Live streaming has risen to significant popularity in the recent past and largely this live streaming is a feature of existing social networks like Facebook, Instagram, and Snapchat. However, there does exist at least one social network entirely devoted to live streaming, and specifically the live streaming of video games, Twitch. This social network is unique for a number of reasons, not least because of its hyper-focus on live content and this uniqueness has challenges for social media researchers.

Despite this uniqueness, almost no scientific work has been performed on this public social network. Thus, it is unclear what user interaction features present on other social networks exist on Twitch. Investigating the interactions between users and identifying which, if any, of the common user behaviors on social network exist on Twitch is an important step in understanding how Twitch fits in to the social media ecosystem. For example, there are users that have large followings on Twitch and amass a large number of viewers, but do those users exert influence over the behavior of other user the way that popular users on Twitter do?

This task, however, will not be trivial. The same hyper-focus on live content that makes Twitch unique in the social network space invalidates many of the traditional approaches to social network analysis. Thus, new algorithms and techniques must be developed in order to tap this data source. In this thesis, a novel algorithm for finding games whose releases have made a significant impact on the network is described as well as a novel algorithm for detecting and identifying influential players of games. In addition, the Twitch network is described in detail along with the data that was collected in order to power the two previously described algorithms.

Social media has become a primary platform for real-time information sharing among users. News on social media spreads faster than traditional outlets and millions of users turn to this platform to receive the latest updates on major events especially disasters. Social media bridges the gap between the people who are affected by disasters, volunteers who offer contributions, and first responders. On the other hand, social media is a fertile ground for malicious users who purposefully disturb the relief processes facilitated on social media. These malicious users take advantage of social bots to overrun social media posts with fake images, rumors, and false information. This process causes distress and prevents actionable information from reaching the affected people. Social bots are automated accounts that are controlled by a malicious user and these bots have become prevalent on social media in recent years.

In spite of existing efforts towards understanding and removing bots on social media, there are at least two drawbacks associated with the current bot detection algorithms: general-purpose bot detection methods are designed to be conservative and not label a user as a bot unless the algorithm is highly confident and they overlook the effect of users who are manipulated by bots and (unintentionally) spread their content. This study is trifold. First, I design a Machine Learning model that uses content and context of social media posts to detect actionable ones among them; it specifically focuses on tweets in which people ask for help after major disasters. Second, I focus on bots who can be a facilitator of malicious content spreading during disasters. I propose two methods for detecting bots on social media with a focus on the recall of the detection. Third, I study the characteristics of users who spread the content of malicious actors. These features have the potential to improve methods that detect malicious content such as fake news.

Graphs are commonly used visualization tools in a variety of fields. Algorithms have been proposed that claim to improve the readability of graphs by reducing edge crossings, adjusting edge length, or some other means. However, little research has been done to determine which of these algorithms best suit human perception for particular graph properties. This thesis explores four different graph properties: average local clustering coefficient (ALCC), global clustering coefficient (GCC), number of triangles (NT), and diameter. For each of these properties, three different graph layouts are applied to represent three different approaches to graph visualization: multidimensional scaling (MDS), force directed (FD), and tsNET. In a series of studies conducted through the crowdsourcing platform Amazon Mechanical Turk, participants are tasked with discriminating between two graphs in order to determine their just noticeable differences (JNDs) for the four graph properties and three layout algorithm pairs. These results are analyzed using previously established methods presented by Rensink et al. and Kay and Heer.The average JNDs are analyzed using a linear model that determines whether the property-layout pair seems to follow Weber's Law, and the individual JNDs are run through a log-linear model to determine whether it is possible to model the individual variance of the participant's JNDs. The models are evaluated using the R2 score to determine if they adequately explain the data and compared using the Mann-Whitney pairwise U-test to determine whether the layout has a significant effect on the perception of the graph property. These tests indicate that the data collected in the studies can not always be modelled well with either the linear model or log-linear model, which suggests that some properties may not follow Weber's Law. Additionally, the layout algorithm is not found to have a significant impact on the perception of some of these properties.

Causality analysis is the process of identifying cause-effect relationships among variables. This process is challenging because causal relationships cannot be tested solely based on statistical indicators as additional information is always needed to reduce the ambiguity caused by factors beyond those covered by the statistical test. Traditionally, controlled experiments are carried out to identify causal relationships, but recently there is a growing interest in causality analysis with observational data due to the increasing availability of data and tools. This type of analysis will often involve automatic algorithms that extract causal relations from large amounts of data and rely on expert judgment to scrutinize and verify the relations. Over-reliance on these automatic algorithms is dangerous because models trained on observational data are susceptible to bias that can be difficult to spot even with expert oversight. Visualization has proven to be effective at bridging the gap between human experts and statistical models by enabling an interactive exploration and manipulation of the data and models. This thesis develops a visual analytics framework to support the interaction between human experts and automatic models in causality analysis. Three case studies were conducted to demonstrate the application of the visual analytics framework in which feature engineering, insight generation, correlation analysis, and causality inspections were showcased.

Conservation planning is fundamental to guarantee the survival of endangered species and to preserve the ecological values of some ecosystems. Planning land acquisitions increasingly requires a landscape approach to mitigate the negative impacts of spatial threats such as urbanization, agricultural development, and climate change. In this context, landscape connectivity and compactness are vital characteristics for the effective functionality of conservation reserves. Connectivity allows species to travel across landscapes, facilitating the flow of genes across populations from different protected areas. Compactness measures the spatial dispersion of protected sites, which can be used to mitigate risk factors associated with species leaving and re-entering the reserve. This research proposes an optimization model to identify areas to protect while enforcing connectivity and compactness. In the suggested projected area, this research builds upon existing methods and develops an alternative metric of compactness that penalizes the selection of patches of land with few protected neighbors. The new metric is referred as leaf because it intends to minimize the number of selected areas with 1 neighboring protected area. The model includes budget and minimum selected area constraints to reflect realistic financial and ecological requirements. Using a lexicographic approach, the model can improve the compactness of conservation reserves obtained by other methods. The use of the model is illustrated by solving instances of up to 1100 patches.

In recent years, the rise in social media usage both vertically in terms of the number of users by platform and horizontally in terms of the number of platforms per user has led to data explosion.

User-generated social media content provides an excellent opportunity to mine data of interest and to build resourceful applications. The rise in the number of healthcare-related social media platforms and the volume of healthcare knowledge available online in the last decade has resulted in increased social media usage for personal healthcare. In the United States, nearly ninety percent of adults, in the age group 50-75, have used social media to seek and share health information. Motivated by the growth of social media usage, this thesis focuses on healthcare-related applications, study various challenges posed by social media data, and address them through novel and effective machine learning algorithms.



The major challenges for effectively and efficiently mining social media data to build functional applications include: (1) Data reliability and acceptance: most social media data (especially in the context of healthcare-related social media) is not regulated and little has been studied on the benefits of healthcare-specific social media; (2) Data heterogeneity: social media data is generated by users with both demographic and geographic diversity; (3) Model transparency and trustworthiness: most existing machine learning models for addressing heterogeneity are considered as black box models, not many providing explanations for why they do what they do to trust them.

In response to these challenges, three main research directions have been investigated in this thesis: (1) Analyzing social media influence on healthcare: to study the real world impact of social media as a source to offer or seek support for patients with chronic health conditions; (2) Learning from task heterogeneity: to propose various models and algorithms that are adaptable to new social media platforms and robust to dynamic social media data, specifically on modeling user behaviors, identifying similar actors across platforms, and adapting black box models to a specific learning scenario; (3) Explaining heterogeneous models: to interpret predictive models in the presence of task heterogeneity. In this thesis, novel algorithms with theoretical analysis from various aspects (e.g., time complexity, convergence properties) have been proposed. The effectiveness and efficiency of the proposed algorithms is demonstrated by comparison with state-of-the-art methods and relevant case studies.

Multi-view learning, a subfield of machine learning that aims to improve model performance by training on multiple views of the data, has been studied extensively in the past decades. It is typically applied in contexts where the input features naturally form multiple groups or views. An example of a naturally multi-view context is a data set of websites, where each website is described not only by the text on the page, but also by the text of hyperlinks pointing to the page. More recently, various studies have demonstrated the initial success of applying multi-view learning on single-view data with multiple artificially constructed views. However, there lacks a systematic study regarding the effectiveness of such artificially constructed views. To bridge this gap, this thesis begins by providing a high-level overview of multi-view learning with the co-training algorithm. Co-training is a classic semi-supervised learning algorithm that takes advantage of both labelled and unlabelled examples in the data set for training. Then, the thesis presents a web-based tool developed in Python allowing users to experiment with and compare the performance of multiple view construction approaches on various data sets. The supported view construction approaches in the web-based tool include subsampling, Optimal Feature Set Partitioning, and the genetic algorithm. Finally, the thesis presents an empirical comparison of the performance of these approaches, not only against one another, but also against traditional single-view models. The findings show that a simple subsampling approach combined with co-training often outperforms both the other view construction approaches, as well as traditional single-view methods.

An old proverb claims that “two heads are better than one”. Crowdsourcing research and practice have taken this to heart, attempting to show that thousands of heads can be even better. This is not limited to leveraging a crowd’s knowledge, but also their creativity—the ability to generate something not only useful, but also novel. In practice, there are initiatives such as Free and Open Source Software communities developing innovative software. In research, the field of crowdsourced creativity, which attempts to design scalable support mechanisms, is blooming. However, both contexts still present many opportunities for advancement.

In this dissertation, I seek to advance both the knowledge of limitations in current technologies used in practice as well as the mechanisms that can be used for large-scale support. The overall research question I explore is: “How can we support large-scale creative collaboration in distributed online communities?” I first advance existing support techniques by evaluating the impact of active support in brainstorming performance. Furthermore, I leverage existing theoretical models of individual idea generation as well as recommender system techniques to design CrowdMuse, a novel adaptive large-scale idea generation system. CrowdMuse models users in order to adapt itself to each individual. I evaluate the system’s efficacy through two large-scale studies. I also advance knowledge of current large-scale practices by examining common communication channels under the lens of Creativity Support Tools, yielding a list of creativity bottlenecks brought about by the affordances of these channels. Finally, I connect both ends of this dissertation by deploying CrowdMuse in an Open Source online community for two weeks. I evaluate their usage of the system as well as its perceived benefits and issues compared to traditional communication tools.

This dissertation makes the following contributions to the field of large-scale creativity: 1) the design and evaluation of a first-of-its-kind adaptive brainstorming system; 2) the evaluation of the effects of active inspirations compared to simple idea exposure; 3) the development and application of a set of creativity support design heuristics to uncover creativity bottlenecks; and 4) an exploration of large-scale brainstorming systems’ usefulness to online communities.

In the artificial intelligence literature, three forms of reasoning are commonly employed to understand agent behavior: inductive, deductive, and abductive.  More recently, data-driven approaches leveraging ideas such as machine learning, data mining, and social network analysis have gained popularity. While data-driven variants of the aforementioned forms of reasoning have been applied separately, there is little work on how data-driven approaches across all three forms relate and lend themselves to practical applications. Given an agent behavior and the percept sequence, how one can identify a specific outcome such as the likeliest explanation? To address real-world problems, it is vital to understand the different types of reasonings which can lead to better data-driven inference.  

This dissertation has laid the groundwork for studying these relationships and applying them to three real-world problems. In criminal modeling, inductive and deductive reasonings are applied to early prediction of violent criminal gang members. To address this problem the features derived from the co-arrestee social network as well as geographical and temporal features are leveraged. Then, a data-driven variant of geospatial abductive inference is studied in missing person problem to locate the missing person. Finally, induction and abduction reasonings are studied for identifying pathogenic accounts of a cascade in social networks.

In recent years, the food, energy, and water (FEW) nexus has become a topic of considerable importance and has spurred research in many scientific and technical fields. This increased interest stems from the high level, and broad area, of impact that could occur in the long term if the interactions between these complex FEW sectors are incorrectly or only partially defined. For this reason, a significant amount of interdisciplinary collaboration is needed to accurately define these interactions and produce viable solutions to help sustain and secure resources within these sectors. Providing tools that effectively promote interdisciplinary collaboration would allow for the development of a better understanding of FEW nexus interactions, support FEW policy-making under uncertainty, facilitate identification of critical design requirements for FEW visualizations, and encourage proactive FEW visualization design.

The goal of this research will be the completion of 3 primary objectives: (i) specify visualization design requirements relating to the FEW nexus; (ii) develop visualization approaches for the FEW nexus; and (iii) provide a comparison of current FEW visualization approaches against the proposed visualization approach. These objectives will be accomplished by reviewing graph-based visualization, network evolution, and visual analysis of volume data tasks, discussion with domain experts, examination of currently used visualization methods in FEW research, and conduction of a user study. This will provide a more thorough and representative depiction of the FEW nexus, as well as a basis for further research in the area of FEW visualization. This research will enhance collaboration between policymakers and domain experts in an attempt to encourage in-depth nexus research that will help support informed policy-making and promote future resource security.