Md. Abdur Rahman

Work place: Centre for Advanced Research in Sciences, University of Dhaka, Dhaka, Bangladesh



Research Interests: Data Structures and Algorithms, Natural Language Processing, Computational Learning Theory, Software Engineering, Computational Science and Engineering


Md. Abdur Rahman received his BSc in Information Technology from Visva Bharati University, India in 2004. He has completed his Post Graduate Diploma and Master in Information Technology from University of Dhaka, Bangladesh, in 2008 and 2009 respectively. He is a Senior Computer Scientist in the Centre for Advanced Research in Sciences at the University of Dhaka. His major research interest includes natural language processing, machine learning, deep learning, big data analytics and software engineering. He has published a number of research papers in various international journals and conferences.

Author Articles
How do Machine Learning Algorithms Effectively Classify Toxic Comments? An Empirical Analysis

By Md. Abdur Rahman Abu Nayem Mahfida Amjad Md. Saeed Siddik

DOI:, Pub. Date: 8 Aug. 2023

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.

[...] Read more.
Subset Matching based Selection and Ranking (SMSR) of Web Services

By Md. Abdur Rahman Md. Belal Hossain Md. Sharifur Rahman Saeed Siddik

DOI:, Pub. Date: 8 Apr. 2019

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.

[...] Read more.
Other Articles