Jyh-Jian Sheu

An Efficient Two-phase Spam Filtering Method Based on E-mails Categorization

The e-mails header session usually contains important attributes such as e-mail title, senders name, senders e-mail address, sending date, which are helpful to classification of e-mails. In this paper, we apply decision tree data mining technique to headers basic attributes to analyze the association rules of spam e-mails and propose an efficient spam filtering method to accurately identify spam and legitimate e-mails. According to the experiment of applying numerous Chinese e-mails to our spam filtering method, we obtain the following excellent datums: the Accuracy is 96.5%, the Precision is 96.67%, and the Recall is 96.3%. Thus, the method proposed in this paper can efficiently identify the spam e-mails by checking only the header sessions, which can reduce the cost for calculation.

Strong diagnosability of regular networks under the comparison model

Diagnosability has played an important role in the reliability of multiprocessor systems. The strongly t-diagnosable system is (t+1) diagnosable except when all of the neighbors of a node are simultaneously faulty. In this paper, we discuss the in-depth properties of diagnosability for t-regular and t-connected networks under the comparison model. We show that a t-regular and t-connected multiprocessor system with at least 2t+6 nodes, for t>=4, is strongly t-diagnosable under the comparison model if the following two conditions hold: (1) the system is triangle free, and (2) there are at most t-2 common neighbors for each pair of distinct nodes in the system.

The associate impact of individual internal experiences and reference groups on buying behavior

We analyzed the influences of both internal cognitions and external environments on the loyalty of animations, comics, and video games consumers.We evaluated consumers internal cognitions through the five experiences in the strategic experiential module, and evaluated external influences through the influences of reference groups.We applied the uncomplicated decision tree data mining method to analyze the hidden association rules between the consumer loyalty and the critical influential factors of consumers internal impressions and external influences. Among the entertainment and media market, it can be observed that animations, comics, and video games (hereinafter abbreviated as ACG) have the highest output value and most market influence. Moreover, ACG also incorporates various industries and creates many derivative products. As the ACG industry emphasizes acousto-optics, imagery, and storylines, personal impressions derived from consumer experiences will influence consumer decisions. In addition, the ACG industry is mainly marketed towards younger age groups, with younger people being the main consumers; as such, these consumers decisions are more easily affected by peer behavior.This study aims to analyze the effects of internal cognitions and external influences on buying behavior of ACG consumers by applying the uncomplicated decision tree data mining algorithm. We analyze and develop the target attributes on measures of customer loyalty for ACG industry to set up the decision trees from the collected questionnaire data. The decision tree data mining method is applied to analyze the hidden association rules between the target attributes (i.e., consumer loyalty) and the critical influencing factors of consumers internal impressions and external influences for ACG consumers. The results and suggestions of this paper can be used as a reference for enterprises in the ACG industry to help with business policies concerning products extensional design, marketing, and CRM, and to further strengthen customer satisfaction and loyalty, thus increasing company profits.

Mining association rules between positive word-of-mouth on social network sites and consumer acceptance

Animations, comics, and games (ACG) have great output value and market influence on the entertainment and digit media market.In addition to its own revenue, the derivative products can extend the ACG industry to win more business opportunities.We analyzed the influential factors of eWOMs communication motivations that affect attitudinal acceptance and purchase intention for consumers of the ACG derivative products.We applied the uncomplicated decision tree method to analyze the hidden association rules between the influential factors of positive eWOM and consumer acceptance.The study found that two influential factors, the degree of perception of ACG product and the degree of taking delight in communication with others, have a great impact on consumer acceptance.The result of this study and the key success factors of the currently popular mobile game Pokmon GO could corroborate each other approximately. In recent years, we can easily observe that animations, comics, and games (ACG) have great output value and market influence on the entertainment and digit media market. The ACG industry is not an industry of a single country or region but a global industry. In addition to its own revenue, the derivative products (or licensed merchandise) of ACG can extend the ACG industry to win more business opportunities. The ACG industry is mainly marketed towards younger people, who are the major users of social network sites. Hence, the electronic word-of-mouth (eWOM) on social network sites often becomes a reference basis of the young peoples attitudinal acceptance and purchase intention in purchasing ACG-related derivative product.In this paper, we analyze the influential factors of positive eWOMs communication motivations that affect consumer acceptance on social network sites, and apply the uncomplicated decision tree data mining algorithm to compute the association rules between these influential factors and consumer acceptance, expecting to understand the relationship between eWOM on social network sites and consumer acceptance. The results of this study can help the business decision-making in CRM and marketing of the industry of ACG-related derivative product. This study found that the degree of perception of ACG product and the degree of taking pleasure in sharing ACG-related information with others have a significant correlation with consumer acceptance.

An efficient incremental learning mechanism for tracking concept drift in spam filtering

This research manages in-depth analysis on the knowledge about spams and expects to propose an efficient spam filtering method with the ability of adapting to the dynamic environment. We focus on the analysis of email’s header and apply decision tree data mining technique to look for the association rules about spams. Then, we propose an efficient systematic filtering method based on these association rules. Our systematic method has the following major advantages: (1) Checking only the header sections of emails, which is different from those spam filtering methods at present that have to analyze fully the email’s content. Meanwhile, the email filtering accuracy is expected to be enhanced. (2) Regarding the solution to the problem of concept drift, we propose a window-based technique to estimate for the condition of concept drift for each unknown email, which will help our filtering method in recognizing the occurrence of spam. (3) We propose an incremental learning mechanism for our filtering method to strengthen the ability of adapting to the dynamic environment.