Non-functional requirements define the quality attribute of a software application, which are necessary to identify in the early stage of software development life cycle. Researchers proposed automatic software Non-functional requirement classification using several Machine Learning (ML) algorithms with a combination of various vectorization techniques. However, using the best combination in Non-functional requirement classification still needs to be clarified. In this paper, we examined whether different combinations of feature extraction techniques and ML algorithms varied in the non-functional requirements classification performance. We also reported the best approach for classifying Non-functional requirements. We conducted the comparative analysis on a publicly available PROMISE_exp dataset containing labelled functional and Non-functional requirements. Initially, we normalized the textual requirements from the dataset; then extracted features through Bag of Words (BoW), Term Frequency and Inverse Document Frequency (TF-IDF), Hashing and Chi-Squared vectorization methods. Finally, we executed the 15 most popular ML algorithms to classify the requirements. The novelty of this work is the empirical analysis to find out the best combination of ML classifier with appropriate vectorization technique, which helps developers to detect Non-functional requirements early and take precise steps. We found that the linear support vector classifier and TF-IDF combination outperform any combinations with an F1-score of 81.5%.

Performance testing of e-commerce site is important for upcoming improvement and making better user experience which is performed by several web performance testing tools available on online platform. There are several tools user can use to scan their site for performance testing. This paper presents a web based application to collect and compare performance parameters with results automatically by applying WebpageTest, PageSpeed Insights and GTmetrix tools. For doing the test comparison nine parameters are considered and these are Load Time, First Byte, Start Render, First Contentful Paint, Speed Index, Largest Contentful Paint, Cumulative Layout Shift, Total Blocking Time and Time to Interactive parameters. The framework is developed with PHP, MySQL, CSS and HTML, where user will provide intended site’s url to test performance. This paper presents the performance of ten e-commerce sites of Bangladesh. Among the three tools WebpageTest and Gtmetrix can collect the reports of all the parameters. 1.62 (site7), 3.25 (site4) and 1.89 (site7) seconds are reported as lowest value for tools WebPageTest, PageSpeed Insight and Gtmetrix respectively. The average results of three tools is measured where, the minimum value is shown as 0.03 seconds for ‘total blocking time’ by site7. And maximum value is shown as 17.78 seconds for ‘load time’ parameter recorded by site10.

Social media has become incredibly popular these days for communicating with friends and for sharing opinions. According to current statistics, almost 2.22 billion people use social media in 2016, which is roughly one third of the world population and three times of the entire population in Europe. In social media people share their likes, dislikes, opinions, interests, etc. so it is possible to know about a person’s thoughts about a specific topic from the shared data in social media. Since, twitter is one of the most popular social media in the world; it is a very good source for opinion mining and sentiment analysis about different topics. In this research, SVM with different kernel functions and Adaboost are experimented using CPD and Chi-square feature extraction techniques to explore the best sentiment classification model. The reported average accuracy of Adaboost for Chi-square and CPD are 70.2% and 66.9%. The SVM radial basis kernel and polynomial kernel with Chi-square n-grams reported average accuracy of 73.73% and 68.67% respectively. Among the performed experimentation, SVM sigmoid kernel with Chi-square n-grams provided the maximum accuracy that is 74.4%.

The users of e-commerce sites are growing rapidly day by day for easy internet access where the performance of web applications plays a key role to satisfy the end-users. The performance of these websites or web applications depends on several parameters such as load time, fully loaded (time), fully loaded (requests), etc. This research tries to investigate and find out the parameters that affects the web performance and it has been tested on e-commerce applications of Bangladesh, where eleven parameters are considered and these are fully loaded (requests), first CPU idle, speed index, start render, load time, fully loaded (time), document complete (time), last painted hero, first contentful paint, and first byte. According to the analysis some applications need to take care of or the developers need to re-modify it. As per the investigation of scanned information, the applications fall under three classes. To start with, the applications do not demonstrate acceptable records to be investigated. The second and third classification applications required medium and high reaction times at the user end separately. Also, the fully loaded (requests)’ and document complete (requests) show the most noteworthy required time at the user end, where maximum values are 347 and 344 seconds individually.