Zhijun Yan

EXPRS: An extended pagerank method for product feature extraction from online consumer reviews

Abstract Online consumer product reviews are a main source for consumers to obtain product information and reduce product uncertainty before making a purchase decision. However, the great volume of product reviews makes it tedious and ineffective for consumers to peruse individual reviews one by one and search for comments on specific product features of their interest. This study proposes a novel method called EXPRS that integrates an extended PageRank algorithm, synonym expansion, and implicit feature inference to extract product features automatically. The empirical evaluation using consumer reviews on three different products shows that EXPRS is more effective than two baseline methods.

Knowledge sharing in online health communities: A social exchange theory perspective

Abstract Online health communities (OHC) are becoming valuable platforms for patients to communicate and find support. These communities are different from general online communities. The knowledge shared in an OHC can be categorized as either general (public) or specific (private), and each category is shared in vastly different ways. Using the social exchange theory, we propose a benefit vs. cost knowledge sharing model for OHCs. The benefits are mainly based on Maslows hierarchy of needs, and the cost includes cognitive and executional costs. We use this benefit vs. cost model to examine how OHC members share general and specific knowledge. Data were collected from 323 users of two well-known OHCs in China and were analyzed using the structural equation model. The results demonstrate that three factors positively impact the sharing of both general and specific knowledge: a sense of self-worth, members’ perceived social support, and reputation enhancement. Another factor, face concern, has a negative influence on specific knowledge sharing and a positive influence on general knowledge sharing. Executional cost only negatively impacts general knowledge sharing, and cognitive cost only negatively impacts specific knowledge sharing. This study of OHCs reveals that personal benefits promote knowledge sharing and costs prohibit it. These impacts vary between general knowledge and specific knowledge sharing.

A domain-feature enhanced classification model for the detection of Chinese phishing e-Business websites

We propose a novel classification model that consists of features of website URLs and content for automatically detecting Chinese phishing e-Business websites. The model incorporates several unique domain-specific features of Chinese e-Business websites. We evaluated the proposed model using four different classification algorithms and approximately 3,000 Chinese e-Business websites. The results show that the Sequential Minimal Optimization (SMO) algorithm performs the best. The proposed model outperforms two baseline models in detection precision, recall, and F-measure. The results of a sensitivity analysis demonstrate that domain-specific features have the most significant impact on the detection of Chinese phishing e-Business websites.

Can rewiring strategy control the epidemic spreading

Abstract Relation existed in the social contact network can affect individuals’ behaviors greatly. Considering the diversity of relation intimacy among network nodes, an epidemic propagation model is proposed by incorporating the link-breaking threshold, which is normally neglected in the rewiring strategy. The impact of rewiring strategy on the epidemic spreading in the weighted adaptive network is explored. The results show that the rewiring strategy cannot always control the epidemic prevalence, especially when the link-breaking threshold is low. Meanwhile, as well as strong links, weak links also play a significant role on epidemic spreading.

A social contagious model of the obesity epidemic

Obesity has been recognized as a global epidemic by WHO, followed by many empirical evidences to prove its infectiousness. However, the inter-person spreading dynamics of obesity are seldom studied. A distinguishing feature of the obesity epidemic is that it is driven by a social contagion process which cannot be perfectly described by the infectious disease models. In this paper, we propose a novel belief decision model based on the famous Dempster-Shafer theory of evidence to model obesity epidemic as the competing spread of two obesity-related behaviors: physical inactivity and physical activity. The transition of health states is described by an SIS model. Results reveal the existence of obesity epidemic threshold, above which obesity is quickly eradicated. When increasing the fading level of information spread, enlarging the clustering of initial obese seeds, or introducing small-world characteristics into the network topology, the threshold is easily met. Social discrimination against the obese people plays completely different roles in two cases: on one hand, when obesity cannot be eradicated, social discrimination can reduce the number of obese people; on the other hand, when obesity is eradicable, social discrimination may instead cause it breaking out.

An Empirical Study: Measuring the Service Quality of an e-Learning System with the Model of ZOT SERVQUAL

Significant changes in the age of information has shift the education paradigm from teacher-centered to learner-centered. Along with this paradigm shift, e-learning systems have taken an important role. However, compared with the research on the design and development of e-learning systems from different perspectives, not much of results of research on the measurement of services provided by e-learning systems have been known. By using an IS-adapted ZOT SERVQUAL model into the investigation on the users of an e-learning system and presenting results of the measurement, the study attempts to evaluate users’ satisfaction of services quality provided by the e-learning system we are using, and then provides the diagnostic suggestion on improvements for better service quality.

Health implications of improved air quality from Beijing's driving restriction policy☆

Driving restrictions is one policy that Beijing enforces to alleviate traffic congestion and air pollution. Based on a before-after comparative research design with general additive models (GAM), we evaluated the effects of Beijings driving restriction policy on air pollution and public health. The results showed that driving restrictions significantly lowered the risk of hazardous pollution and brought valuable health benefits. Moreover, the health effects of the driving restriction policy were stronger in the cold season, for females and for residents above 65 years old. The findings imply that driving restrictions in Beijing offer substantial environmental and health benefits.

Personalized recommendation for learning resources based-on case reasoning agents

Ample online resources for e-learning provide students with choices and initiative, which however results in much challenge in matching the needs of students with different backgrounds and learning preferences due to information overload. Facing diverse learning resources, students have difficulties in making appropriate choices to meet their learning objectives. This paper proposes a framework of multi-agents collaboration case-based reasoning (MACBR) for personalized recommendations of e-learning resources, taking into account of characteristics of the learner. The paper firstly presents a workflow of Case-based Reasoning (CBR) for learning resource recommendation, and then proposes the collaboration framework of MACBR, finally illustrates the application of MACBR for personalized recommendation in e-learning.

Association between air pollution and chronic diseases among the elderly in China

With the development of Chinese economies, air pollution is becoming more and more serious, which greatly affects the residents’ daily life and health. Meanwhile, China’s aging population is growing rapidly and bringing a number of social problems. We used the data of CHARLS and analyzed the relationships between air pollution and chronic diseases among the elderly in China. The results showed that air pollution had significant adverse effects on the health of the elderly, especially on diabetes and heart diseases. The subgroup analysis showed that female is more sensitive to air pollution than male, while different age groups are significantly sensitive to different chronic diseases.

The impact of energy consumption on environment and public health in China

Fossil energy consumption is one of the main reasons for the deterioration of environmental pollution and decline in public health. This paper tests for the long-run and short-run relationship among energy consumption, environment pollution and public health using the autoregressive-distributed lag approach in China for the period 1985–2014. The study used energy consumption variables (i.e., the proportion of coal consumption, that of oil and clean energy, abbreviated as PCC, POIL and PCE, respectively), environmental pollution ones (i.e., SO2 emissions, abbreviated SO2, soot and dust emissions,), two health proxies (i.e., the proportion of cardiovascular and respiratory diseases mortality, abbreviated as PCD and PRD, respectively). These variables were selected due to vital importance in China. The overall results indicate that there was co-integration relationship under the study with statistically significantly positive relationship between environmental pollution and energy consumption, public health and environmental pollution in the short and long run. Comparing the long-run and short-run coefficients of energy use variable with respect to SO2 and soot indicates that the long-run coefficients are the same as the short-run. The long-run coefficients of soot and dust emissions with respect to PCD and PRD, respectively, are higher than the short-run coefficients. This implies that environment pollution level is found to worsen with respect to fossil energy use presently and over time, while public health level descending with reference to soot and dust emission over time in China. The Granger causality results suggested a unidirectional Granger causality between energy use and environment pollution, environment pollution and public health. The results emphasized the importance of energy transformation and sustainable development policies that help to adjust the structure of energy consumption and to improve public health level.