Skip to Main Content
Frequently Asked Questions
Submit an ETD
Global Search Box
Need Help?
Keyword Search
Participating Institutions
Advanced Search
School Logo
Files
File List
Thesis by Li Zhou corrected final format approved LW CN 4-27-15.pdf (1.39 MB)
ETD Abstract Container
Abstract Header
Information Diffusion on Twitter
Author Info
Zhou, Li
Permalink:
http://rave.ohiolink.edu/etdc/view?acc_num=dayton1430183977
Abstract Details
Year and Degree
2015, Master of Computer Science (M.C.S.), University of Dayton, Computer Science.
Abstract
With the wide and increasing application areas of social network, both business and academia pay great attention on it. Studies on information diffusion are one of the emerging but still understudied areas. Most of the studies focus on how to leverage the link structure of social network to maximize information diffusion and base their algorithms development and verification on virtual social network structures. As such, researchers may have limited information diffusion within a certain boundary. Furthermore, the application of the algorithms and findings could be weak when facing the real social network structure. To address the gaps of literature, this thesis investigates the impact of single information source and multiple information sources on information diffusion patterns with real world public social network structure, which is collected by designing a functional and ready-to-use data crawling structure. To answer the research question, a simulation experiment was designed and executed. With the simulation data, ANOVA and ordinary least square regress were applied. According to the analysis results, I found that information diffusion patterns vary significantly between single information source and multiple information sources. Specifically, the number of individuals holding the information and the number of individuals retweeting the information, information diffusion pattern parameters based on a variant of susceptible-infected-recovered (SIR) model, increase when there are multiple information sources. The result has significant implications for both academic and managerial area. Specifically, from academic perspective, by identifying the differences of information diffusion patterns resulting from attributes of information source, it would facilitate the researchers to efficiently choose information source detection techniques. From managerial perspective, applicants could design their information source/sources based on their desired information diffusion pattern.
Committee
Zhongmei Yao (Advisor)
Pages
42 p.
Subject Headings
Computer Science
Keywords
Social Network
;
Web Crawling
;
Information Diffusion
;
Simulation
;
ANOVA
;
OLS
Recommended Citations
Refworks
EndNote
RIS
Mendeley
Citations
Zhou, L. (2015).
Information Diffusion on Twitter
[Master's thesis, University of Dayton]. OhioLINK Electronic Theses and Dissertations Center. http://rave.ohiolink.edu/etdc/view?acc_num=dayton1430183977
APA Style (7th edition)
Zhou, Li.
Information Diffusion on Twitter.
2015. University of Dayton, Master's thesis.
OhioLINK Electronic Theses and Dissertations Center
, http://rave.ohiolink.edu/etdc/view?acc_num=dayton1430183977.
MLA Style (8th edition)
Zhou, Li. "Information Diffusion on Twitter." Master's thesis, University of Dayton, 2015. http://rave.ohiolink.edu/etdc/view?acc_num=dayton1430183977
Chicago Manual of Style (17th edition)
Abstract Footer
Document number:
dayton1430183977
Download Count:
2,977
Copyright Info
© 2015, all rights reserved.
This open access ETD is published by University of Dayton and OhioLINK.