No abstract

No abstract

Abstract-Twitter is one of the most popular social network sites on the Internet to share opinions and knowledge extensively. Many advertisers use these Tweets to collect some features and attributes of Tweeters to target specific groups of highly engaged people. Gender detection is a sub-field of sentiment analysis for extracting and predicting the gender of a Tweet author. In this paper, we aim to investigate the gender of Tweet authors using different classification mining techniques on Arabic language, such as Naïve Bayes (NB), Support vector machine (SVM), Naïve Bayes Multinomial (NBM), J48 decision tree, KNN. The results show that the NBM, SVM, and J48 classifiers can achieve accuracy above to 98%, by adding names of Tweet author as a feature. The results also show that the preprocessing approach has negative effect on the accuracy of gender detection. In nutshell, this study shows that the ability of using machine learning classifiers in detecting the gender of Arabic Tweet author.

Cloud computing technology has opened an avenue to meet the critical need to securely share distributed resources and web services, and especially those that belong to clients who have sensitive data and applications. However, implementing crosscutting concerns for cloud-based applications is a challenge. This challenge stems from the nature of distributed Web-based technology architecture and infrastructure. One of the key concerns is security logic, which is scattered and tangled across all the cloud service layers. In addition, maintenance and modification of the security aspect is a difficult task. Therefore, cloud services need to be extended by enriching them with features to support adaptation so that these services can become better structured and less complex. Aspect-oriented programming is the right technical solution for this problem as it enables the required separation when implementing security features without the need to change the core code of the server or client in the cloud. Therefore, this article proposes a Runtime Reusable Weaving Model for weaving security-related crosscutting concerns through layers of cloud computing architecture. The proposed model does not require access to the source code of a cloud service and this can make it easier for the client to reuse the needed security-related crosscutting concerns. The proposed model is implemented using aspect orientation techniques to integrate cloud security solutions at the software-as-a-service layer.

No abstract