MD ABUL BASHAR

Queensland University of Technology, Electrical Engineering and Computer Science, Post-Doc

Followers

117

Following

185

Public Views

I am a Research Associate at Queensland University of Technology (QUT), Brisbane, Australia. My research area is Knowledge Discovery and Data Mining. I got my PhD from the same university. I am also a lecturer (on study leave) at Comilla University, Bangladesh. Previously I was a Software Engineer at Structured Data System Limited, Dhaka, Bangladesh. I completed my Bachelor of Science (Engg.) in Computer Science and Engineering from Shah Jalal University of Science and Technology, Bangladesh. I like to share ideas with people.
Supervisors: Professor Yuefeng Li and Dr Richi Nayak
Address: Brisbane, Queensland, Australia

less

Related Authors

IIT Bombay

University of Ibadan Nigeria

University of Regina

University of Trento

Universität Passau

Universität Passau

Computer Science & Information Technology (CS & IT) Computer Science Conference Proceedings (CSCP)

Interests

Uploads

Papers by MD ABUL BASHAR

Misogynistic Tweet Detection: Modelling CNN with Small Datasets

Data Mining, 2019

Online abuse directed towards women on the social media platform such as Twitter has attracted co... more Online abuse directed towards women on the social media platform such as Twitter has attracted considerable attention in recent years. An automated method to effectively identify misogynistic abuse could improve our understanding of the patterns, driving factors, and effectiveness of responses associated with abusive tweets over a sustained time period. However, training a neural network (NN) model with a small set of labelled data to detect misogynistic tweets is difficult. This is partly due to the complex nature of tweets which contain misogynistic content, and the vast number of parameters needed to be learned in a NN model. We have conducted a series of experiments to investigate how to train a NN model to detect misogynistic tweets effectively. In particular, we have customised and regularised a Convolutional Neural Network (CNN) architecture and shown that the word vectors pre-trained on a task-specific domain can be used to train a CNN model effectively when a small set of labelled data is available. A CNN model trained in this way yields an improved accuracy over the state-of-the-art models.

DownloadEdit

A Role based Address Cleaner

International Journal ofInformation Sciences and Computer Engineering, 2010

About 80% to 90% of governmental and business data collections contain address information. In ma... more About 80% to 90% of governmental and business data collections contain address information. In many cases, address records are captured and/or stored in a free-form or inconsistent manner. There are many causes to dirty data: misuse of abbreviations, data entry mistakes, control information hiding, missing fields, spelling, outdated codes etc. Due to the 'garbage in, garbage out' principle, dirty data will distort information obtained from it. The purpose of address cleaning is to maximize the value of address data and ensure that every address is spelt correctly and properly structured. This improves accuracy and standardization in mailing, boosts company image , reduces mailing costs, and through geocoding opens up a number of opportunities to support strategic decisions through accurate spatial analysis. We report the implementation of a role based address cleaner. In this address cleaner we define indicators and grammars for address cleaning and thus make the cleaning process configurable.

DownloadEdit

Regularising LSTM Classifier by Transfer Learning for Detecting Misogynistic Tweets with Small Training Set

Springer Nature, 2020

Supervised machine learning methods depend highly on the quality of the training dataset and the ... more Supervised machine learning methods depend highly on the quality of the training dataset and the underlying model. In particular, neural network (NN) models, that have shown great success in dealing with natural language problems, require a large dataset to learn a vast number of parameters. However, it is not always easy to build a large (labelled) dataset. For example, due to the complex nature of tweets and the manual labour involved, it is hard to create a large Twitter data set with the misogynistic label. In this paper, we propose to regularise a Long Short-Term Memory (LSTM) classifier using a pretrained LSTM-based Language Model (LM) to build an accurate classification model with a small training set. We explain transfer learning (TL) with a Bayesian interpretation and show that TL can be viewed as an uncertainty regularisation technique in Bayesian inference. We show that a LM pre-trained on a sequence of general to task-specific domain datasets can be used to regularise a LSTM classifier effectively when a small training dataset is available. Empirical analysis with two small Twitter datasets reveals that an LSTM model trained in this way can outperform the state-of-the-art classification models.

DownloadEdit

A Framework for Automatic Personalised Ontology Learning

—Understanding or acquiring a user's information needs from their local information repository (e... more —Understanding or acquiring a user's information needs from their local information repository (e.g. a set of example-documents that are relevant to user information needs) is important in many applications. However, acquiring the user's information needs from the local information repository is very challenging. Personalised ontology is emerging as a powerful tool to acquire the information needs of users. However, its manual or semi-automatic construction is expensive and time-consuming. To address this problem, this paper proposes a model to automatically learn personalised ontology by labelling topic models with concepts, where the topic models are discovered from a user's local information repository. The proposed model is evaluated by comparing against ten baseline models on the standard dataset RCV1 and a large ontology LCSH. The results show that the model is effective and its performance is significantly improved.

DownloadEdit

Interpreting Discovered Patterns in terms of Ontology Concepts

Semantic Web offers many possibilities for future Web technologies. Therefore, it is a need to se... more Semantic Web offers many possibilities for future Web technologies. Therefore, it is a need to search for ways that can bring the huge amount of unstructured documents from current Web to Semantic Web automatically. One big challenge in searching for such ways is how to understand patterns by both humans and machine. To address this issue, we present an innovative model which interprets patterns to high level concepts. These concepts can explain the patterns' meanings in a human understandable way while improving the information filtering performance. The model is evaluated by comparing it against one state-of-the-art benchmark model using standard Reuters dataset. The results show that the proposed model is successful. The significance of this model is three fold. It gives a way to interpret text mining output, provides a technique to find concepts relevant to the whole set of patterns which is an essential feature to understand the topic, and to some extent overcomes information mismatch and overload problems of existing models. This model will be very useful for knowledge based applications.

DownloadEdit

MD ABUL BASHAR

Uploads

Papers by MD ABUL BASHAR

Log In