Main thesis objective is in social network analysis. Theoretic will describe their origin, development and circumstances under which certain social networks were built. Part with analysis will concern in how to compete with business rivals using CI and will search techniques for proper facebook usage as a company's CI tool by rating of chosen fan facebook pages.

<p>Care of patients with chronic conditions is complicated and usually includes large number of healthcare providers. Understanding the team structure and networks of healthcare providers help to make informed decisions for health policy makers and design of wellness programs by identifying the influencers in the network. This work presents a novel approach to assess the collaboration of healthcare providers involved in the care of patients with chronic conditions and the impact on patient outcomes. </p> <p>In the first study, we assessed a patient population needs, preventive service utilization, and impact of an onsite clinic as an intervention on preventive service utilization patterns over a three-year period. Classification models were developed to identify groups of patients with similar characteristics and healthcare utilization. Logistic regression models identified patient factors that impacted their utilization of preventive health services in the onsite clinic vs. other providers. Females had higher utilizations compared to males. Type of insurance coverages, and presence of diabetes/hypertension were significant factors that impacted utilization. The first study framework helps to understand the patient population characteristics and role of specific providers (onsite clinic), however, it does not provide information about the teams of healthcare providers involved in the care process. </p> <p>Considering the high prevalence of diabetes in the patient cohort of study 1, in the second study, we followed the patient cohort with diabetes from study 1 and extracted their healthcare providers over a two-year period. A framework based on the social network analysis was presented to assess the healthcare providers’ networks and teams involved in the care of diabetes. The relations between healthcare providers were generated based on the patient sharing relations identified from the claims data. A multi-scale community detection algorithm was used to identify groups of healthcare providers more closely working together. Centrality measures of the social network identified the influencers in the overall network and each community. Mail-order and retail pharmacies were identified as central providers in the overall network and majority of communities. This study presented metrics and approach for assessment of provider collaboration. To study how these collaborative relations impact the patients, in the last study, we presented a framework to assess impacts of healthcare provider collaboration on patient outcomes. </p> <p>We focused on patients with diabetes, hypertension, and hyperlipidemia due to their similar healthcare needs and utilization. Similar to the second study, social network analysis and a multi-scale community detection algorithm were used to identify networks and communities of healthcare providers. We identified providers who were the majority source of care for patients over a three-year period. Regression models using generalized estimating equations were developed to assess the impact of majority source of care provider community-level centrality on patient outcomes. Higher connectedness (higher degree centrality) and higher access (higher closeness centrality) of the majority source of care provider were associated with reduced number of inpatient hospitalization and emergency department visits. </p> <p>This research proposed a framework based on the social network analysis that provides metrics for assessment of care team relations using large-scale health data. These metrics help implementation experts to identify influencers in the network for better design of care intervention programs. The framework is also useful for health services researchers to assess impact of care teams’ relations on patient outcomes. </p> <br> <p> </p>

abstract: Many existing applications of machine learning (ML) to cybersecurity are focused on detecting malicious activity already present in an enterprise. However, recent high-profile cyberattacks proved that certain threats could have been avoided. The speed of contemporary attacks along with the high costs of remediation incentivizes avoidance over response. Yet, avoidance implies the ability to predict - a notoriously difficult task due to high rates of false positives, difficulty in finding data that is indicative of future events, and the unexplainable results from machine learning algorithms. In this dissertation, these challenges are addressed by presenting three artificial intelligence (AI) approaches to support prioritizing defense measures. The first two approaches leverage ML on cyberthreat intelligence data to predict if exploits are going to be used in the wild. The first work focuses on what data feeds are generated after vulnerability disclosures. The developed ML models outperform the current industry-standard method with F1 score more than doubled. Then, an approach to derive features about who generated the said data feeds is developed. The addition of these features increase recall by over 19% while maintaining precision. Finally, frequent itemset mining is combined with a variant of a probabilistic temporal logic framework to predict when attacks are likely to occur. In this approach, rules correlating malicious activity in the hacking community platforms with real-world cyberattacks are mined. They are then used in a deductive reasoning approach to generate predictions. The developed approach predicted unseen real-world attacks with an average increase in the value of F1 score by over 45%, compared to a baseline approach. / Dissertation/Thesis / Doctoral Dissertation Computer Science 2019

No description available.

Analysis of Inferred Social Networks While the social network analysis (SNA) is not a new science branch, thanks to the boom of social media platforms in recent years new methods and approaches appear with increasing frequency. However, not all datasets have network structure visible at first glance. We believe that every reasonable interconnected system of data hides a social network, which can be inferred using specific methods. In this thesis we examine such social network, inferred from the real-world data of a smaller bank. We also review some of the most commonly used methods in SNA and then apply them on our complex network, expecting to find structures typical for traditional social networks.

This paper is about application of various data mining methods in social networks and social media area. It reveals basic principles of social media with the aim to high information potential of usage of the data from social networks. This is demonstrated on selected data mining methods, especially Social Network Analysis and Sentiment Analysis. Other opportunities of using social media data are shown in chapter about Social Media Monitoring tools. All these chapters are supplemented by practical examples and particular researches. Last chapter reveals visions and threats, which can bring data mining in the future. Keywords Data mining, social networks, social media, social network analysis, sentiment analysis, social media monitoring

No description available.

No description available.

No description available.

Analysis of large network datasets has become increasingly important. Algorithms have been designed to find many kinds of structure, with numerous applications across the social and biological sciences. However, a tradeoff is always present between accuracy and scalability; otherwise promising techniques can be computationally infeasible when applied to networks with huge numbers of nodes and edges. One way of extending the reach of network analysis is to sparsify the graph by retaining only a subset of its edges. The reduced network could prove much more tractable. For this thesis, I propose a new sparsification algorithm that preserves the properties of a random walk on the network. Specifically, the algorithm finds a subset of edges that best preserves the stationary distribution of a random walk by minimizing the Kullback-Leibler divergence between a walk on the original and sparsified graphs. A highly efficient greedy search strategy is developed to optimize this objective. Experimental results are presented that test the performance of the algorithm on the influence maximization task. These results demonstrate that sparsification allows near-optimal solutions to be found in a small fraction of the runtime that would required using the full network. Two cases are shown where sparsification allows an influence maximization algorithm to be applied to a dataset that previous work had considered intractable.