This thesis addresses the modeling of events in social media, with an emphasis on the detection, tracking, and analysis of disaster-related events like the 2011 Tohuku Earthquake in Japan. Successful event modeling is critical for many applications including information search, entity extraction, disaster assessment, and emergency monitoring. However, modeling events in social media is challenging since: (i) social media is noisy and oftentimes incomplete, in the sense that users provide only partial evidence of their participation in an event; (ii) messages in social media are usually short, providing only little textual narrative (thereby making event detection difficult); and (iii) the size of short-lived events typically changes rapidly, growing and shrinking in sharp bursts. With these challenges in mind, this thesis proposes a framework for event modeling in social media and makes three major contributions: The first contribution is a signal processing-inspired approach for event detection from social media. Concretely, this research proposes an iterative spatial- temporal event mining algorithm for identifying and extracting topics from social media. One of the key aspects of the proposed algorithm is a signal processing-inspired approach for viewing spatial-temporal term occurrences as signals, analyzing the noise contained in the signals, and applying noise filters to improve the quality of event extraction from these signals. The second contribution is a new model of population dynamics of event-related crowds in social media as they first form, evolve, and eventually dissolve. To- ward robust population modeling, a duration model is proposed to predict the time users spend in a particular crowd. And then a time-evolving population model is designed for estimating the number of people departing a crowd, which enables the prediction of the total population remaining in a crowd. The third contribution of this thesis is a set of methods for event analytics for leveraging social media in an earthquake damage assessment scenario. Firstly, the difference between text tweets and image tweets is investigated, and then three features – tweet density, re-tweet density, and user tweeting count – are extracted to model the intensity attenuation of earthquakes. The observation that the relationship between social media activity vs. the loss/damage attenuation suggests that social media following a catastrophic event can provide rapid insight into the extent of damage.

As computing matures, it is becoming increasingly obvious that a change is necessary for the manner in which web services interact with users. Server-centric models are inconvenient for users. A new paradigm, Smart Interactions, provides a web service architecture which is centered around the user's needs, rather than the simplistic server view currently being used. The system responds to the individual user and is able to adapt to changes to better serve the user. The Smart Internet system helps the user accomplish their tasks efficiently and intuitively. An important aspect of Smart Interactions is that of cognitive support, which provides enhanced information and guidance to the system or user linked to the current task. This thesis examines predictive analytics and its application to cognitive support in Smart Interactions, and presents and evaluates a framework for using predictive analytic support within the Smart Internet model. / Thesis (Master, Computing) -- Queen's University, 2011-09-29 18:11:02.374

Thesis (M.S.)--Oregon State University, 2009. / Printout. Includes bibliographical references (leaves 85-91). Also available on the World Wide Web.

Thesis (Ph. D.)--Ohio State University, 2008. / Title from first page of PDF file. Includes bibliographical references (p. 104-109).

No description available.

abstract: Traditionally, visualization is one of the most important and commonly used methods of generating insight into large scale data. Particularly for spatiotemporal data, the translation of such data into a visual form allows users to quickly see patterns, explore summaries and relate domain knowledge about underlying geographical phenomena that would not be apparent in tabular form. However, several critical challenges arise when visualizing and exploring these large spatiotemporal datasets. While, the underlying geographical component of the data lends itself well to univariate visualization in the form of traditional cartographic representations (e.g., choropleth, isopleth, dasymetric maps), as the data becomes multivariate, cartographic representations become more complex. To simplify the visual representations, analytical methods such as clustering and feature extraction are often applied as part of the classification phase. The automatic classification can then be rendered onto a map; however, one common issue in data classification is that items near a classification boundary are often mislabeled. This thesis explores methods to augment the automated spatial classification by utilizing interactive machine learning as part of the cluster creation step. First, this thesis explores the design space for spatiotemporal analysis through the development of a comprehensive data wrangling and exploratory data analysis platform. Second, this system is augmented with a novel method for evaluating the visual impact of edge cases for multivariate geographic projections. Finally, system features and functionality are demonstrated through a series of case studies, with key features including similarity analysis, multivariate clustering, and novel visual support for cluster comparison. / Dissertation/Thesis / Doctoral Dissertation Computer Science 2016

abstract: The connections between different entities define different kinds of networks, and many such networked phenomena are influenced by their underlying geographical relationships. By integrating network and geospatial analysis, the goal is to extract information about interaction topologies and the relationships to related geographical constructs. In the recent decades, much work has been done analyzing the dynamics of spatial networks; however, many challenges still remain in this field. First, the development of social media and transportation technologies has greatly reshaped the typologies of communications between different geographical regions. Second, the distance metrics used in spatial analysis should also be enriched with the underlying network information to develop accurate models. Visual analytics provides methods for data exploration, pattern recognition, and knowledge discovery. However, despite the long history of geovisualizations and network visual analytics, little work has been done to develop visual analytics tools that focus specifically on geographically networked phenomena. This thesis develops a variety of visualization methods to present data values and geospatial network relationships, which enables users to interactively explore the data. Users can investigate the connections in both virtual networks and geospatial networks and the underlying geographical context can be used to improve knowledge discovery. The focus of this thesis is on social media analysis and geographical hotspots optimization. A framework is proposed for social network analysis to unveil the links between social media interactions and their underlying networked geospatial phenomena. This will be combined with a novel hotspot approach to improve hotspot identification and boundary detection with the networks extracted from urban infrastructure. Several real world problems have been analyzed using the proposed visual analytics frameworks. The primary studies and experiments show that visual analytics methods can help analysts explore such data from multiple perspectives and help the knowledge discovery process. / Dissertation/Thesis / Doctoral Dissertation Computer Science 2017

The thesis focuses on the behavior of users and the performance of the selected e-shop. The theoretical part of the thesis characterizes online shopping in the Czech Republic, commercial effectiveness of websites, and the most important online website traffic sources. The applied part of the thesis is devoted to competitive comparisons of attractiveness of supply and prices from the customer's perspective. The next part of the thesis characterizes user´s behavior and evaluates the effectiveness of various online marketing channels by using web analytics and user testing. The conclusion is devoted to recommendations aimed at increasing the performance of the particular e-shop.

Sistemas educacionais possuem diversas funcionalidades capazes de apoiar a interação entre alunos e professores de maneira dinâmica, síncrona e assíncrona. Uma das formas de monitorar a eficácia do processo educacional e por meio da utilização dos dados armazenados nesses sistemas como fonte de informação. Pesquisas em Learning Analytics, Academic Analytics e Mineração de Dados Educacionais, buscam explorar os dados de sistemas educacionais utilizando processamento analítico e técnicas de mineração de dados. No entanto, há uma serie de fatores que dificultam a gestão eficiente do processo educacional a partir dos dados de sistemas educacionais. A transformação de dados provenientes de diferentes tipos de sistemas educacionais, como Sistemas de Gestão de Aprendizagem e Sistemas Acadêmicos, e uma tarefa complexa devido a natureza heterogênea dos dados. Dados provenientes desses sistemas podem ser analisados considerando diferentes stakeholders, sob varias perspectivas e níveis de granularidade. Neste cenário, um modelo de referência para a descoberta de conhecimento a partir de dados de sistemas educacionais, denominado Modelo de Referência de Dados Educacionais (EDRM), foi desenvolvido neste trabalho. O EDRM e um modelo dimensional no formato star schema, estruturado em um Data Warehouse, projetado para ser uma fonte única de dados integrados e correlacionados voltada a tomada de decisão. Assim, e possível armazenar dados de diversas fontes, combina-los e, por fim, realizar analises que levem as instituições a desenvolver uma melhor compreensão, rastrear tendências e descobrir lacunas e ineficiências acerca do processo educacional. Neste trabalho, o EDRM foi validado por meio de um estudo de caso, utilizando bases de dados reais coletadas de diferentes sistemas educacionais. Os resultados mostram que o EDRM e eficiente em tarefas com diferentes objetivos, utilizando processamento analítico e mineração de dados. / Educational systems support dynamic, synchronous and asynchronous interaction between students and educators. Researches in Learning Analytics, Academic Analytics and Educational Data Mining explore data from educational systems for knowledge discovery through analytical processing, statistical analysis and data mining. However, there are some factors that hinder an efficient management of the educational process. The transformation of data from different kinds of educational system, as Learning Management Systems and Student Information Systems, can be even more difficult due to data heterogeneity. Data from these systems can be analyzed considering different stakeholders, under different perspectives and under different granularities. Motivated by this scenario, in this work we propose Modelo de Referência de Dados Educacionais (EDRM), a reference data model for knowledge discovery in data from educational systems. EDRM is an analytical model structured under a Data Warehouse architecture following a multidimensional data model. EDRM is projected for being an resource of integrated and correlated data focused in decision taking in the educational process. EDRM was developed considering a deep analysis of data and functionalities from different educational systems. In this sense, data from different kinds of systems and sources can be used unified, integrated and consistently. This allows institutions to better comprehend their data, as well as discover patterns, gaps and inefficiencies about their educational process. In this work, EDRM was validated in a case study using real-world databases from different educational systems. The results indicate that EDRM is efficient in tasks with different objectives, using Learning Analytics and Educational Data Mining techniques, and analyzing different perspectives.

Despite the emergence of artificial intelligence (AI) and machine learning (ML) in medicine and the resultant interest in predictive analytics in surgery, there remains a paucity of research on the actual impact of prediction models and their effect on surgeons’ risk assessment of post-surgical complications. This research evaluated how spinal surgeons predict post-surgical complications with and without additional information generated by a ML predictive model. The study was conducted in two stages. In the preliminary stage an ML prediction model for post-surgical complications in spine surgery was developed. In the second stage, a survey instrument was developed, using patient vignettes, to determine how providing ML model support affected surgeons’ predictions of post-surgical complications. Results show that support provided by a ML prediction model improved surgeons’ accuracy to correctly predict the presence or absence of a complication in patients undergoing spinal surgery from 49.1% to 54.8% (p=0.024). It is clear that predicting post-surgical complications in patients undergoing spinal surgery is difficult, for models and experienced surgeons, but it is not surprising that additional information provided by the ML model prediction was beneficial overall. This is the first study in the spine surgery literature that has evaluated the impact of a ML prediction model on surgeon prediction accuracy of post-surgical complications.