Learning and gaining knowledge of Roman history is an area of interest for students and citizens at large. This is an example of a subject with great sweep (with many interrelated sub-topics over, in this case, a 3,000 year history) that is hard to grasp by any individual and, in its full detail, is not available as a coherent story. In this paper, we propose a visual analytics approach to construct a data driven view of Roman history based on a large collection of Wikipedia articles. Extracting and enabling the discovery of useful knowledge on events, places, times, and their connections from large amounts of textual data has always been a challenging task. To this aim, we introduce VAiRoma, a visual analytics system that couples state-of-the-art text analysis methods with an intuitive visual interface to help users make sense of events, places, times, and more importantly, the relationships between them. VAiRoma goes beyond textual content exploration, as it permits users to compare, make connections, and externalize the findings all within the visual interface. As a result, VAiRoma allows users to learn and create new knowledge regarding Roman history in an informed way. We evaluated VAiRoma with 16 participants through a user study, with the task being to learn about roman piazzas through finding relevant articles and new relationships. Our study results showed that the VAiRoma system enables the participants to find more relevant articles and connections compared to Web searches and literature search conducted in a roman library. Subjective feedback on VAiRoma was also very positive. In addition, we ran two case studies that demonstrate how VAiRoma can be used for deeper analysis, permitting the rapid discovery and analysis of a small number of key documents even when the original collection contains hundreds of thousands of documents.

Big Data Analytics is getting a great deal of attention in the business and government communities. If it lives up to its name, visual analytics will be a prime path by which visualization competes successfully in this arena. This paper discusses some fundamental work we have done in this area through integration of interactive visualization and automated analysis methods and the applications that have resulted.

The phenomenally wide-adoption of social media has stimulated a new means in organizing and carrying-out modern social movements. Exemplified by the Occupy Movement (OM), rich information, including protest-related events and people's responses to those events, is posted and shared through social media sites such as Twitter. However, it is quite challenging to make sense of such valuable information in a collective manner, as it is often submerged by all the other content on Twitter. In this case study, we demonstrate the combination of computational methods (e.g., topic modeling and event detection) and interactive visual analytics in facilitating users to examine how relevant tweets can reflect a collective view of a social movement. In particular, we focus on discovering and associating key events throughout the OM. Based on the event frequencies, our system helps users to divide the movement into three distinct stages. Information regarding "what" the events were about, "when" and "where" the events occurred, and "who" were involved is extracted from the tweets to describe each stage of the movement. The resulting case studies show that we can indeed construct a collective diary of the social movement by analyzing events extracted from the content of the tweets.

No abstract