Principal Investigator: David Ebert
SMART allows end users to map, interactively explore and navigate large volumes of data, topics, and anomalies that occur in real-time via social media networks such as Instagram and Twitter. The Visual Analytics for Command, Control, and Interoperability Environments (VACCINE) Center has developed a new approach to let end users build and customize message/keyword filters interactively and visually, enriched with an integrated real-time machine learning approach that learns from users interaction to display relevant information. The created filter methods can be arranged and adapted continually for monitoring and analyzing data, which is of particular importance when making decisions in a time sensitive manner. This technology provides end users with scalable and interactive social media analysis and visualization through topic extraction, a combination of filters, cluster examination, and stream categorization. Features of the system include real-time monitoring of social media channels, extraction of trending and abnormal topics, density-based spatial clustering at multiple spatial scales, message classification based on intention verbs, task-tailored interactive message categorization, and real-time geolocation inference of non-geotagged data. These components are tightly integrated into a highly interactive visual analysis workbench that allows end users to observe, supervise, and configure the methods in each analysis process. The system also incorporates novel visual analytic techniques to extract and visualize crowd movement patterns and trajectories using social media data at various scales of analysis to allow users to detect anomalies and outlier patterns. The system can also send automatic email alerts based on user-defined keywords and thresholds.
Students: Luke Snyder, Yi-Shan Lin
Snyder, L. S., Lin, Y. S., Karimzadeh, M., Goldwasser, D., & Ebert, D. S. (2019). Interactive Learning for Identifying Relevant Tweets to Support Real-time Situational Awareness. IEEE transactions on visualization and computer graphics.
Chae, J., Zhang, J., Ko, S., Malik, A., Connell, H., & Ebert, D. S. (2016, May). Visual analytics for investigative analysis of hoax distress calls using social media. In Technologies for Homeland Security (HST), 2016 IEEE Symposium on (pp. 1-6). IEEE.
Zhang, J., Surakitbanharn, C., Elmqvist, N., Maciejewski, R., Qian, Z., & Ebert, D. S. (2018). TopoText: Context-Preserving Text Data Exploration Across Multiple Spatial Scales. In Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems (to appear). ACM.
Zhang, J., Malik, A., Ahlbrand, B., Elmqvist, N., Maciejewski, R., & Ebert, D. S. (2017, May). Topogroups: Context-preserving visual illustration of multi-scale spatial aggregates. In Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems (pp. 2940-2951). ACM.
Zhang, J., Ahlbrand, B., Malik, A., Chae, J., Min, Z., Ko, S., & Ebert, D. S. (2016, June). A Visual Analytics Framework for Microblog Data Analysis at Multiple Scales of Aggregation. In Computer Graphics Forum (Vol. 35, No. 3, pp. 441-450).
Chae, J., Thom, D., Jang, Y., Kim, S., Ertl, T., & Ebert, D. S. (2014). Public behavior response analysis in disaster events utilizing visual analytics of microblog data. Computers & Graphics, 38, 51-60.
Chae, J., Thom, D., Bosch, H., Jang, Y., Maciejewski, R., Ebert, D. S., & Ertl, T. (2012, October). Spatiotemporal social media analytics for abnormal event detection and examination using seasonal-trend decomposition. In 2012 IEEE Conference on Visual Analytics Science and Technology (VAST), (pp. 143-152). IEEE.
Keywords: situation awareness, social media, visual analytics