Abstract:
In recent years border security has been identified as a critical part of homeland security. The Department of Homeland Security monitors vehicles entering and leaving the country at land borders. Some vehicles are targeted to search for drugs and other contraband. Customs and Border Protection agents believe that vehicles involved in illegal activity operate in groups. If the criminal links of one vehicle are known then their border crossing patterns can be used to identify other partner vehicles. We perform this association analysis by using mutual information (MI) to identify pairs of vehicles that are potentially involved in criminal activity. Domain experts also suggest that criminal vehicles may cross at certain times of the day to evade inspection. We propose to modify the MI formulation to include this heuristic by using cross-jurisdictional criminal data from border-area jurisdictions.
Discussion content in firm-specific social media helps managers understand stakeholders' concerns and make informed decisions. Despite such benefits, the over-abundance of information online makes it difficult to identify and focus on the most important stakeholder groups. In this study, we propose a novel stakeholder-based event analysis framework that uses online stylometric analysis to segment the forum participants by stakeholder groups, and partitions their messages into different time periods of major firm events to examine how important stakeholders evolve over time. With this approach, we identified stakeholder groups from a sample of six companies in the petrochemical and banking industries, using more than 500,000 online message postings. To evaluate the proposed system, we conducted market prediction within the identified groups, and compared the prediction performance with traditional approaches that did not account for stakeholder groups or events. Results showed that some stakeholder groups identified by our system had stronger relationships with firms' market performance, compared to the entire set of web forum participants. Incorporating event-induced temporal dynamics further improved the prediction performance. (C) 2014 Elsevier B.V. All rights reserved.
Abstract:
Nanoscale science and engineering (NSE) and related areas have seen rapid growth in recent years. The speed and scope of development in the field have made it essential for researchers to be informed on the progress across different laboratories, companies, industries and countries. In this project, we experimented with several analysis and visualization techniques on NSE-related United States patent documents to support various knowledge tasks. This paper presents results on the basic analysis of nanotechnology patents between 1976 and 2002, content map analysis and citation network analysis. The data have been obtained on individual countries, institutions and technology fields. The top 10 countries with the largest number of nanotechnology patents are the United States, Japan, France, the United Kingdom, Taiwan, Korea, the Netherlands, Switzerland, Italy and Australia. The fastest growth in the last 5 years has been in chemical and pharmaceutical fields, followed by semiconductor devices. The results demonstrate potential of information-based discovery and visualization technologies to capture knowledge regarding nanotechnology performance, transfer of knowledge and trends of development through analyzing the patent documents.
Abstract:
The significant use of online technologies has facilitated the creation of large amounts of textual data. The continuous textual data requires the development of a surveillance system that can collect, filter, extract, quantify, and analyze relevant information from the Internet. Finance-related textual content is divided into three categories, the first includes forums, blogs, and wikis, the second category includes news and research reports and the third category involves finance-related content generated by firms. Several firms maintain their own Web sites as a communication channel with consumers and investors. Public companies are required to submit their filings to the Edgar system, which is publicly accessible on the Web. The growing body of Web 2.0 content can facilitate the implementation of near real-time monitoring system and allow financial institutions to benefit from the continues textual data.
