Wingyan Chung

Web searching in a multilingual world

Studies of three prototype Web search portals---in Chinese, Spanish, and Arabic---reveal how to best support non-English Web searching.

Exploring How the Tobacco Industry Presents and Promotes Itself in Social Media

Background The commercial potential of social media is utilized by tobacco manufacturers and vendors for tobacco promotion online. However, the prevalence and promotional strategies of pro-tobacco content in social media are still not widely understood. Objective The goal of this study was to reveal what is presented by the tobacco industry, and how it promotes itself, on social media sites. Methods The top 70 popular cigarette brands are divided into two groups according to their retail prices: group H (brands with high retail prices) and group L (brands with low retail prices). Three comprehensive searches were conducted on Facebook, Wikipedia, and YouTube respectively using the top 70 popular cigarette brands as keywords. We identified tobacco-related content including history and culture, product features, health warnings, home page of cigarette brands, and Web-based tobacco shops. Furthermore, we examined the promotional strategies utilized in social media. Results According to the data collected from March 3, 2014 to March 10, 2014, 43 of the 70 representative cigarette brands had created 238 Facebook fan pages, 46 cigarette brands were identified in Wikipedia, and there were over 120,000 pro-tobacco videos on YouTube, associated with 61 cigarette brands. The main content presented on the three social media websites differs significantly. Wikipedia focuses on history and culture (67%, 32/48; P<.001). Facebook mainly covers history and culture (37%, 16/43; P<.001) and major products (35%, 15/43), while YouTube focuses on the features of major tobacco products (79%, 48/61; P=.04) and information about Web-based shops (49%, 30/61; P=.004). Concerning the content presented by groups H and L, there is no significant difference between the two groups. With regard to the promotional strategies used, sales promotions exist extensively in social media. Sales promotion is more prevalent on YouTube than on the other two sites (64%, 39/61 vs 35%, 15/43; P=.004). Generally, the sale promotions of higher-cost brands in social media are more prevalent than those of lower-cost brands (55%, 16/29 vs 7%, 1/14; P<.001 for Facebook; 78%, 28/36 vs 44%, 11/25; P=.005 for YouTube). Conclusions The prevalence of cigarette brands in social media allows more pro-tobacco information to be accessed by online users. This dilemma indicates that corresponding regulations should be established to prevent tobacco promotion in social media.

BizPro: Extracting and categorizing business intelligence factors from textual news articles

Abstract Company movements and market changes often are headlines of the news, providing managers with important business intelligence (BI). While existing corporate analyses are often based on numerical financial figures, relatively little work has been done to reveal from textual news articles factors that represent BI. In this research, we developed BizPro, an intelligent system for extracting and categorizing BI factors from news articles. BizPro consists of novel text mining procedures and BI factor modeling and categorization. Expert guidance and human knowledge (with high inter-rater reliability) were used to inform system development and profiling of BI factors. We conducted a case study of using the system to profile BI factors of four major IT companies based on 6859 sentences extracted from 231 news articles published in major news sources. The results show that the chosen techniques used in BizPro – Naive Bayes (NB) and Logistic Regression (LR) – significantly outperformed a benchmark technique. NB was found to outperform LR in terms of precision, recall, F-measure, and area under ROC curve. This research contributes to developing a new system for profiling company BI factors from news articles, to providing new empirical findings to enhance understanding in BI factor extraction and categorization, and to addressing an important yet under-explored concern of BI analysis.

Group-Buying E-Commerce in China

Group-buying is growing rapidly in emerging economies, where Web sites have rudimentary functions and cluttered interfaces. The authors review 11 major Chinese group-buying Web sites, using case studies to provide timely guidance to e-commerce practitioners and researchers.

Organizing domain-specific information on the Web: An experiment on the Spanish business Web directory

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.

Evaluating text visualization: An experiment in authorship analysis

Analyzing authorship of online texts is an important analysis task in security-related areas such as cybercrime investigation and counter-terrorism, and in any field of endeavor in which authorship may be uncertain or obfuscated. This paper presents an automated approach for authorship analysis using machine learning methods, a robust stylometric feature set, and a series of visualizations designed to facilitate analysis at the feature, author, and message levels. A testbed consisting of 506,554 forum messages, in English and Arabic, from 14,901 authors was first constructed. A prototype portal system was then developed to support feasibility analysis of the approach. A preliminary evaluation to assess the efficacy of the text visualizations was conducted. The evaluation showed that task performance with the visualization functions was more accurate and more efficient than task performance without the visualizations.

Characterizing Social Interaction in Tobacco-Oriented Social Networks: An Empirical Analysis.

Social media is becoming a new battlefield for tobacco “wars”. Evaluating the current situation is very crucial for the advocacy of tobacco control in the age of social media. To reveal the impact of tobacco-related user-generated content, this paper characterizes user interaction and social influence utilizing social network analysis and information theoretic approaches. Our empirical studies demonstrate that the exploding pro-tobacco content has long-lasting effects with more active users and broader influence, and reveal the shortage of social media resources in global tobacco control. It is found that the user interaction in the pro-tobacco group is more active, and user-generated content for tobacco promotion is more successful in obtaining user attention. Furthermore, we construct three tobacco-related social networks and investigate the topological patterns of these tobacco-related social networks. We find that the size of the pro-tobacco network overwhelms the others, which suggests a huge number of users are exposed to the pro-tobacco content. These results indicate that the gap between tobacco promotion and tobacco control is widening and tobacco control may be losing ground to tobacco promotion in social media.

Evaluating text visualization for authorship analysis

Methods and tools to conduct authorship analysis of web contents is of growing interest to researchers and practitioners in various security-focused disciplines, including cybersecurity, counter-terrorism, and other fields in which authorship of text may at times be uncertain or obfuscated. Here we demonstrate an automated approach for authorship analysis of web contents. Analysis is conducted through the use of machine learning methodologies, an expansive stylometric feature set, and a series of visualizations intended to help facilitate authorship analysis at the author, message, and feature levels. To operationalize this, we utilize a testbed containing 506,554 forum messages in English and Arabic, source from 14,901 authors that participated in an online web forum. A prototype portal system providing authorship comparisons and visualizations was then designed and constructed in order to support feasibility analysis and real world value of the automated authorship analysis approach. A preliminary user evaluation was performed to assess the efficacy of visualizations, with evaluation results demonstrating task performance accuracy and efficiency was improved through use of the portal.

Managing web repositories in emerging economies: Case studies of browsing web directories

Abstract 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 4735 and 5107 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.

Visualising e-business stakeholders on the Web: a methodology and experimental results

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.