Yilu Zhou

SpidersRUs: Creating specialized search engines in multiple languages

While small-scale search engines in specific domains and languages are increasingly used by Web users, most existing search engine development tools do not support the development of search engines in languages other than English, cannot be integrated with other applications, or rely on proprietary software. A tool that supports search engine creation in multiple languages is thus highly desired. To study the research issues involved, we review related literature and suggest the criteria for an ideal search tool. We present the design of a toolkit, called SpidersRUs, developed for multilingual search engine creation. The design and implementation of the tool, consisting of a Spider module, an Indexer module, an Index Structure, a Search module, and a Graphical User Interface module, are discussed in detail. A sample user session and a case study on using the tool to develop a medical search engine in Chinese are also presented. The technical issues involved and the lessons learned in the project are then discussed. This study demonstrates that the proposed architecture is feasible in developing search engines easily in different languages such as Chinese, Spanish, Japanese, and Arabic.

Introduction to special issue on terrorism informatics

Since September 11th, the multidisciplinary field of terrorism informatics has experienced tremendous growth, and research communities as well as local, state, and national governments are facing increasingly more complex and challenging issues. The challenges facing the intelligence and national security communities worldwide include accurately and efficiently monitoring, analyzing, predicting and preventing terrorist activities. The development and use of advanced information technologies, including methodologies, models and algorithms, infrastructure, systems, and tools for national/international and homeland security related applications have provided promising new directions for study. Terrorism informatics has been defined as the application of advanced methodologies, information fusion and analysis techniques to acquire, integrate process, analyze, and manage the diversity of terrorism-related information for international and homeland security-related applications (Chen et al. 2008). It is a highly interdisciplinary and comprehensive field. The wide variety of methods used in terrorism informatics are derived from Computer Science, Informatics, Statistics, Mathematics, Linguistics, Social Sciences, and Public Policy, and these methods are involved in the collection of huge amounts of many types of multi-lingual information from varied and multiple sources. Information fusion and information technology analysis techniques, which include data mining, data integration, language translation technologies, and image and video processing, play central roles in the prevention, detection, and remediation of terrorism. The purpose of this special issue is to bring together international researchers, engineers, policy makers, and practitioners working on terrorism informatics as well as related fields such as the organizational and social sciences. We have accepted nine papers that report research in terrorism informatics. They study a variety of topics from terrorist social networks to terrorist Website sophistication, from online forum to Twitter, and from English content to Chinese content. They represent a good mix of multiple disciplines and look at terrorism informatics from different perspectives. The first two papers provide comprehensive reviews of the field, demand, techniques and trends. These papers provide guidelines as what are the interests and challenges in this community. “Tracking and Disrupting Dark Networks: Challenges of Data Collection and Analysis” by Roberts (Roberts 2011) provide challenges of data collection and analysis from within the intelligence community. Various relevant government agencies, their research interests and their ongoing projects on terrorism information collection and analysis are introduced. “Computational Approaches to Suspicion in Adversarial Settings” by Skillicorn 2011 provides a computational framework for adversarial data analysis in the context of crime and terrorism investigations. The author reviewed and discussed three major components including adversary-based data collection and characteristics, the detection techniques that identify suspicious individuals, and the network-based association techniques that find individuals related to a known suspicious individual. The next four papers focus on web content analysis with the last one also addresses web structure analysis to reveal sophistication level of terrorist websites. Two of them look at a new and promising data source: Twitter. “Information Control H. Chen Management Information Systems, University of Arizona, Tucson, AZ, USA

A Text Mining Model for Strategic Alliance Discovery

Strategic alliances among organizations are one of the central drivers of innovation and economy and have raised strong interest among policymakers, strategists and economists. However, discovery of alliances has relied on pure manual search and has limited scope. This research addresses the limitations by proposing a text mining framework that automatically extracts alliances from news articles. The model not only integrates meta-search, entity extraction and shallow and deep linguistic parsing techniques, but also proposes an innovative ADT-based relation extraction method to deal with the extremely skewed and noisy news articles and AC Rank to further improve the precision using various linguistic features. Evaluation from an IBM alliances case study showed that ADT-based extraction achieved 78.1% in recall, 44.7% in precision and 0.569 in F-measure and eliminated over 99% of the noise in document collections. AC Rank further improved precision to 97% with the top-20% extracted alliance instances. Our case study also showed that the widely cited Thomson SDC database only covered less than 20% of total alliances while our automatic approach can covered 67%.