Cascades are a popular construct to observe and study information propagation (or diffusion) in social media such as Twitter and are defined using notions of influence, activity, or discourse commonality (e.g., hashtags). While these notions of cascades lead to different perspectives, primarily cascades are modeled as trees. We argue in this thesis an alternative viewpoint of cascades as forests (of trees) which yields a richer vocabulary of features to understand information propagation. We propose to develop a framework to extract forests and analyze their growth by studying their evolution at the tree-level and at the node-level. Furthermore, we outline four different problems that use the forest framework. First, we show that such forests of information cascades can be used to design counter-contagion algorithms to disrupt the spread of negative campaigns or rumors. Secondly, we demonstrate how such forests of information cascades can give us a rich set of features (structural and temporal), which can be used to forecast information flow. Thirdly, we argue that cascades modeled as forests can help us glean social network sensors to detect future contagious outbreaks that occur in the social network. To conclude, we show preliminary results of an approach - a generative model, that can describe information cascades modeled as forests and can generate synthetic cascades with empirical properties mirroring cascades extracted from Twitter. / Ph. D. / How do memes spread on blogs? How and when does a hashtag become popular? Can we predict viral content? This thesis answers such questions by analyzing information dissemination in social media. Only few years ago the goal of modeling large social and technological systems would have been unattainable. However, in less than a decade the world wide web has transformed from a large static library that people only browse into a vast information resource where people interact with each other. Through the emergence of online social networking and social media, daily activities of hundreds of millions of people are migrating to the Web. Today the Web is a “sensor” that captures the pulse of human behavior: what we are thinking, what we are doing, and what we know. Moreover, social media activity has become precursors to several events, particularly disruptive ones like protests, strike, and “occupy” events. Therefore, analyzing and forecasting the emergence of such activity is an important social research problem. This thesis presents analytical and predictive models that can predict and detect bursts of activity in social media like Twitter. We also provide algorithmic tools that can effectively quell the spread of a rumor, predict viral content, and allow scientists to synthetically simulate such events computationally. The achievement of the thesis is to arm social scientists with tools that can assist in understanding some aspects of online social behavior.
| Identifer | oai:union.ndltd.org:VTETD/oai:vtechworks.lib.vt.edu:10919/83362 |
| Date | 18 May 2018 |
| Creators | Krishnan, Siddharth |
| Contributors | Computer Science, Heath, Lenwood S., Ras, Zbigniew W., Mitra, Tanushree, Ribbens, Calvin J., Marathe, Madhav Vishnu |
| Publisher | Virginia Tech |
| Source Sets | Virginia Tech Theses and Dissertation |
| Detected Language | English |
| Type | Dissertation |
| Format | ETD, application/pdf |
| Rights | In Copyright, http://rightsstatements.org/vocab/InC/1.0/ |
Page generated in 0.0019 seconds