Publication
Refereed Journal and Book
Chung, W. and Hershey, L. Enhancing Information Privacy and Data Sharing in a Healthcare IT Firm: The Case of Ricerro Communications. Journal of Information Privacy and Security, 2013, (in press).
Information privacy and data sharing are two conflicting but important data management concerns. As more data are shared among stakeholders, the design of information systems (IS) often emphasizes on data sharing at the expense of information privacy. Unfortunately, existing IS research on designing tools to enhance information privacy is isolated from actual use of the tools. In this research, we examined the design of a data sharing system in a real-world company. The company, Ricerro Communications, Inc., produces and markets wearable communications devices used mainly in healthcare organizations. Poor data sharing in Ricerro’s multiple systems resulted in loss of information privacy and security and inefficiency, seriously affecting customer relationship management. A consulting team has analyzed Ricerro’s needs, gathered stakeholder requirements, and developed a privacy-enhancing data integration solution, which consists of database schema integration and data migration from various sources to a Web-based transaction processing system. Through this industry case, we illustrate how our developed principles and guidelines for designing IT artifacts incorporate the benefits of information privacy and data sharing.
Chung, W. and Chen, L. Group-buying e-commerce in China. IEEE IT Professional, 14 (4), 2012, 24-30.
Group-buying is growing rapidly in emerging economies, where websites have rudimentary functions and cluttered interfaces. The authors review 11 major Chinese group-buying websites, using case studies to provide timely guidance to e-commerce practitioners and researchers.
Chung, W. and Tseng, B. Discovering Business Intelligence from Online Product Reviews: A Rule-Induction Framework. Expert Systems with Applications, 39 (15), 2012, 11870-11879.
Online product reviews are a major source of business intelligence (BI) that helps managers and marketers understand customers’ concerns and interests. The large volume of review data makes it difficult to manually analyze customers’ concerns. Automated tools have emerged to facilitate this analysis, however most lack the capability of extracting the relationships between the reviews’ rich expressions and the customer ratings. Managers and marketers often resort to manually read through voluminous reviews to find the relationships. To address these challenges, we propose the development of a new class of BI systems based on rough set theory, inductive rule learning, and information retrieval methods. We developed a new framework for designing BI systems that extract the relationship between the customer ratings and their reviews. Using reviews of different products from Amazon.com, we conducted both qualitative and quantitative experiments to evaluate the performance of a BI system developed based on the framework. The results indicate that the system achieved high accuracy and coverage related to rule quality, and produced interesting and informative rules with high support and confidence values. The findings have important implications for market sentiment analysis and e-commerce reputation management.
Chung, W. Managing Web Repositories in Emerging Economies: Case Studies of Browsing Web Directories. International Journal of Information Management, 32 (3), 2012, 232-238.
Over the past decade, worldwide Internet usage has grown tremendously, with the most rapid growth in some emerging economies such as Latin America and the Middle East, where people speaking different languages actively seek information on the Web. Global search engines may not adequately address local users’ needs while regional Web portals may lack rich Web content. Different from search engines, Web directories organize sites and pages into intuitive hierarchical structures to facilitate browsing. However, high-quality Web directories in users’ native languages often do not exist and their development requires much domain knowledge not readily available. In this research, we proposed a novel semi-automatic approach to facilitate Web repository management. We applied the approach to developing Web directories in the business and health-care domains for the Spanish-speaking and Arabic-speaking communities respectively. The two directories contain respectively 4,735 and 5,107 unique sites and pages with a maximum depth of 5 levels. Results of experiments involving 37 native speakers show that these directories outperformed existing benchmark directories in terms of browsing effectiveness and efficiency, providing strong implications for information professionals and multinational enterprise managers.
Chung, W. Web Searching and Browsing: A Multilingual Perspective. In Marvin V. Zelkowitz (ed.), Advances in Computers, Vol. 78, Elsevier Inc, 2010, 41-69.
Since the publication of "The World Wide Web" in a 1999 volume of Advances
in Computers, worldwide Internet usage has grown tremendously, with the most
rapid growth in some non-English-speaking regions. A widening gap exists
between the surging demand for non-English Web content and the availability
of non-English resources. This chapter reviews previous works on computermediated
information seeking on the Web, computing technologies that support
Web searching and browsing, and Web portals in several major regions and
languages of the world. We introduce a general framework for supporting
Web searching and browsing in a multilingual world. Three Web portals were
developed to support searching, browsing, and postretrieval analysis of Chinese
business intelligence, Spanish business intelligence, and Arabic medical intelligence.
Results of experiments involving 67 native speakers of the three
languages confirm the usability and benefits of the portals and support the
applicability of the framework. The review, framework, and findings presented
in this chapter contribute to the fields of Web analysis, text mining, business and
medical informatics, and human computer interaction.
Chung, W. and Chen, H. Web-based Business Intelligence Systems: A Review and Case Studies. In G. Adomavicius and A. Gupta (ed.), Handbooks in Information Systems: Business Computing, Emerald Group Publishing Limited, 2009.
As businesses increasingly use the Web to share and disseminate information,
effectively and efficiently discovering business intelligence (BI) from
voluminous information has challenged researchers and practitioners. In
this chapter, we review literature in BI on the Web and technology for Web
analysis, and propose a framework for developing Web-based BI systems,
which can help managers and analysts to understand their competitive
environment and to support decision-making. The framework consists of
steps including collection, conversion, extraction, analysis, and visualization
that transform Web data into BI. Combinations of data and text mining
(TM) techniques were used to assist human analysis in different scenarios.
We present three case studies applying the framework to BI discovery on the
Web. In these studies, we designed, developed, and evaluated Web-based BI
systems that search for and explore BI from a large number of Web pages
and help analysts to classify and visualize the results. Experimental results
show that the systems compared favorably with benchmark methods,
showing the usability of the framework in alleviating information overload
and in collecting and analyzing BI on the Web. Considering the scarce
research work found in this field, this chapter provides valuable insights and
new research findings on developing Web-based BI systems. Future
directions of BI research are discussed.
Chung, W. Enhancing business intelligence quality with visualization: An experiment on stakeholder network analysis. Pacific Asia Journal of the Association for Information Systems, 1, 1 (March 2009), 33-53.
Business intelligence (BI) has gained a strategic importance in today's global competitive environment. However, high-quality BI is not easy to obtain on the Web due to information overload and difficulty to present complicated relationships among various types of business stakeholders. Unfortunately, existing BI tools lack the capability of analyzing and visualizing such relationships and research on BI systems is sparse. In this paper, we review the current market of BI tools and related research, describe an approach to support the development of tools that provide high-quality BI, and report the findings of a user evaluation study of the prototype developed based on the proposed approach. The approach combines information visualization and Web mining techniques with human knowledge to enable business analysts to analyze and visualize complicated business stakeholder relationships. Results of an experiment involving 62 subjects show that the prototype significantly outperformed a traditional method of BI analysis in terms of efficiency, quality of BI, and user satisfaction. The subjects provided favorable comments and expressed strong preferences toward the prototype in most applications. This research contributes to advancing BI research and to providing new empirical findings for BI systems evaluation.
Chung, W. and Chen, H. Browsing the underdeveloped Web: An experiment on the Arabic Medical Web Directory. Journal of the American Society for Information Science and Technology, 60, (March 2009), 595-607.
While the Web has grown significantly in recent years, some portions of the Web remain largely underdeveloped, as shown in a lack of high-quality content and functionality. An example is the Arabic Web, in which a lack of well-structuredWeb directories limits users' ability to browse for Arabic resources. In this research, we proposed an approach to buildingWeb directories for the underdeveloped Web and developed a proof-of-concept prototype called the Arabic MedicalWeb Directory (AMed-Dir) that supports browsing of over 5,000 Arabic medical Web sites and pages organized in a hierarchical structure. We conducted an experiment involving Arab participants and found that the AMedDir significantly outperformed two benchmark ArabicWeb directories in terms of browsing effectiveness, efficiency, information quality,and user satisfaction. Participants expressed strong preference for the AMedDir and provided many positive comments. This research thus contributes to developing a useful Web directory for organizing the information in the Arabic medical domain and to a better understanding of how to support browsing on the underdevelopedWeb.
Chung, W., Chen, H. and Reid, E. Business stakeholder analyzer: An experiment of classifying stakeholders on the Web. Journal of the American Society for Information Science and Technology, 60, (January 2009), 59-74.
As the Web is used increasingly to share and disseminate information, business analysts and managers are challenged to understand stakeholder relationships.Traditional stakeholder theories and frameworks employ a manual approach to analysis and do not scale up to accommodate the rapid growth of the Web. Unfortunately, existing business intelligence (BI) tools lack analysis capability,and research on BI systems is sparse. This research proposes a framework for designing BI systems to identify and to classify stakeholders on theWeb, incorporating human knowledge and machinelearned information from Web pages. Based on the framework, we have developed a prototype called Business Stakeholder Analyzer (BSA) that helps managers and analysts to identify and to classify their stakeholders on the Web. Results from our experiment involving algorithm comparison, feature comparison, and a user study showed that the system achieved better withinclass accuracies in widespread stakeholder types such as partner/sponsor/supplier and media/reviewer, and was more efficient than human classification. The student and practitioner subjects in our user study strongly agreed that such a system would save analysts' time and help to identify and classify stakeholders. This research contributes to a better understanding of how to integrate information technology with stakeholder theory, and enriches the knowledge base of BI system design.
Chen, H., Chung, W., Qin, J., Reid, E., Sageman, M. and Weimann, G. Uncovering the Dark Web: A case study of Jihad on the Web. Journal of the American Society for Information Science and Technology, 59, (August 2008), 1347-1358.
While the Web has become a worldwide platform for communication, terrorists share their ideology and communicate with members on the "DarkWeb敆the reverse side of the Web used by terrorists. Currently, the problems of information overload and difficulty to obtain a comprehensive picture of terrorist activities hinder effective and efficient analysis of terrorist information on the Web. To improve understanding of terrorist activities,
we have developed a novel methodology for collecting and analyzing Dark Web information. The methodology
incorporates information collection, analysis, and visualization techniques, and exploits variousWeb information
sources. We applied it to collecting and analyzing information of 39 JihadWeb sites and developed visualization
of their site contents, relationships,and activity levels. An expert evaluation showed that the methodology is very
useful and promising, having a high potential to assist in investigation and understanding of terrorist activities by
producing results that could potentially help guide both policymaking and intelligence research.
Chung, W. Visualizing E-Business Stakeholders on the Web: A Methodology and Experimental Results. International Journal of Electronic Business, 6, (January 2008), 25-46.
Competition among e-businesses has become ever more fierce as electronic commerce is gaining wide acceptance. Meanwhile, effectively collecting and analysing competitive intelligence has challenged researchers and practitioners. This research proposed and validated a new methodology for developing competitive intelligence tools to support e-business stakeholder analysis. We developed a prototype that supports collecting, analysing, and visualising stakeholder Web pages and relationships. Experimental results show that the prototype significantly outperformed a traditional method of stakeholder analysis in terms of user satisfaction and effectiveness on certain task types. This research thus provides a useful methodology and new empirical findings for e-business stakeholder analysis.
Chung, W. Web Searching in a Multilingual World. Communications of the ACM, 51, (May 2008), 32-40.
Worldwide Internet use has grown tremendously in recent years, most rapidly in non-English-speaking regions. For example, from 2000 to 2007, the online populations in Latin America and the Middle East grew by 577.3% and 920.2%, respectively [9]. At the same time, the number of registered domain names in mainland China (.cn) surged by 137.5% annually [2], fueling the growth of Web pages in Chinese, the second most popular language on the Web. Meanwhile, Arabic Web content was estimated to be doubling every year [1]. Such growth has created demand for better Web searching and browsing in some non-English languages. However, existing Web portals may be unable to meet it because they primarily serve English-speaking users.
Chung, W., Lai, G., Bonillas, A., Xi, W. and Chen, H. Organizing domain-specific information on the Web: An experiment on the Spanish business Web directory. International Journal of Human-Computer Studies, 66, (February 2008), 51-66.
Web directories organize voluminous information into hierarchical structures, helping users to quickly locate relevant information and to support decision-making. The development of existing ontologies and Web directories either relies on expert participation that may not be available or uses automatic approaches that lack precision. As more users access the Web in their native languages, better approaches to organizing and developing non-English Web directories are needed. In this paper, we have proposed a semi-automatic framework, which consists of anchor directory boosting, meta-searching, and heuristic filtering, to construct domain-specific Web directories. Using the framework, we have built a Web directory in the Spanish business (SBiz) domain. Experimental results show that the SBiz Web directory achieved significantly better recall, F-value, efficiency, and satisfaction rating than the benchmark directory. Subjects provided favorable comments on the SBiz Web directory. This research thus contributes to developing a useful framework for organizing domain-specific information on the Web and to providing empirical findings and useful insights for end-users, system developers, and researchers of Web information seeking and knowledge management.
Leroy, G., Xu, J., Chung, W., Eggers, S. and Chen, H. An end user evaluation of query formulation and results review tools in three meta-search engines. International Journal of Medical Informatics, 76, (November 2007), 780-789.
Retrieving sufficient relevant information online is difficult formany people because they use too few keywords to search and search engines do not provide many support tools. To further complicate the search, users often ignore support tools when available. Our goal is to evaluate in a realistic setting when users use support tools and howthey perceive these tools.
Chung, W. Studying information seeking in the non-English Web: An experiment on a Spanish business Web portal. International Journal of Human Computer Studies, 64, (September 2006), 811-829.
The Internet is estimated to grow significantly as access to Web content in some non-English languages continues to increase. However, prior research in human computer interaction (HCI) has implicitly assumed the primary language used on the Web to be English. This assumption is not true for many non-English-speaking regions where rapidly growing on-line populations access the Web in their native languages. For example, Latin America, where the majority of people speak Spanish, will have the fastest growing population in coming decades. However, existing Spanish search engines lack search, browse, and analysis capabilities. The research reported here studied human information seeking on the non-English Web. In it we developed a Spanish business Web portal that supports searching, browsing, summarization, categorization, and visualization of Spanish business Web pages. Using 42 Spanish speakers as subjects we conducted a two-phase experiment to evaluate this portal and found that, compared with a Spanish search engine and a Spanish Web directory, it achieved significantly better user ratings on information quality, cross-regional search capability, system performance attributes, and overall satisfaction. Subjects' verbal comments strongly favored the search and browse functionality and user interface of our portal. As the Web becomes more international, this research makes three contributions: (1) an empirical evaluation of the performance level of a Spanish search portal; (2) an examination of the information quality, cross-regional search capability and usability of search engines for the non-English Web; and (3) a better understanding of non-English Web searching.
Chung, W., Bonillas, A., Lai, G., Xi, W. and Chen, H. Supporting non-English Web searching: An experiment on the Spanish business and the Arabic medical intelligence portals. Decision Support Systems, 42, (March 2006), 1697-1714.
Although non-English-speaking online populations are growing rapidly, support for searching non-English Web content is much weaker than for English content. Prior research has implicitly assumed English to be the primary language used on the Web, but this is not the case for many non-English-speaking regions. This research proposes a language-independent approach that uses meta-searching, statistical language processing, summarization, categorization, and visualization techniques to build high-quality domain-specific collections and to support searching and browsing of non-English information. Based on this approach, we developed SBizPort and AMedPort for the Spanish business and Arabic medical domains respectively. Experimental results showed that the portals achieved significantly better search accuracy, information quality, and overall satisfaction than benchmark search engines. Subjects strongly favored the portals' search and browse functionality and user interface. This research thus contributes to developing and validating a useful approach to non-English Web searching and providing an example of supporting decision-making in non-English Web domains.
Chung, W., Chen, H., Chang, W. and Chou, S. Fighting cybercrime: a review and the Taiwan experience. Decision Support Systems, 41, (March 2006), 669-682.
Cybercrime is becoming ever more serious. Findings from the 2002 Computer Crime and Security Survey show an upward trend that demonstrates a need for a timely review of existing approaches to fighting this new phenomenon in the information age. In this paper, we define different types of cybercrime and review previous research and current status of fighting cybercrime in different countries that rely on legal, organizational, and technological approaches. We focus on a case study of fighting cybercrime in Taiwan and discuss problems faced. Finally, we propose several recommendations to advance the work of fighting cybercrime.
Chung, W., Chen, H., Chaboya, L. G., O'Toole, C. and Atabakhsh, H. Evaluating event visualization: a usability study of COPLINK Spatio-Temporal Visualizer. International Journal of Human-Computer Studies, 62, (January 2005), 127-157.
Event visualization holds the promise of alleviatinginformation overload in human analysis and numerous tools and techniques have been developed and evaluated. However, previous work does not specifically address either the coordination of event dimensions with the types of tasks involved or the way that visualizingdifferent event dimensions can benefit human analysis. In this paper, we propose a taxonomy of event visualization and present a methodology for evaluating a coordinated event visualization tool called COPLINK Spatio-Temporal Visualizer (STV). The taxonomy encompasses various event dimensions, application domains, visualization metaphors, evaluation methods and performance measures.
Chung, W., Chen, H. and Nunamaker, J. F. A visual framework for knowledge discovery on the Web: An empirical study on business intelligence exploration. Journal of Management Information Systems, 21, (April 2005), 57-84.
Chen, H., Chung, W., Xu, J. J., Wang, G., Chau, M. and Qin, Y. Crime data mining: a general framework and some examples. IEEE Computer, 37, (April 2004), 50-56.
The concern about national security has increased significantly since the 9/11 attacks. However, information overload hinders the effective analysis of criminal and terrorist activities. Data mining applied in the context of law enforcement and intelligence analysis holds the promise of alleviating such problems. In this paper, we review crime data mining techniques and present four case studies done in or ongoing COPLINK project.
Chung, W., Zhang, Y., Huang, Z., Wang, G., Ong, T.-H. and Chen, H. Internet searching and browsing in a multilingual world: an experiment on the Chinese Business Intelligence Portal (CBizPort). Journal of the American Society for Information Science and Technology, 55, (September 2004), 818-831.
The rapid growth of the non-English-speaking Internet population has created a need for better searching and browsing capabilities in languages other than English. However, existing search engines may not serve the
needs of many non-English-speaking Internet users. In this paper, we propose a generic and integrated approach to searching and browsing the Internet in a multilingual world. Based on this approach, we have developed the Chinese Business Intelligence Portal (CBiz-Port), a meta-search engine that searches for business information of mainland China, Taiwan, and Hong Kong. Additional functions provided by CBizPort include encoding conversion (between Simplified Chinese and Traditional Chinese), summarization, and categorization.
Experimental results of our user evaluation study show that the searching and browsing performance of CBiz-Port was comparable to that of regional Chinese search engines, and CBizPort could significantly augment these search engines. Subjects' verbal comments indicate that CBizPort performed best in terms of analysis functions, cross-regional searching, and user-friendliness, whereas regional search engines were more efficient and more popular. Subjects especially liked CBizPort's summarizer and categorizer, which helped in understanding search results. These encouraging results suggest a promising future of our approach to Internet searching and browsing in a multilingual world.
Huang, Z., Chung, W. and Chen, H. A graph model for e-commerce recommender systems. Journal of the American Society for Information Science and Technology, 55, (March 2004), 259-274.
Information overload on the Web has created enormous challenges to customers selecting products for online purchases and to online businesses attempting to identify customers' preferences efficiently. Various recommender systems employing different data representations and recommendation methods are currently used to address these challenges. In this research, we developed a graph model that provides a generic data representation and can support different recommendation methods. To demonstrate its usefulness and flexibility, we developed three recommendation methods: direct retrieval, association mining, and high-degree association retrieval. We used a data set from an online bookstore as our research test-bed. Evaluation results showed that combining product content information and historical customer transaction information achieved more accurate predictions and relevant recommendations than using only collaborative information. However, comparisons among different methods showed that high-degree association retrieval did not perform significantly better than the association mining method or the direct retrieval method in our test-bed.
Marshall, B., McDonald, D., Chen, H. and Chung, W. EBizPort: collecting and analyzing business intelligence information. Journal of the American Society for Information Science and Technology, 55, (October 2004), 873-891.
To make good decisions, businesses try to gather good intelligence information. Yet managing and processing a large amount of unstructured information and data stand in the way of greater business knowledge. An effective business intelligence tool must be able to access quality information from a variety of sources in a
variety of forms, and it must support people as they search for and analyze that information. The EBizPort system was designed to address information needs for the business/IT community. EBizPort's collection-building process is designed to acquire credible, timely, and relevant information. The user interface provides access to collected and metasearched resources using innovative tools for summarization, categorization, and visualization. The effectiveness, efficiency, usability, and information quality of the EBizPort system were measured. EBizPort significantly outperformed Brint, a business search portal, in search effectiveness, information quality, user satisfaction, and usability. Users particularly liked EBizPort's clean and user-friendly interface. Results from our evaluation study suggest that the visualization function added value to the search and analysis process, that the generalizable collection-building
technique can be useful for domain-specific information searching on the Web, and that the search interface
was important for Web search and browse support.
Lai, V. S. and Chung, W. Managing international data communications: a Delphi study of issues. Communications of the ACM, 45, (March 2002), 89-93.
International data communication (IDC) activities are vital to multinational corporations (MNCs) in managing the complexity of information exchanges required for the control and implementation of worldwide business strategies. IDC activities are also critical because they allow MNCs to extract information and move it globally without incurring major time delays, or transportation, reproduction, or inventory costs. Compared with data communications that occur within national borders, IDC encounters more difficulties due to differences in the international technological infrastructure, network systems, culture, government regulations, and the level of technological and economic development.
Refereed Conference
Chung, W., Zhu, M. Risk Assessment Based on News Articles: An Experiment on IT Companies. In Proceedings of the International Conference on Information Systems (Orlando, FL, 2012).
Company movements often are headlines of the press, helping managers to gauge the risk factors. While most corporate analyses are based on numerical financial figures stated in corporate reports, relatively little work has been done to reveal company risk factors from news articles. In this research, we developed an integrated framework for automatic assessment of company risks from news articles. We present a study of using the framework to categorize four IT companies' risk factors. Our experimental findings show that the three chosen classification techniques - Support Vector Machine, Naïve Bayes, and Logistic Regression - achieved encouraging results. NB outperformed both SVM and LR, while LR outperformed SVM in terms of precision, recall, and F-measure. This research addresses an important concern of risk management that received relatively less attention from previous works. The results demonstrate a strong potential for industry deployment.
Chung, W., Yew, B. Evaluating Computational Thinking in a Business Data Mining Course In Proceedings of the AIS-SIGED:IAIM pre-ICIS conference (Shanghai, China, 2011).
Computational thinking (CT) contributes to new knowledge discovery in nearly all disciplines by abstraction and automation. Although CT is an important part of undergraduate curricula, the evaluation of how CT impacts student learning is not widely studied, especially in the discipline of information systems. In this research, we developed and evaluated a CT learning module for an undergraduate business data mining course. We review in this paper previous works in the area of CT and its evaluation, describe our learning module and evaluation study, and report the findings, which show significantly positive impacts of the CT learning module in students’ acquisition of business data mining skills. Students reported highly positive perception on how the module enabled them to abstract and to automate data mining tasks. Our work should benefit educators interested in evaluating CT in their curricula and in data mining skill development.
Chung, W. A Risk Categorization Method with Application to Mobile Internet Companies, Proceedings of the Organizations and Society in Information Systems (OASIS) Workshop, Shanghai, 2011
In this research, we model the problem of risk factor evaluation as a feature extraction task in which key terms appearing in company-specific news articles are identified as factors affecting stakeholders’ perception on the company’s risk level and types.
Zachrisson, C., Chung, W., Nguyen, C., Csongradi, E. and Choi, D. Enhancing the data management of a health-care IT company: An integrated Web-based solution, Proceedings of the International Business Informatics Challenge and Conference, Muncie, IN, 2011.
A Silicon Valley Health-care IT company suffered from poor sharing of its software licensing
data, forcing administrators to manually transfer and enter data into multiple systems. A team of
graduate students from Santa Clara University developed an integrated Web-based solution to
tackle the problems. This paper describes the systems analysis and design work performed to
Chung, W. Automatic categorization of risks based on news articles: A study of hi-tech companies. In Proceedings of the 41st Annual Meeting of the Decision Sciences Institute (San Diego, CA, 2010).
A tremendous amount of information is produced daily to describe company movements and the
financial market. However, relatively little work is found on automatically extracting company
risk profiles from the textual content of news articles. This research develops a risk
categorization scheme based on the literature and an approach to automatic risk categorization
from news articles. We conducted a case study of classifying company risks from news articles
of high-tech companies. The preliminary findings demonstrate the promise of the approach in
advancing the theory and practice of risk assessment.
Chung, W. Mining company risk factors from news articles: An empirical study of mobile Internet companies. In Proceedings of the Business Intelligence Congress (Saint Louis, MO, 2010).
Concerns about companies' risk exposure have increased significantly since the global financial
crisis in 2008. While most corporate analyses are based on numerical financial figures, relatively
little work has been found on automatically identifying company risk factors from the textual
content of news articles. In this research, we propose a framework for automatic categorization of
company risks from news articles. The framework integrates text mining and automatic
classification techniques to support risk extraction from company news articles. We describe in
this paper empirical findings of categorizing risks of three companies in the mobile Internet
market. We also discuss the performance of our framework and outline the potential contributions.
Chung, W. and Tseng, T.-L. Extracting business intelligence from online product reviews: An experiment of automatic rule-induction. In Proceedings of the International Conference on Information Systems (Saint Louis, MO, 2010).
Online product reviews are a major source of business intelligence (BI) that helps managers and
market researchers make important decisions on product development and promotion. However,
the large volume of online product review data creates significant information overload problems,
making it difficult to analyze users' concerns. In this paper, we employ a design science paradigm
to develop a new framework for designing BI systems that correlate the textual content and the
numerical ratings of online product reviews. Based on the framework, we developed a prototype
for extracting the relationship between the user ratings and their textual comments posted on
Amazon.com's Web site. Two data mining algorithms were implemented to extract automatically
decision rules that guide the understanding of the relationship. We report on experimental results
of using the prototype to extract rules from online reviews of three products and discuss the
managerial implications.
Chung, W., Yang, S., Fox, E. A. and Sheetz, S. D. Integrating computational thinking into information systems and other curricula. In Proceedings of the AIS-SIGED:IAIM pre-ICIS conference (Saint Louis, MO, 2010).
Computational thinking (CT) is a fundamental skill needed to function in modern society. Despite widespread
use of computers as productivity tools, existing curricula in information systems (IS) and other disciplines
have not fully embraced CT concepts and skills. Increasing cross-disciplinary integration of CT into these
curricula can help develop students' problem-solving ability and provide educators with useful resources.
Our collaborative initiative, named the "Living in the Knowledge Society" (LIKES) community building project,
supports the integration of CT into college-level curricula by building a community of scholars and educators
who will define the way to make systemic changes in how computing and IT concepts are taught and applied
in both computing and other fields, thus better preparing the next-generation Knowledge Society builders.
We describe the workshops, community-building activities, outcomes achieved, and case studies of
developing teaching modules, curriculum guidelines, and teacher adoption strategies. Our work should
benefit educators interested in integrating CT in their curricula, computing researchers interested in
collaborating with other domain experts, and current students who aspire to become educators.
Carr, E., Fox, E., Beck, B., Chung, W., Evia, C., Fan, P., Sheetz, S. and Zobel, C. Living In the KnowlEdge Society Community Building Project. In Proceedings of the 40th ACM Technical Symposium on Computer Science Education (Chattanooga, TN, 2009).
As i-schools try to equip college graduates with skills and knowledge to work in the Information Field (iField), the Living In the KnowlEdgeSociety (LIKES) Community Building project focuses broadly on preparing these graduates to live in and to build the emerging knowledge society of the 21stcentury. We expect that LIKES graduates will connect naturally with the iField, and hope for more synergy between the two initiatives.
Chung, W. Summarizing User-Generated Reviews in Digital Libraries: A Visual Clustering Approach. In Proceedings of the Joint Conference on Digital Libraries (Austin, TX, 2009).
In this paper, we describe a visual clustering approach to
summarizing user-generated reviews of digital library items and
services. The approach consists of the steps of sentence
extraction, aspect identification, opinion classification, and
review summarization. Our work augments existing work by
considering non-standard input and by incorporating clustering
and visualization in summarization.
Chung, W. Summarizing Online Reviews to Support Customer Relationship Management in E-Commerce. In Proceedings of the Third China Summer Workshop on Information Management (CSWIM) (Guangzhou, China, 2009).
As the Internet supports more user interaction, customer reviews posted on the Web are growing significantly in recent years. However, the large volume of these reviews makes it difficult for marketers and business analysts to understand customers' concerns. This paper presents our ongoing effort to support customer relationship management through automatic summarization of online customer reviews. Our approach consists of the steps of sentence extraction, aspect identification, sentiment classification, and review summarization. We report preliminary results of using our approach to summarize product reviews extracted from a major online retailer. We discuss the preliminary findings and outline the potential benefits.
As the Internet supports more user interaction, customer reviews posted on the Web are growing significantly in recent years. However, the large volume of these reviews makes it difficult for marketers and business analysts to understand customers' concerns. This paper presents our ongoing effort to support customer relationship management through automatic summarization of online customer reviews. Our approach consists of the steps of sentence extraction, aspect identification, sentiment classification, and review summarization. We report preliminary results of using our approach to summarize product reviews extracted from a major online retailer. We discuss the preliminary findings and outline the potential benefits.
Chung, W. Automatic Summarization of Customer Reviews: An Integrated Approach. In Proceedings of the Americas Conference on Information Systems (San Francisco, CA, 2009).
The proliferation of interactivity between Web content producers and consumers underscores the development of the Internet
in recent years. In particular, customer reviews posted on the Web have grown significantly. Because customers represent the
primary stakeholder group of a company, understanding customers' concerns expressed in these reviews could help
marketers and business analysts to identify market trends and to provide better products and services. However, the large
volume of textual reviews written in informal language makes it difficult to understand customers' concerns. This paper
describes an integrated approach to summarizing customer reviews. The approach consists of the steps of sentence extraction,
aspect identification, sentiment classification, and review summarization. We report preliminary results of using our
approach to summarize product reviews extracted from Amazon.com. Our work augments existing work by considering nonstandard
input and by incorporating linguistic resources and clustering in automatic summarization.
Chung, W., Fox, E., Yang, S. and Sheetz, S. The Living In the KnowlEdge Society (LIKES) Community Building Project: Building Collaboration between Computing and Non-Computing Disciplines. In Proceedings of the Conference for Higher Education Pedagogy (Blacksburg, VA, 2009).
A collaborative effort between four universities (Virginia
Tech, Villanova, NC A&T, and Santa Clara University), is transforming computing
education for the 21st Century. Transforming computing education is necessary to
enable the Knowledge Society by providing the computing competencies necessary to
advance the health, security, and prosperity of the nation. Such a transformation
requires a vision both for the education of computing professionals and for enhancing
the computing capabilities of the larger society represented by the range of disciplines
existing in universities today. Many of these disciplines are increasingly dependent
upon computing to support decision making in their own domains.
Chung, W., Fox, E. A., Sheetz, S. D. and Yang, S. LIKES: Educating the Next Generation of Knowledge Society Builders. In Proceedings of the Americas Conference on Information Systems (San Francisco, CA, 2009).
Although information technology (IT) is used extensively in the education of all disciplines, the computing-related fields are
facing tremendous challenges, such as declining student enrollment and a lack of representation from minorities and women.
Strengthening the connection between computing and other fields could help instructors to integrate IT in their teaching and
to support the learning of students, who will become the next generation of Knowledge Society builders. Presently, this
connection is weak due to the lack of interdisciplinary collaboration and mutual understanding among faculty in computing
and other fields. Our ongoing effort entitled "Living in the KnowlEdge Society (LIKES) Community Building Project" aims
to build a community that will define a socially-relevant way to make systemic changes in how computing and IT concepts
are taught and applied in both computing and other fields. In this paper, we review previous efforts in this area and
summarize our project's achievements and lessons learned. We also provide recommendations on integrating IT into other
curricula and on strengthening interdisciplinary collaborations.
Yang, S., Fox, E. A. and Chung, W. Living In the KnowlEdge Society (LIKES) Initiative and i-Schools’ Focus on the Information Field. In Proceedings of the Fourth iSchools Conference (The University of North Carolina, Chapel Hill, NC, 2009).
As i-schools try to equip college graduates with skills and knowledge to work in the Information Field (iField), the Living In the KnowlEdgeSociety (LIKES) Community Building project focuses broadly on preparing these graduates to live in and to build the emerging knowledge society of the 21stcentury. We expect that LIKES graduates will connect naturally with the iField, and hope for more synergy between the two initiatives.
Chung, W. and Leung, A. Supporting Web searching of business intelligence with information visualization. In Proceedings of the IEEE/WIC/ACM International Conference on Web Intelligence (Fremont, CA, 2007).
In this research, we proposed and validated an
approach to using information visualization to augment search
engines in supporting the analysis of business stakeholder
information on the Web. We report in this paper findings from a
preliminary evaluation comparing a visualization prototype with
a traditional method of stakeholder analysis (Web browsing and
searching). We found that the prototype achieved a higher
perceived usefulness and perceived analysis effectiveness and was
perceived favorably in expediting the subjects' decision making
and in helping them understand the analysis results. Overall, the
proposed approach was found to augment traditional methods of
analyzing business stakeholders. We discuss implications to
researchers and practitioners and future directions.
Chung, W. and Wang, G. A. Profiling and visualizing cyber-criminal activities: A general framework. In Proceedings of the International Conference on Intelligence and Security Informatics (New Brunswick, NJ, May 23-24, 2007, 2007).
As the US-Mexico border areas recently emerge as a hub for cyber-criminal activities, the El Paso (Texas) division of FBI processes voluminous cases on Internet crimes. Using data from the Internet Crime Complaint Center this research project aims to develop and validate scalable methods and techniques for profiling and visualizing cyber-criminal activities. A general framework and potential contributions are discussed.
Chung, W. Evaluating the use of a visual approach to business stakeholder analysis. In Proceedings of the Fifth AIS SIGHCI Annual Workshop on HCI Research in MIS (Milwaukee, WI, 2006).
As businesses increasingly use the Web to share information with stakeholders, the problems arising from information overload and interconnected nature of the Web make it difficult to obtain business intelligence (BI). This research proposes a visual approach to business stakeholder analysis that integrates information visualization and Web mining techniques with human domain knowledge. A proof-of-concept prototype was developed based on the approach to assist in analyzing and visualizing complicated stakeholder networks on the Web. We report results of an empirical evaluation comparing the prototype with a traditional method of BI analysis and discuss the implications on HCI research and BI systems development.
Chung, W. Supporting E-Business Stakeholder Analysis with a Visualization Tool: An Experiment with Students and Business Practitioners. In Proceedings of the Fifth Workshop on e-Business (Milwaukee, WI, 2006).
As businesses increasingly use the Web to share information with stakeholders, the problems arising from information overload and interconnected nature of the Web make it difficult to obtain business intelligence (BI). This research proposes a visual approach to business stakeholder analysis that integrates information visualization and Web mining techniques with human domain knowledge. A proof-of-concept prototype was developed based on the approach to assist in analyzing and visualizing complicated stakeholder networks on the Web. We report results of an empirical evaluation comparing the prototype with a traditional method of BI analysis and discuss the implications on HCI research and BI systems development.
Chung, W. Designing Web-based business intelligence systems: A framework and case studies. In Proceedings of the The First International Conference on Design Science Research in Information Systems and Technology (Claremont, CA, 2006).
As businesses increasingly use the Web to share and disseminate information, effectively and efficiently discovering business intelligence (BI) from voluminous information has challenged researchers and practitioners. In this paper, we have proposed a framework for discovering BI on the Web. The framework consists of steps including collection, conversion, extraction, analysis, and visualization that transform Web data into business intelligence. Combinations of data and text mining techniques were used to assist human analysis in different scenarios. The two case studies applying the framework to BI applications present two Web-based BI systems that respectively help to explore BI from a large number of search results and to automatically classifu business stakeholder Web pages. Experimental results show that the systems compared favorably with the benchmark methods. Based on these results and our experience, we present the principles of designing these systems. This research contributes to advancing the science of designing Web-based BI systems.
Chung, W. Business Stakeholder Analyzer: an automatic classification approach to facilitating collaborative commerce on the Web. In Proceedings of the Hawaii International Conference on System Sciences (Island of Hawaii, 2005).
As businesses increasingly use the Web to share information with stakeholders, the problems arising from information overload and interconnected nature of the Web make it difficult to obtain business intelligence (BI). This research proposes a visual approach to business stakeholder analysis that integrates information visualization and Web mining techniques with human domain knowledge. A proof-of-concept prototype was developed based on the approach to assist in analyzing and visualizing complicated stakeholder networks on the Web. We report results of an empirical evaluation comparing the prototype with a traditional method of BI analysis and discuss the implications on HCI research and BI systems development.
Chung, W. Decision support in business stakeholder analysis: An automatic classification approach versus human judgment. In Proceedings of the 36th Annual Meeting of the Decision Sciences Institute (San Francisco, CA, November 19-22, 2005, 2005).
As businesses increasingly use the Web to share information with stakeholders, the problems arising from information overload and interconnected nature of the Web make it difficult to obtain business intelligence (BI). This research proposes a visual approach to business stakeholder analysis that integrates information visualization and Web mining techniques with human domain knowledge. A proof-of-concept prototype was developed based on the approach to assist in analyzing and visualizing complicated stakeholder networks on the Web. We report results of an empirical evaluation comparing the prototype with a traditional method of BI analysis and discuss the implications on HCI research and BI systems development.
Chung, W., Elhourani, T., Bonillas, A., Lai, G., Xi, W. and Chen, H. Supporting information seeking in multinational organizations: A knowledge portal approach. In Proceedings of the Hawaii International Conference on System Sciences (Island of Hawaii, 2005).
As businesses increasingly use the Web to share information with stakeholders, the problems arising from information overload and interconnected nature of the Web make it difficult to obtain business intelligence (BI). This research proposes a visual approach to business stakeholder analysis that integrates information visualization and Web mining techniques with human domain knowledge. A proof-of-concept prototype was developed based on the approach to assist in analyzing and visualizing complicated stakeholder networks on the Web. We report results of an empirical evaluation comparing the prototype with a traditional method of BI analysis and discuss the implications on HCI research and BI systems development.
Tseng, B., Kwon, Y., Ertekinc, Y. M., Chung, W. and Jiang, F. Comparative analysis between in-process CNC touch probe gauging and post-process CMM inspection. In Proceedings of the Proceedings of IEE Industrial Engineering Research Conference (Atlanta, GA, 2005).
In-process part inspection using a spindle touch probe has gained a significant importance, mainly because parts can
stay on the machine without disrupting the machine setup while inspection is being conducted. This practice leads to
a shorter inspection time, improved part accuracies, and reduction of scraps. Recently, intense domestic and
international competition has put more importance on part quality in terms of producing parts right the first time and
maintaining the consistent quality standards. A literature review revealed that a comparative analysis between inprocess
gauging using a touch probe and post-process inspection using a coordinate measuring machine (CMM) to
ascertain part quality has not been adequately studied. Therefore, there is a need for a study to measure the
characteristics of the two inspection techniques. To address the problem, cutting experiments were conducted and
measurement data were analyzed using a state-of-the-art CNC machine, a CMM, a touch probe, and a highprecision
ballbar system. The experimental data show that machined features and touch probe measurements are
affected by the inherent shortcomings in machine tool structures, suggesting a machine tool capability analysis be
undertaken in tune with the required tolerance specifications prior to machining operations, rather than solely
relying on the touch probe inspection for part quality assessment.
Chung, W., Chaboya, L. G., O'Toole, C. and Atabakhsh, H. An evaluation methodology for coordinated event visualization in digital libraries. In Proceedings of the Fourth ACM/IEEE-CS Joint Conference on Digital Libraries (Tucson, Arizona, 2004).
Event visualization holds the promise of alleviaing information overload in digital libraries. We propose a methodology for evaluating a coordinated event visualization tool called COPLINK Spatio- Temporal Visualizer (STV). The methodology examines different event dimensions and compares STV with another frequently used crime analysis tool (Microsoft Excel). We briefly describe the experimental procedure and result, and discuss future directions.
Reid, E., Qin, J., Chung, W., Xu, J., Zhou, Y., Schumaker, R., Sageman, M. and Chen, H. Terrorism knowledge discovery project: a knowledge discovery approach to addressing the threats of terrorism. In Proceedings of the Second Symposium on Intelligence and Security Informatics (Tucson, Arizona, 2004).
Ever since the 9-11 incident, the multidisciplinary field of terrorism
has experienced tremendous growth. As the domain has benefited greatly from
recent advances in information technologies, more complex and challenging
new issues have emerged from numerous counter-terrorism-related research
communities as well as governments of all levels. In this paper, we describe an
advanced knowledge discovery approach to addressing terrorism threats. We
experimented with our approach in a project called Terrorism Knowledge Discovery
Project that consists of several custom-built knowledge portals. The
main focus of this project is to provide advanced methodologies for analyzing
terrorism research, terrorists, and the terrorized groups (victims). Once completed,
the system can also become a major learning resource and tool that the
general community can use to heighten their awareness and understanding of
global terrorism phenomenon, to learn how best they can respond to terrorism
and, eventually, to garner significant grass root support for the government's efforts
to keep America safe.
Chang, W., Chung, W., Chen, H. and Chou, S. An international perspective on fighting cybercrime. In Proceedings of the First NSF/NIJ Symposium on Intelligence and Security Informatics (ISI 2003).
Cybercrime is becoming ever more serious. Findings from the 2002 Computer Crime and Security Survey show an upward trend that demonstrates a need for a timely review of existing approaches to fighting this new phe-nomenon in the information age. In this paper, we provide an overview of cy-bercrime and present an international perspective on fighting cybercrime. We review current status of fighting cybercrime in different countries, which rely on legal, organizational, and technological approaches, and recommend four di-rections for governments, lawmakers, intelligence and law enforcement agen-cies, and researchers to combat cybercrime.
Chen, H., Chung, W., Qin, Y., Chau, M., Xu, J., Wang, G., Zheng, R. and Atabakhsh, H. Crime data mining: an overview and case studies. In Proceedings of the National Conference for Digital Government Research (Boston, MA, 2003).
The concern about data national security has increased significantly since the 9/11 attacks. However, information overload hinders the effective analysis of criminal and terrorists activities. Data mining applied in the context of law enforcement and intelligence analysis holds the promise of alleviating such problems. In this paper, we review crime data mining techniques and present four case studies in our ongoing COPLINK project.
Chung, W., Chen, H. and Nunamaker, J. F. Business Intelligence Explorer: a knowledge map framework for discovering business intelligence on the Web. In Proceedings of the 36th Hawaii International Conference on System Sciences (HICSS-36) (Island of Hawaii, HI, USA, 2003).
Nowadays, information overload hinders the discovery of business intelligence on the World Wide Web. Existing business intelligence tools sufer from a lack of analysis and visualization capabilities and traditional result list display by search engines often overwhelms business analysts with irrelevant information. Thus, developing tools that enable better analysis while reduce information has been a challence. The literature show that hierarchical and map displays enable effective access and browsing of information. However, they have not been widely applied to discover business intelligence on the Web. This research proposes Business Intelligence Explorer, a tool implementing the steps in a knowledge map framework for discovering business intelligence on the Web. Two browsing methods, namely, Web community and knowledge map, have been implemented. Web community uses a genetic algorithm to organize different Web sites into a hierarchical format. Knowledge map uses a multidimensional scaling algorithm to place different Web sutes as points on a map. Preliminary results of our user study shows that Web community helps user locate results quickly and effectively. Users liked the intuitive map display of knowledge map. Our Business Intelligence Explorer contributes to alleviate information overload in business analysis. Future directions on applying document visualization techniques in discovering business intelligence are described.
Zhou, Y., Qin, J., Chen, H., Huang, Z., Zhang, Y., Chung, W. and Wang, G. CMedPort: a cross-regional Chinese medical portal. In Proceedings of the Third ACM/IEEE-CS Joint Conference on Digital Libraries (Houston, TX, 2003).
CMedPort is a cross-regional Chinese medical Web
portal developed in the AI Lab at the University of Arizona.
We will demonstrate the major system functionalities.
Huang, Z., Chung, W., Ong, T. and Chen, H. A graph-based recommender system for digital library. In Proceedings of the Second ACM/IEEE-CS Joint Conference on Digital Libraries.
Research shows that recommendations comprise a valuable
service for users of a digital library [11]. While most existing
recommender systems rely either on a content-based
approach or a collaborative approach to make
recommendations, there is potential to improve
recommendation quality by using a combination of both
approaches (a hybrid approach). In this paper, we report how
we tested the idea of using a graph-based recommender
system that naturally combines the content-based and
collaborative approaches. Due to the similarity between our
problem and a concept retrieval task, a Hopfield net
algorithm was used to exploit high-degree book-book, useruser
and book-user associations. Sample hold-out testing and
preliminary subject testing were conducted to evaluate the
system, by which it was found that the system gained
improvement with respect to both precision and recall by
combining content-based and collaborative approaches.
However, no significant improvement was observed by
exploiting high-degree associations.
Chung, W. A conceptual analysis on correlating the CASE success factors with the dimensions of IS function performance. In Proceedings of the 5th World Multiconference on Systemics, Cybernetics and Informatics.
In the past fifteen years, numerous articles on
Computer-Aided Software Engineering (CASE) have
been published on a wide variety of topics. However,
it is surprising to find there is hardly any research
performed on correlating CASE success factors with
the dimensions of IS function performance. This
paper aims at filling this research gap in order to
logically relate the factors contributing to CASE
success / failure and IS function performance. It
addresses the factors contributing to CASE success or
failure and discusses the dimensions used to measure
IS function performance. It is found that
infrastructure support, user participation / support and
training on CASE implementation affect a great
number of IS function performance clusters including
operational and financial performance, knowledge
sharing and integration across business functions, and
assimilation with other technologies. Also, the vision
of CASE adoption, management support, and costs
and benefits of implementing CASE affect some IS
clusters like strategic impact of IS to the
organization, user / management attitude. It is hoped
that this paper paves the way for more in-depth
investigation on CASE implementation and IS
function performance, and hence benefit the
academia and the MIS field.
Chung, W. The use of large-scale non-linear integer programming in scheduling the timetable of a secondary school in Hong Kong. In Proceedings of the Fourth Asia Pacific Decision Science Institute Conference, Shanghai, China, 1999.
This paper presents a large scale non-linear integer programming model to schedule the school timetable of a secondary
school in Hong Kong. A large number of constraints are generated to address to the many particular needs of the school,
namely, subject requirements, split classes, teachers' constraints, classroom constraints, and other special constraints.
Owing to the large number of subject-class combinations, the number of constraints on subject requirements is large (about
10,000 constraints) and hence makes the actual solving difficult. However, a sucessful model formulation of this problem
is presented for further studies. The contribution of this paper is to provide a theoretical framework for modelling school
