List of Articles پروفایل

• Open Access Article
  • Abstract Page
  • Full-Text
  
  1 - A proper method for the advertising email classification based on user’s profiles
  rahim hazratgholizadeh Mohammad Fathian
  In general, Spam is related to satisfy or not satisfy the client and isn’t related to the content of the client’s email. According to this definition, problems arise in the field of marketing and advertising for example, it is possible that some of the advertising email More

  In general, Spam is related to satisfy or not satisfy the client and isn’t related to the content of the client’s email. According to this definition, problems arise in the field of marketing and advertising for example, it is possible that some of the advertising emails become spam for some users, and not spam for others. To deal with this problem, many researchers design an anti-spam based on personal profiles. Normally machine learning methods for spam classification with good accuracy are used. However, there isn’t a unique successful way based on Electronic Commerce approach. In this paper, at first were prepared a new profile that can lead to better simulations of user’s behavior. Then we gave this profile with advertising emails to students and collected their answers. In continue, were examined famous methods for email classification. Finally, comparing different methods by criteria of data mining standards, it can be shown that neural network method has the best accuracy for various data sets. Manuscript profile
• Open Access Article
  • Abstract Page
  • Full-Text
  
  2 - Identifying Cloned Profiles on Online Social Networks by Identifying Nodes in Overlapping Communities and User Interactions
  Zahra Hamzehzadeh
  With the growing popularity of social networks, identifying Profile Cloning Attacks (PCAs) is an important challenge within the scope of privacy in the communications world. Until now, researchers have identified these attacks by using features such as profile informati More

  With the growing popularity of social networks, identifying Profile Cloning Attacks (PCAs) is an important challenge within the scope of privacy in the communications world. Until now, researchers have identified these attacks by using features such as profile information, link information, and interactions information that are based on methods like similarities and network structure. Previously suggested approaches lack specific routine and logic to track an attacker, and begin identifying PCAs with victim direct requests or according to the time of a friend request from an attacker. This research offers a new approach with a total of two major steps. Step one emphasizes that  legitimate users are attracted to interactions within their local communities; conversely, attackers are attracted to more dense areas. Step two was designed according to the analysis of the interactive behavior that is obtained from users 'earlier research. With this approach, according to a logic based on network structure, search cloned profiles can be identified.   Finally, a list of suspicious nodes to cloned nodes has been introduced with their scores that show the accuracy of selection. During the research, a logical relation between the average degrees of social network graph and the selection of the appropriate suspicious nodes with high priority was extracted. Finally, a general framework is proposed. Manuscript profile
• Open Access Article
  • Abstract Page
  • Full-Text
  
  3 - Providing a suitable method for categorizing promotional e-mails based on user profiles
  Mohammad fathiyan rahim hazratgholizadeh
  In general, the definition of spam is related to the consent or lack of consent of the recipient, not the content of the e-mail. According to this definition, problems arise in the classification of electronic mails in marketing and advertising. For example, it is possi More

  In general, the definition of spam is related to the consent or lack of consent of the recipient, not the content of the e-mail. According to this definition, problems arise in the classification of electronic mails in marketing and advertising. For example, it is possible that some promotional e-mails are spam for some users and not spam for others. To deal with this problem, personal anti-spams are designed according to the profile and behavior of users. Usually, machine learning methods are used with good accuracy to classify spam. But in any case, there is no single successful method based on the point of view of e-commerce. In this article, first, a new profile is prepared to better simulate the behavior of users. Then this profile is presented to students along with emails and their responses are collected. In the following, well-known methods are tested for different data sets to categorize electronic mails. Finally, by comparing data mining evaluation criteria, neural network is determined as the best method with high accuracy. Manuscript profile