Toxic comments on social media platforms, news portals, and online forums are impolite, insulting, or unreasonable that usually make other users leave a conversation. Due to the significant number of comments, it is impractical to moderate them manually. Therefore, online service providers use the automatic detection of toxicity using Machine Learning (ML) algorithms. However, the model's toxicity identification performance relies on the best combination of classifier and feature extraction techniques. In this empirical study, we set up a comparison environment for toxic comment classification using 15 frequently used supervised ML classifiers with the four most prominent feature extraction schemes. We considered the publicly available Jigsaw dataset on toxic comments written by human users. We tested, analyzed and compared with every pair of investigated classifiers and finally reported a conclusion. We used the accuracy and area under the ROC curve as the evaluation metrics. We revealed that Logistic Regression and AdaBoost are the best toxic comment classifiers. The average accuracy of Logistic Regression and AdaBoost is 0.895 and 0.893, respectively, where both achieved the same area under the ROC curve score (i.e., 0.828). Therefore, the primary takeaway of this study is that the Logistic Regression and Adaboost leveraging BoW, TF-IDF, or Hashing features can perform sufficiently for toxic comment classification.

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.

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.

For the betterment of teaching methodology student’s evaluation is an integral part of any educational organization. To achieve this process the authority needs to know how the teachers are teaching and therefore the interaction between the learners and therefore educators. This paper develops an android based automated tool for performance evaluation of a course teacher (CTE) which is able to create an educator’s performance report from the student’s evaluation based on some predefined questionnaire by using an android mobile device with internet connectivity from anywhere and anytime. The performance report is auto generated together with a graph and it also creates a file to send the teacher if the authority wants to inform the educator. With the assistance of this technique, course teachers can easily understand their current situation of their corresponding courses where they should focus on.

For any educational institution course or teacher evaluation is an integral part for the betterment and effective education system. Student’s feedback could be taken as one of parts of teacher evaluation. This paper has tried to evaluate the effectiveness of the course teacher evaluation system from the students’ feedback of their corresponding courses. At Stamford University Bangladesh currently the teacher’s evaluation task is running by manually which is very time consuming, slow and a lengthy process. It also needs number of human resources for completing this task. This paper has presented a web based automated tool for Course Teacher Evaluation System (TTE). In this technique student’s opinions are taken from some predefined questions in a web based platform for evaluating a teacher of any particular course. And the result from the data analysis is automatically generated along with a graphical representation. From the generated report it becomes very easy for the teacher to understand and focus on the area where they need to emphasize for their personal and professional growth. As the results are generated automatically from the survey it saves time as well as man power.

Water automation is all about controlling, monitoring and even billing of water usage in different places like hotel, house, irrigation land and industry. The researchers done water automation based on different purposes using different types of hardware and technologies. This paper develops Automated Water Management System (WMS) which can monitor water tank by measuring the water flow, water level, water temperature, cut ON/OFF water supply and send notifications to the user through mobile messaging. All of the things are connected through an android application that is much more efficient and easier to control the whole process.