Daniel Zeng

Social Media Analytics and Intelligence

In a broad sense, social media refers to a conversational, distributed mode of content generation, dissemination, and communication among communities. Different from broadcast-based traditional and industrial media, social media has torn down the boundaries between authorship and readership, while the information consumption and dissemination process is becoming intrinsically intertwined with the process of generating and sharing information. This special issue samples the state of the art in social media analytics and intelligence research that has direct relevance to the AI subfield from either an methodological or domain perspective.

Smart Cars on Smart Roads: An IEEE Intelligent Transportation Systems Society Update

To promote tighter collaboration between the IEEE Intelligent Transportation Systems Society and the pervasive computing research community, the authors introduce the ITS Society and present several pervasive computing-related research topics that ITS Society researchers are working on. This department is part of a special issue on Intelligent Transportation.

A Study of the Human Flesh Search Engine: Crowd-Powered Expansion of Online Knowledge

This first comprehensive empirical study of a search function that originated in China examines its tremendous growth in recent years and its uniquely rich online/offline interactions.This first comprehensive empirical study of a search function that originated in China examines its tremendous growth in recent years and its uniquely rich online/offline interactions.

Twitter Sentiment Analysis: A Bootstrap Ensemble Framework

Twitter sentiment analysis has become widely popular. However, stable Twitter sentiment classification performance remains elusive due to several issues: heavy class imbalance in a multi-class problem, representational richness issues for sentiment cues, and the use of diverse colloquial linguistic patterns. These issues are problematic since many forms of social media analytics rely on accurate underlying Twitter sentiments. Accordingly, a text analytics framework is proposed for Twitter sentiment analysis. The framework uses an elaborate bootstrapping ensemble to quell class imbalance, sparsity, and representational richness issues. Experiment results reveal that the proposed approach is more accurate and balanced in its predictions across sentiment classes, as compared to various comparison tools and algorithms. Consequently, the bootstrapping ensemble framework is able to build sentiment time series that are better able to reflect events eliciting strong positive and negative sentiments from users. Considering the importance of Twitter as one of the premiere social media platforms, the results have important implications for social media analytics and social intelligence.

New York City Syndromic Surveillance Systems

The New York City (NYC) Department of Health and Mental Hygiene (DOHMH) has conducted prospective surveillance of nonspecific health indicators (syndromes) since 1995 (Heffernan et al., 2004a). The DOHMH syndromic surveillance system consists of (ED)-visits-based surveillance system and a few other complementary surveillance systems for Emergency Medical Services (EMS) ambulance dispatch calls, retail pharmacy sales, and work absenteeism data. These systems started operating separately, and different analytical methods are being employed by each of them. A “drop-in” syndromic surveillance system that deployed CDC field-staff to conduct 24 hours surveillance for bioterrorism related illness was implemented following the September 11th 2001 attack (Das et al., 2003; CDC, 2002). We use Table 11-1 to summarize these systems that comprise the syndromic surveillance activities in New York City. However, in the following text, the case study will focus around the ED visits based syndromic surveillance system in NYC.The New York City (NYC) Department of Health and Mental Hygiene (DOHMH) has conducted prospective surveillance of nonspecific health indicators (syndromes) since 1995 (Heffernan et al., 2004a). The DOHMH syndromic surveillance system consists of (ED)-visits-based surveillance system and a few other complementary surveillance systems for Emergency Medical Services (EMS) ambulance dispatch calls, retail pharmacy sales, and work absenteeism data. These systems started operating separately, and different analytical methods are being employed by each of them. A “drop-in” syndromic surveillance system that deployed CDC field-staff to conduct 24 hours surveillance for bioterrorism related illness was implemented following the September 11th 2001 attack (Das et al., 2003; CDC, 2002). We use Table 11-1 to summarize these systems that comprise the syndromic surveillance activities in New York City. However, in the following text, the case study will focus around the ED visits based syndromic surveillance system in NYC.

Intelligent Railway Systems in China

The Chinese rail transportation system has been going through a period of rapid improvement and innovation. Despite this rapid development, the railroad lines are far from meeting the countrys expanding travel and freight transportation needs. According to some recent estimates, the current systems meet only 35 percent of the freight orders on a typical day. The shortfall has significant negative economic impact on many sectors of the economy. During major national holidays and festivals, getting a railway ticket and making the trip are major endeavors for travelers. As a national response to these gaps between capacities and needs, the government is investing heavily in the rail transportation system. This rapid expansion is bringing significant opportunities as well as challenges to both academia and industry. The next-generation Chinese rail transportation system will require major advances in related technologies. Intelligent rail transportation systems represent a critical enabling framework

Ontology-enhanced automatic chief complaint classification for syndromic surveillance

Emergency department free-text chief complaints (CCs) are a major data source for syndromic surveillance. CCs need to be classified into syndromic categories for subsequent automatic analysis. However, the lack of a standard vocabulary and high-quality encodings of CCs hinder effective classification. This paper presents a new ontology-enhanced automatic CC classification approach. Exploiting semantic relations in a medical ontology, this approach is motivated to address the CC vocabulary variation problem in general and to meet the specific need for a classification approach capable of handling multiple sets of syndromic categories. We report an experimental study comparing our approach with two popular CC classification methods using a real-world dataset. This study indicates that our ontology-enhanced approach performs significantly better than the benchmark methods in terms of sensitivity, F measure, and F2 measure.

How Useful Are Tags? — An Empirical Analysis of Collaborative Tagging for Web Page Recommendation

As a representative Web 2.0 application, collaborative tagging has been widely adopted and inspires significant interest from academies. Roughly, two lines of research have been pursued: (a) studying the structure of tags, and (b) using tag to promote Web search. However, both of them remain preliminary. Research reported in this paper is aimed at addressing some of these research gaps. First, we apply complex network theory to analyze various structural properties of collaborative tagging activities to gain a detailed understanding of user tagging behavior and also try to capture the mechanism that can help explain such tagging behavior. Second, we conduct a preliminary computational study to utilize tagging information to help improve the quality of Web page recommendation. The results indicate that under the user-based recommendation framework, tags can be fruitfully exploited as they facilitate better user similarity calculation and help reduce sparsity related to past user-Web page interactions.

Challenges and Future Directions

We conclude this book by discussing key challenges facing syndromic surveillance research and summarizing future directions. Although syndromic surveillance has gained wide acceptance as a response to disease outbreaks and bioterrorism attacks, many research challenges remain. First, there are circumstances in which syndromic surveillance may not be effective or necessary. The potential benefit of syndromic surveillance as to the timeliness of detection could not be realized if there were hundreds or thousands of people infected simultaneously. In extreme cases, modern biological weapons could easily lead to mass infection via airborne or waterborne agents. In another scenario, syndromic surveillance could be rendered ineffective if the cases involved only a few people (e.g., the anthrax outbreak in 2001) and thus would not trigger any alarms and could go undetected (2005b). In this situation, one single positive diagnosis of a spore of anthrax could be sufficient to confirm the event.

Finding leaders from opinion networks

This paper is motivated to utilize results from opinion mining to facilitate social network analysis. We introduce the concept of Opinion Networks and propose a PageRank-like algorithm, named OpinionRank, to rank the nodes in an opinion network. This proposed approach has been applied to real-world datasets and initial experiments indicate that the sentiment information is helpful for finding leaders of online communities and that the OpinionRank method outperforms benchmark methods that ignore sentiment information.