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.

Web service is a software application, which is accessible using platform independent and language neutral web protocols. However, selecting the most relevant services became one of the vital challenges. Quality of services plays very important role in web service selection, as it determines the quality and usability of a service, including its non-functional properties such as scalability, accessibility, integrity, efficiency, etc. When agent application send request with a set of quality attributes, it becomes challenging to find out the best service for satisfying maximum quality requirements. Among the existing approaches, the single value decomposition technique is popular one; however, it suffers for computational complexity. To overcome this limitation, this paper proposed a subset matching based web service selection and ranking by considering the quality of service attributes. This proposed method creates a quality-web matrix to store available web services and associated quality of service attributes. Then, matrix subsets are created using web service repository and requested quality attributes. Finally, web services are efficiently selected and ranked based on calculated weights of corresponding web services to reduce composition time. Experimental results showed that proposed method performs more efficient and scalable than existing several techniques such as single value decomposition.