source of a large amount of data which can be utilized for Syndromic surveillance.

We propose developing a prototype system for gathering, storing, filtering and presenting data collected from Twitter (a popular social media platform). Since social media data is inherently noisy we describe ways to preprocess the gathered data and utilize SVM (Support Vector Machine) to identify tweets relating to influenza like symptoms. The filtered data is presented in a web application, which allows the user to explore the underlying data in both spatial and temporal dimensions.

Library of Congress Subject Headings

Communicable diseases--Data processing; Epidemiology--Data processing; Data mining; Social media

Publication Date

5-19-2016

Document Type

Thesis

Student Type

Graduate

Degree Name

Bioinformatics (MS)

Department, Program, or Center

Thomas H. Gosnell School of Life Sciences (COS)

Advisor

Jim Leone

Advisor/Committee Member

Gary Skuse

Advisor/Committee Member

Brian Tomaszewski

Comments

Physical copy available from RIT's Wallace Library at RA643 .A79 2016

Campus

RIT – Main Campus

Download

Share

COinS