Yulei Zhang

A Lexicon-Enhanced Method for Sentiment Classification: An Experiment on Online Product Reviews

As an emerging communication platform, Web 2.0 has led the Internet to become increasingly user-centric. People are participating in and exchanging opinions through online community-based social media, such as discussion boards, Web forums, and blogs. Along with such trends, an increasing amount of user-generated content containing rich opinion and sentiment information has appeared on the Internet. Understanding such opinion and sentiment information has become increasingly important for both service and product providers and users because it plays an important role in influencing consumer purchasing decisions.

Evaluating sentiment in financial news articles

Can the choice of words and tone used by the authors of financial news articles correlate to measurable stock price movements? If so, can the magnitude of price movement be predicted using these same variables? We investigate these questions using the Arizona Financial Text (AZFinText) system, a financial news article prediction system, and pair it with a sentiment analysis tool. Through our analysis, we found that subjective news articles were easier to predict in price direction (59.0% versus 50.0% of chance alone) and using a simple trading engine, subjective articles garnered a 3.30% return. Looking further into the role of author tone in financial news articles, we found that articles with a negative sentiment were easiest to predict in price direction (50.9% versus 50.0% of chance alone) and a 3.04% trading return. Investigating negative sentiment further, we found that our system was able to predict price decreases in articles of a positive sentiment 53.5% of the time, and price increases in articles of a negative sentiment 52.4% of the time. We believe that perhaps this result can be attributable to market traders behaving in a contrarian manner, e.g., see good news, sell; see bad news, buy.

Trends in worldwide nanotechnology patent applications: 1991 to 2008

Nanotechnology patent applications published during 1991–2008 have been examined using the “title–abstract” keyword search on esp@cenet “worldwide” database. The longitudinal evolution of the number of patent applications, their topics, and their respective patent families have been evaluated for 15 national patent offices covering 98% of the total global activity. The patent offices of the United States (USA), People’s Republic of China (PRC), Japan, and South Korea have published the largest number of nanotechnology patent applications, and experienced significant but different growth rates after 2000. In most repositories, the largest numbers of nanotechnology patent applications originated from their own countries/regions, indicating a significant “home advantage.” The top applicant institutions are from different sectors in different countries (e.g., from industry in the US and Canada patent offices, and from academe or government agencies at the PRC office). As compared to 2000, the year before the establishment of the US National Nanotechnology Initiative (NNI), numerous new invention topics appeared in 2008, in all 15 patent repositories. This is more pronounced in the USA and PRC. Patent families have increased among the 15 patent offices, particularly after 2005. Overlapping patent applications increased from none in 1991 to about 4% in 2000 and to about 27% in 2008. The largest share of equivalent nanotechnology patent applications (1,258) between two repositories was identified between the US and Japan patent offices.

Automatic online news monitoring and classification for syndromic surveillance

Abstract Syndromic surveillance can play an important role in protecting the publics health against infectious diseases. Infectious disease outbreaks can have a devastating effect on society as well as the economy, and global awareness is therefore critical to protecting against major outbreaks. By monitoring online news sources and developing an accurate news classification system for syndromic surveillance, public health personnel can be apprised of outbreaks and potential outbreak situations. In this study, we have developed a framework for automatic online news monitoring and classification for syndromic surveillance. The framework is unique and none of the techniques adopted in this study have been previously used in the context of syndromic surveillance on infectious diseases. In recent classification experiments, we compared the performance of different feature subsets on different machine learning algorithms. The results showed that the combined feature subsets including Bag of Words, Noun Phrases, and Named Entities features outperformed the Bag of Words feature subsets. Furthermore, feature selection improved the performance of feature subsets in online news classification. The highest classification performance was achieved when using SVM upon the selected combination feature subset.

Knowledge mapping for rapidly evolving domains: A design science approach

Knowledge mapping can provide comprehensive depictions of rapidly evolving scientific domains. Taking the design science approach, we developed a Web-based knowledge mapping system (i.e., Nano Mapper) that provides interactive search and analysis on various scientific document sources in nanotechnology. We conducted multiple studies to evaluate Nano Mappers search and analysis functionality respectively. The search functionality appears more effective than that of the benchmark systems. Subjects exhibit favorable satisfaction with the analysis functionality. Our study addresses several gaps in knowledge mapping for nanotechnology and illustrates desirability of using the design science approach to design, implement, and evaluate an advanced information system.

Developing a Dark Web collection and infrastructure for computational and social sciences

In recent years, there have been numerous studies from a variety of perspectives analyzing the Internet presence of hate and extremist groups. Yet the websites and forums of extremist and terrorist groups have long remained an underutilized resource for terrorism researchers due to their ephemeral nature and access and analysis problems. The purpose of the Dark Web archive is to provide a research infrastructure for use by social scientists, computer and information scientists, policy and security analysts, and others studying a wide range of social and organizational phenomena and computational problems. The Dark Web Forum Portal provides web enabled access to critical international jihadist and other extremist web forums. The focus of this paper is on the significant extensions to previous work including: increasing the scope of data collection, adding an incremental spidering component for regular data updates; enhancing the searching and browsing functions; enhancing multilingual machine-translation for Arabic, French, German and Russian; and advanced Social Network Analysis. A case study on identifying active participants is shown at the end.

Dark web forums portal: Searching and analyzing jihadist forums

With the advent of Web 2.0, the Web is acting as a platform which enables end-user content generation. As a major type of social media in Web 2.0, Web forums facilitate intensive interactions among participants. International Jihadist groups often use Web forums to promote violence and distribute propaganda materials. These Dark Web forums are heterogeneous and widely distributed. Therefore, how to access and analyze the forum messages and interactions among participants is becoming an issue. This paper presents a general framework for Web forum data integration. Specifically, a Web-based knowledge portal, the Dark Web Forums Portal, is built based on the framework. The portal incorporates the data collected from different international Jihadist forums and provides several important analysis functions, including forum browsing and searching (in single forum and across multiple forums), forum statistics analysis, multilingual translation, and social network visualization. Preliminary results of our user study show that the Dark Web Forums Portal helps users locate information quickly and effectively. Users found the forum statistics analysis, multilingual translation, and social network visualization functions of the portal to be particularly valuable.

Gender Classification for Web Forums

More and more women are participating in and exchanging opinions through community-based online social media. Questions concerning gender differences in the new media have been raised. This paper proposes a feature-based text classification framework to examine online gender differences between Web forum posters by analyzing writing styles and topics of interest. Our experiment on an Islamic womens political forum shows that feature sets containing both content-free and content-specific features perform significantly better than those consisting of only content-free features, feature selection can improve the classification results significantly, and female and male participants have significantly different topics of interest.

Research note: Examining gender emotional differences in Web forum communication

Abstract Web 2.0 has enabled and fostered Internet users to share and discuss their opinions and ideas online. Thus, a large amount of opinion-rich content has been generated. With more and more women starting to participate in online communications, questions regarding gender emotional differences in Web 2.0 communication platform have been raised. However, few studies have systematically examined such differences. Motivated to address this gap, we have developed an advanced and generic framework to automatically analyze gender emotional differences in social media. Algorithms are developed and embedded in the framework to conduct analyses in different granularity levels, including sentence level, phrase level, and word level. To demonstrate the proposed research framework, an empirical experiment is conducted on a large Web forum. The analysis results indicate that women are more likely to express their opinions subjectively than men (based on sentence-level analysis), and they are more likely to express both positive and negative emotions (based on phrase-level and word-level analyses).

An Integrated Framework for Avatar Data Collection from the Virtual World

To mine the rich social media data produced in virtual worlds, an integrated framework combines bot- and spider-based approaches to collect avatar behavioral and profile data.