Perspectives and Vision
Project Epic sees a vision of the future of emergency management that better supports inclusion of activities and information from members of the public during disasters and mass emergency events. Such a vision relies on integration of multiple subfields of computer science, and a commitment to an understanding of the domain of application. It supports the hopes of a grid/cyberinfrastructure-enabled future that makes use of social software. However, in contrast to how emergency management is often understood, it aims to push beyond the idea of monitoring on-line activity, and instead focuses on an understudied but critical aspect of mass emergency response—the needs and roles of members of the public. By viewing the citizenry as a powerful, self-organizing, and collectively intelligent force, information and communication technology can play a transformational role in crisis. Critical topics for research and development include an understanding of the quantity and quality of information (and its continuous change) produced through computer-mediated communication during emergencies; mechanisms for ensuring trustworthiness and security of information; mechanisms for aligning informal and formal sources of information; and new applications of information extraction techniques.
A common site of innovation, disasters and crisis often stretch the applied uses of current technology which exposes new abilities of these modern computer-mediated communication tools. Specifically highlighted are new methods of collaborative problem solving as victims of disaster attempt to organize in information sharing and recovery efforts.
Project EPIC investigates these constructive interpersonal relationships from understanding how people come together over Twitter to raise money for pre-paid cell phone plans for earthquake victims to analyzing the use of Facebook in performing immediate mobile background checks of new acquaintances in war zones.
In the age of Big Data and quantitative statistics, Project EPIC strives to perform qualitative analysis, acknowledging that today's crisis data is generated by distinct individuals in unique situations. Treating a user's entire social media stream as a single datapoint instead of just bits and pieces of their public communications allows us to construct a rich dataset which includes the background context for a user's communications.
Natural disasters and crisis events generate a strong social media response and produce high volume of textual data that are difficult to peruse manually and organize into a coherent picture. Yet valuable information is transmitted, and can provide useful insight into time- and safety-critical situations if captured and analyzed properly and rapidly. Computational linguistics allows us to extract linguistic and behavioral information from tweet text to aid in the task of information integration. We use natural language processing tools such as linguistic annotation, in the form of Named Entity Tagging, Part of Speech Tagging, and Event Extraction, and apply machine learning classification techniques to aid with information integration. We also combine linguistic annotation with sentiment analysis and geographic information to capture tweets that contribute to situational awareness.
Software Data Infrastructure
Efforts to architect software to collect, organize, curate, and process large-scale social media data have been a major challenge. Twitter data, for example, are both constantly changing and ephemeral, posing unique requirements for their collection and analysis. Restrictions held by service-hosted APIs such as rate limiting may cause unexpected throttling of the data collection process. When data have been collected, they must be cleaned, organized, and indexed for batch and real-time querying based on end-user requirements. Finally, as is evident in many forms within our society, infrastructure seeks to become invisible and provide a layer of security and trust to end-users who depend on it. In the Project EPIC lab, we software engineering researchers grapple with these concerns from software design to user studies. Our flagship systems, EPIC Collect and EPIC Analyze, are a testament to the research work carried out to advance knowledge of software infrastructural design and development.