Jialun Qin

US domestic extremist groups on the Web: link and content analysis

Although US domestic extremist and hate groups might not be as well-known as some international groups, they nevertheless pose a significant threat to homeland security. Increasingly, these groups are using the Internet as a tool for facilitating recruitment, linking with other extremist groups, reaching global audiences, and spreading hate materials that encourage violence and terrorism. A study of semiautomated methodologies to capture and organize domestic extremist Web site data revealed interorganizational structures and cluster affinities that coincided with both domain expert knowledge and earlier manual research.

Building domain-specific Web collections for scientific digital libraries: a meta-search enhanced focused crawling method

Collecting domain-specific documents from the Web using focused crawlers has been considered one of the most important strategies to build digital libraries that serve the scientific community. However, because most focused crawlers use local search algorithms to traverse the Web space, they could be easily trapped within a limited sub-graph of the Web that surrounds the starting URLs and build domain-specific collections that are not comprehensive and diverse enough to scientists and researchers. We investigated the problems of traditional focused crawlers caused by local search algorithms and proposed a new crawling approach, meta-search enhanced focused crawling, to address the problems. We conducted two user evaluation experiments to examine the performance of our proposed approach and the results showed that our approach could build domain-specific collections with higher quality than traditional focused crawling techniques.

Analyzing terrorist networks: a case study of the global salafi jihad network

It is very important for us to understand the functions and structures of terrorist networks to win the battle against terror. However, previous studies of terrorist network structure have generated little actionable results. This is mainly due to the difficulty in collecting and accessing reliable data and the lack of advanced network analysis methodologies in the field. To address these problems, we employed several advance network analysis techniques ranging from social network analysis to Web structural mining on a Global Salafi Jihad network dataset collected through a large scale empirical study. Our study demonstrated the effectiveness and usefulness of advanced network techniques in terrorist network analysis domain. We also introduced the Web structural mining technique into the terrorist network analysis field which, to the best our knowledge, has never been used in this domain. More importantly, the results from our analysis provide not only insights for terrorism research community but also empirical implications that may help law-reinforcement, intelligence, and security communities to make our nation safer.

CMedPort: an integrated approach to facilitating Chinese medical information seeking

As the number of non-English resources available on the Web is increasing rapidly, developing information retrieval techniques for non-English languages is becoming an urgent and challenging issue. In this research to facilitate information seeking in a multilingual world, we focused on discovering how search-engine techniques developed for English could be generalized for use with other languages. We proposed a general framework incorporating a focused collection-building technique, a generic language processing ability, an integration of information resources, and a post-retrieval analysis module. Based on this approach, we developed CMedPort, a Chinese Web portal in the medical domain that not only allows users to search for Web pages from local collections and meta-search engines but also provides encoding conversion between simplified and traditional Chinese to support cross-regional search and document summarization and categorization. User studies were conducted to compare the effectiveness and efficiency of CMedPort with those of three major Chinese search engines. Results indicate that CMedPort achieved similar accuracy for search tasks, but exhibited significantly higher recall than each of the three search engines as well as higher precision than two of the search engines for browse tasks. There were no significant differences among the efficiency measures for CMedPort and benchmarks systems. A post-questionnaire regarding system usability indicated that CMedPort achieved significantly higher user satisfaction than any of the three benchmark systems. The subjects especially liked CMedPorts categorizer, commenting that it helped improve understanding of search results. These encouraging outcomes suggest a promising future for applying our approach to Internet searching and browsing in a multilingual world.

Multilingual Web Retrieval: An Experiment on a Multilingual Business Intelligence Portal

The amount of non-English information on the Web has proliferated so rapidly in recent years that it often is difficult for a user to retrieve documents in an unfamiliar language. In this study, we report the design and evaluation of a multilingual Web portal in the business domain in English, Chinese, Japanese, Spanish, and German. Web pages relevant to the domain were collected. Search queries were translated using bilingual dictionaries, while phrasal translation and co-occurrence analysis were used for query translation disambiguation. Pivot translations were also used for language-pairs where bilingual dictionaries were not available. A user evaluation study showed that on average, multilingual performance achieved 72.99% of monolingual performance. In evaluating pivot translation, we found that it achieved 40% performance of monolingual retrieval, which was not as good as direct translation. Overall, our results are encouraging and show promise of successful application of MLIR techniques to Web retrieval.

Using Genetic Algorithm in Building Domain-Specific Collections: An Experiment in the Nanotechnology Domain

As the key technique to build domain-specific search engines, focused crawling has drawn a lot of attention from researchers in the past decade. However, as Web structure analysis techniques advance, several problems in traditional focused crawler design were revealed and they could result in domain-specific collections with low quality. In this work, we studied the problems of focused crawling that are caused by using local search algorithms. We also proposed to use a global search algorithm, the Genetic Algorithm, in focused crawling to address the problems. We conducted evaluation experiments to examine the effectiveness of our approach. The results showed that our approach could build domain-specific collections with higher quality than traditional focused crawling techniques. Furthermore, we used the concept of Web communities to evaluate how comprehensively the focused crawlers could traverse the Web search space, which could be a good complement to the traditional focused crawler evaluation methods.

Enhancing Mobile Learning Using Speech Recognition Technologies: A Case Study

While many studies have demonstrated the value of mobile learning (m-learning) applications in educational environments, the limitations of mobile devices may impair the accessibility of such applications. In this study, we explore the integration of speech or voice recognition technologies into m- learning applications to reduce access barriers. Based on an m-learning framework proposed in our previous work, we built an educational online forum accessible through mobile devices. We then developed customized interactive voice response (IVR) and text-to-speech (TTS) technologies to allow users to interact with the forum through voice commands. This voice-enabled discussion forum application not only helps normal users avoid the cumbersome task of typing using small keypads, but also enables people with visual and mobility disabilities to engage in online educations. The prototype forum was tested in two different blind institutions in Massachusetts with 10 users. The results from this study provide insights into how to improve accessibility of m-learning and other related m- commerce applications.

SpidersRUs: automated development of vertical search engines in different domains and languages

In this paper we discuss the architecture of a tool designed to help users develop vertical search engines in different domains and different languages. The design of the tool is presented and an evaluation study was conducted, showing that the system is easier to use than other existing tools

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.

Exploring the dark side of the web: collection and analysis of u.s. extremist online forums

Contents in extremist online forums are invaluable data sources for extremism reseach. In this study, we propose a systematic Web mining approach to collecting and monitoring extremist forums. Our proposed approach identifies extremist forums from various resources, addresses practical issues faced by researchers and experts in the extremist forum collection process. Such collection provides a foundation for quantitative forum analysis. Using the proposed approach, we created a collection of 110 U.S. domestic extremist forums containing more than 640,000 documents. The collection building results demonstrate the effectiveness and feasibility of our approach. Furthermore, the extremist forum collection we created could serve as an invaluable data source to enable a better understanding of the extremism movements.