14 August 2020 in International Journal of Emerging Technologies in Learning (iJET)
Twitter is one of the most popular microblogging and social networking platforms where massive instant messages (i.e. tweets) are posted every day. Twitter sentiment analysis tackles the problem of analyzing users’ tweets in terms of thoughts, interests and opinions in a variety of contexts and domains. Such analysis can be valuable for several researchers and applications that require understanding people views about a particular topic or event. The study carried out in this paper provides an overview of the algorithms and approaches that have been used for sentiment analysis in twitter. The reviewed articles are categories into four categories based on the approach they use. Furthermore, we discuss directions for future research on how twitter sentiment analysis approaches can utilize theories and technologies from other fields such cognitive science, semantic Web, big data and visualization.
9 January 2017 in Journal of Information Science
Twitter is a social networking website that has gained a lot of popularity around the world in the last decade. This popularity made Twitter a common target for spammers and malicious users to spread unwanted advertisements, viruses and phishing attacks. In this article, we review the latest research works to determine the most effective features that were investigated for spam detection in the literature. These features are collected to build a comprehensive data set that can be used to develop more robust and accurate spammer detection models. The new data set is tested using popular classifiers (Naive Bayes, support vector machines, multilayer perceptron neural networks, Decision Trees, Random forests and k-Nearest Neighbour). The prediction performance of these classifiers is evaluated and compared based on different evaluation metrics. Moreover, a further analysis is carried out to identify the features that have higher impact on the accuracy of spam detection. Three different techniques are used and compared for this analysis: change of mean square error (CoM), information gain (IG) and Relief-F method. Top five features identified by each technique are used again to build the detection models. Experimental results show that most of the developed classifiers obtained high evaluation results based on the comprehensive data set constructed in this work. Experiments also reveal the important role of some features like the reputation of the account, average length of the tweet, average mention per tweet, age of the account, and the average time between posts in the process of identifying spammers in the social network.
2 January 2023 in IEEE Access
The problem of finding the shortest path between two nodes is a common problem that requires a solution in many applications like games, robotics, and real-life problems. Since its deals with a large number of possibilities. Therefore, parallel algorithms are suitable to solve this optimization problem that has attracted a lot of researchers from both industry and academia to find the optimal path in terms of runtime, speedup, efficiency, and cost compared to sequential algorithms. In mountain climbing, finding the shortest path from the start node under the mountain to reach the destination node is a fundamental operator, and there are some interesting issues to be studied in mountain climbing that cannot be found in a traditional two-dimensional space search. We present a parallel Ant Colony Optimization (ACO) to find the shortest path in the mountain climbing problem using Apache Spark. The proposed algorithm guarantees the security of the selected path by applying some constraints that take into account the secure slop angle for the path. A generated dataset with variable sizes is used to evaluate the proposed algorithm in terms of runtime, speedup, efficiency, and cost. The experimental results show that the parallel ACO algorithm significantly ( p < 0.05) outperformed the best sequential ACO. On the other hand, parallel ACO algorithm compared with one of the most recent research from the literature for finding the best path for mountain climbing problems using parallel A* algorithm with Apache Spark. The parallel ACO algorithm with Spark significantly outperformed the parallel A* algorithm.
30 May 2019 in International Journal of Emerging Technologies in Learning (iJET)
Cloud computing is one of the paradigms that have undertaken to deliver the utility computing concept. It views computing as a utility similar to water and electricity. We aim in this paper to make an investigation of two highly efficacious Cloud platforms: Microsoft Azure (Azure) and Amazon Web Services (AWS) from users’ perspectives the point of view of users. We highlight and compare in depth the features of Azure and AWS from users’ perspectives. The features which we shall focus on include (1) Pricing, (2) Availability, (3) Confidentiality, (4) Secrecy, (5) Tier Account and (6) Service Level Agreement (SLA). The study shows that Azure is more appropriate when considering Pricing and Availability (Error Rate) while AWS is more appropriate when considering Tier account. Our user survey study and its statistical analysis agreed with the arguments made for each of the six comparisons factors.
6 September 2013 in International Journal of Engineering & Technology
This paper presents the development of a new mobile phone dialler application which is designed to help blind and visually impaired people make phone calls. The new mobile phone dialler application is developed as a windows phone application to facilitate entering information to touch screen mobile phones by blind people. This application is advantageous through its innovative concept, its simplicity and its availability at an affordable cost. Feedback from users showed that this new application is easy to use and solves many problems of voice recognition applications such as inaccuracy, slowness and interpretation of unusual voices. In addition, this application has increased the users’ ability to dial phone numbers more independently and less stressfully.
1 January 2017 in Procedia Computer Science