Visual Query and Exploration System for inspecting terror networks

The September 11 attacks brought into focus the malfunctioning of information agencies in the USA. In fact, many terrorist attacks could have been prevented if the available intelligence had been properly utilized. All the raw intelligence materials were available before these attacks were committed; the main problem was to push aside all the material that was not relevant to the investigation, to integrate all the relevant facts, and to construct a clear and complete picture of all the decentralized information available. In order to face these threats, intelligence agencies should adopt new strategies of data collection and data analysis. Text Mining is a new and exciting research area that tries to solve the information overload problem by using techniques from data mining, machine learning, NLP, IR, and knowledge management. Text Mining involves the preprocessing of document collections, information extraction, the storage of the intermediate representations, and techniques to analyze these intermediate representations. Link Analysis is the graphic portrayal of extracted/derived data, in a manner designed to facilitate the understanding of large amounts of data and particularly to allow analysts to develop possible relationships between entities that otherwise would remain hidden by the mass of data obtained. The purpose of this research is to create a visual environment in which the end user is able to query and explore a temporal relational database. This research brings into focus methods and visual facilities that aid the user to extract relations according to their temporal behavior and to explore the evolution of the relations over time. The major assumption is that the analysis of static networks does not yield satisfactory information. If the time dimension is taken into consideration much more interesting conclusions can be inferred. Tracking relations over time may assist the user to identify special temporal patterns, to classify similar patterns, and to predict the future behavior of a relation. The system developed during this research is called pureVision in line with its designated purpose: to bring into focus uncharted trails hidden by the mass of data. Temporal databases enable to retrieve each of states observed in the past and even planned future states. Several query languages for relational databases have been introduced, but only a few of them deal with temporal databases. Moreover, most users are not highly skilled in query formulation and hence are not able to define complex queries. The visual approach introduced here aims at simplifying the query construction process. It gives the user the option to define complex temporal constructs and provides visual tools with which to explore the returned networks intuitively. The exploration process should provide better insight into networks of entities, reveal patterns between the entities, and enable the user to forecast the behavior of entities in the future. A visual query language as an isolated subsystem is not sufficient in itself for a complete data analysis process. A query's output should be further explored to find patterns that are hidden in the output.