Search

Online news blogs and websites are becoming influential to any society as they accumulate the world in one place. Aside from that, online news blogs and websites have efficient strategies in grabbing readers’ attention by the headlines, that being so to recognize the sentiment orientation or polarity of the news headlines for avoiding misinterpretation against any fact. In this study, we have examined 3383 news headlines created by five different global newspapers. In the interest of distinguishing the sentiment polarity (or sentiment orientation) of news headlines, we have trained our model by seven machine learning and two deep learning algorithms. Finally, their performance was compared. Among them, Bernoulli naïve Bayes and Convolutional Neural Network (CNN) achieved higher accuracy than other machine learning and deep learning algorithms, respectively. Such a study will help the audience in determining their impression against or for any leader or governance; and will provide assistance to recognize the most indifferent newspaper or news blogs.

In the field of information security, phishing URLs detection and prevention has recently become egregious. For detecting, phishing attacks several anti-phishing systems have already been proposed by researchers. The performance of those systems can be affected due to the lack of proper selection of machine learning classifiers along with the types of feature sets. A details investigation on machine learning classifiers (KNN, DT, SVM, RF, ERT and GBT) along with three publicly available datasets with multidimensional feature sets have been presented on this paper. The performance of the classifiers has been evaluated by confusion matrix, precision, recall, F1-score, accuracy and misclassification rate. The best output obtained from Random Forest and Extremely Randomized Tree with dataset one and three (binary class feature set) of 97% and 98% accuracy accordingly. In multiclass feature set (dataset two), Gradient Boosting Tree provides highest performance with 92% accuracy.

Stock price forecasting, is one of the most significant financial complexities, since data are not reliable and noisy, impacting many factors. This article offers a machine learning model for the stock price prediction using Support Vector Machine-Regression (SVR) with two different kernels which are Radial Basis Function (RBF) and linear kernel. This study shows the Prediction and accuracy comparison between Support Vector Regression (SVR) and Linear Regression (LR) and also the accuracy comparison for different kernels of Support vector Regression (SVR). The model has used sum squared error (SSE) to determine the accuracy of each algorithm; which has shown significant improvement than the other studies. This analysis is conducted on the price data of about five years of Grameenphone listed on Dhaka Stock Exchange (DSE). The highest accuracy was found with Linear Regression model in every case with the highest accuracy of about 97.07% followed by SVR (Linear) model and SVR (radial basis function) model with the highest accuracy rate of about 97.06% and 96.82%. In some cases the accuracy of SVR (radial basis function) was higher than SVR (linear). But it was the Linear Regression which had the highest accuracy of all in every case.

Analyzing short text or documents using topic modeling becomes a popular solutions for the increasing number of documents produced in everyday life. For handling the large amount of documents, many topic modeling algorithms are used e.g. LDA, LSI, pLSI, NMF. In this study, we have used LDA, LSI, NMF and also lexical database wordNet synset for candidate labels in our topics labeling. And finally compare the effectiveness of topic modeling algorithms for short documents. Among those LDA gives the better result in terms of WUP similarity. This study will help to select the proper algorithm for labeling topics and can easily identify the meaning of topics.

Cloud computing provides data storage and computing power based on user demand by assigning tasks to virtual resources. To deliver overall improved performance and meet challenges such as availability, resource utilization and reliability in the cloud, appropriate resource scheduling methods are needed. A number of metaheuristic optimization algorithms are used to solve the problem of resource scheduling. This work lists challenges and analyzes previous scheduling methods based on Genetic Algorithm (GA). It classifies the GA-based scheduling methods with respect to many parameters. At last, it presents the scopes of enhancement for future researchers.

Requirements re-usability in a distributed software development project is applied to increase system productivity, reliability, quality, decreasing system development sprint and maintaining consistency between two identical systems, which later help to reduce both project time and cost. Nowadays, most of the projects are driven by market so that the intention of this research is to identify the challenges faced by practitioners in requirements re-usability in distributed large-scale agile projects and to find out how practitioners apply the concept of re-usability to mitigating those challenges in distributed large-scale agile software development from requirement engineering or re-usability perspective. In this study, a survey is used to identify requirement re-usability challenges and mitigation approach from practitioners. From a series of semi-structured interview, we have identified 14 challenges and 10 mitigation approaches into three categories, such as communication, coordination, and control from the global software engineering perspective. The findings from this research will help industry people to make a decision in their industry oriented activities.

Nowadays, a startup is being very popular and entrepreneurs are increasing day by day. Though we are watching many successful startups e.g. Dropbox, Amazon, Viber and so on, the list of unsuccessful startups is very long. Who is being successful they must have their own strategy, which they apply in their startup and get success. In lean startup strategy, the customers give feedbacks about the startup and the owner understands the demand of customers by collecting feedback from customers and provides service according to the feedback. On the other hand, all the feedbacks from the customers are not important for a startup project. So it is needed to separate or prioritize feedbacks which are needed to execute the startup project. But there are not sufficient techniques for prioritizing the feedbacks collected from customers. By conducting a systematic mapping study and a case study (interview and observation is used), we propose a technique which will be used to prioritize customer feedback in lean startup. This technique will be helpful for the startup projects to become successful.

Topics generated by topic models are typically reproduced as a list of words. To decrease the cognitional overhead of understanding these topics for end-users, we have proposed labeling topics with a noun phrase that summarizes its theme or idea. Using the WordNet lexical database as candidate labels, we estimate natural labeling for documents with words to select the most relevant labels for topics. Compared to WUP similarity topic labeling system, our methodology is simpler, more effective, and obtains better topic labels.

The most widely recognized relative directions are left, right, forward and backward. This paper has presented a computational technique for tracking location by learning relative directions between two intelligent agents, where two agents communicate with each other by radio signal and one intelligent agent helps another intelligent agent to find location. This proposed method represents an alternative approach to GSM (Global System for Mobile Communications) for the AI (Artificial Intelligence), where no network may not be available. Our research paper has proposed Relative Direction Based Location Tracking (RDBLT) model for understanding how one intelligent agent assists another intelligent agent to find out the location by learning and identifying relative directions. Moreover, three proficient algorithms have been developed for constructing our proposed model.