Projects

Collective Sense Making of Terrorist Attacks

Social media has been central to the public's response to terrorism -- from the transmission of breaking news, to the offering of social support, to the dissemination of radical messages. This project utilizes the social media data to investigate the reactions of individuals during the terrorist attacks in order to enhance the public resilience to terrorist incidents. The work is in part supported by an NSF award.
read more »

Threat Perception Following Mass Violence Events

How does experiencing mass violence, terrorism, or other traumatic events shape individuals' perceive and respond to their social world? In this project, we empirically study how emotionally potent media coverage of a real-world threat alters people's perception of risk and threats. The work is in part supported by an NSF award.
read more »

Pitt Smart Living

Urban planners have begun to realize that a truly sustainable transportation and urban environment in general, requires a shift to multimodal transportation. This project is a pilot study to evaluate the benefits of making real­time transportation information available to city­dwellers and also the potential impact of incentives as a way to encourage pro-­social behavior. We will develop, deploy, and evaluate techniques that will integrate information for increasing the utilization and quality of public transportation. The work is in part supported by an NSF award.
read more »

Diffusion Analytics for Public Policy Research

Stability in social, technical, and financial systems, as well as the capacity of organizations to work across borders, requires consistency in public policy across jurisdictions. In this project, we combine cutting-edge methods of text and network analysis to understand how policies, as represented in digitized text, spread in the US states. It will help researchers, public officials, advocacy groups, and other relevant stakeholders understand how to balance the competing goals of innovation and consistency in public policy. The work is in part supported by an NSF award.
read more »

Disaster Impact Discovery

There is an indisputably increasing need to develop new tools and methods to strengthen crisis management, humanitarian response, and the resiliency in societies and organizations. Analyzing the event impact has been central to understanding and responding to crises. This project aims to automatically discover the impact of an exogenous event on multiple facets of community's activities -- e.g., how the event changes when, where, and what individuals normally would do in a place or community.
read more »

Anomaly Detection in Dynamic Networks

The problem of anomaly detection has extensive applications in many domains such as transportation, communication, financial systems, and social networks. With the increasing adoption of ubiquitous sensors and social mobile technologies, it becomes possible to continuously collect datasets from multiple data sources. The dynamic nature of data and network structure have introduced new types of anomalies and challenges. This project aims to investigate novel anomaly mining techniques to tackle these new challenges.
read more »

Anomaly visual analytics

Traditionally, the problem of anomaly detection has been approached mainly through statistical and machine learning techniques. However, the effectiveness of these techniques is often hinged by the difficulty of properly defining and labeling normal and abnormal cases. We seek to tackle the anomaly detection problem by introducing visual analytics that allowing users to provide instant feedback in the analysis loop.
read more »

Data Wrangling for Nuclear Nonproliferation Monitoring

Today, the likelihood of large-scale nuclear warfare is low, but the possibility of non-state actors gaining possession of fissile material has grown. This project aims to identify the best ways to recognize and prevent these activities and create a research and policy base for a much more holistic approach to nonproliferation decision-making. The work is supported by the CIS Multidisciplinary Research Grant.
read more »