Moqsadur Rahman

Bio: Moqsadur Rahman is an academic researcher from Shahjalal University of Science and Technology. The author has contributed to research in topics: Artificial intelligence & Stop words. The author has an hindex of 2, co-authored 6 publications receiving 11 citations.

Identifying and Categorizing Opinions Expressed in Bangla Sentences using Deep Learning Technique

Abstract: Identifying and categorizing opinions in a sentence is the most prominent branch of natural language processing. It deals with the text classification to determine the intention of the author of the text. The intention can be for the presentation of happiness, sadness, patriotism, disgust, advice, etc. Most of the research work on opinion or sentiment analysis is in the English language. Bengali corpus is increasing day by day. A large number of online News portals publish their articles in Bengali language and a few News portals have the comment section that allows expressing the opinion of people. Here a research work has been done on Bengali Sports news comments published in different newspapers to train a deep learning model that will be able to categorize a comment according to its sentiment. Comments are collected and separated based on immanent sentiment. The deep learning algorithms that have been used are Convolutional Neural Network (CNN), Multilayer Perceptron, Long Short-Term Memory (LSTM). General Terms Sentiment Analysis, Deep Learning, Emotion Classification

Observing the Unobserved: A Newspaper Based Dengue Surveillance System for the Low-Income Regions of Bangladesh.

Abstract: Dengue is one of the emerging diseases of this century, which established itself as both endemic and epidemic - particularly in the tropical and subtropical-regions. Because of its high morbidity and mortality rates, Dengue is a significant economic and health burden for middle to lower-income countries. The lack of a stable, cost-effective, and suitable surveillance system has made the identification of dengue zones and designing potential control programs very challenging. As a result, it is not feasible to assess the effect of the intervention actions properly. Therefore, most of the prevention and mitigation efforts by the associated health officials are failing. In this work, we chose Bangladesh, a developing country from the South-East Asia region with its occasional history of dengue outbreaks and with a high out-of-pocket medical expenditure, as a use case. We use some well known data-mining techniques on the local newspapers, written in Bengali, to unearth valuable insights and develop a dengue news surveillance system. We categorize dengue-news and detect the spatio-temporal trends among crucial variables. Our technique provides an f-score of 91.45\% and very closely follows the ground truth of reported cases. Additionally, we identify the under-reported regions of the country effectively while establishing a meaningful relationship between complex socio-economic factors and reporting of dengue.

Bengali Stop Word Detection Using Different Machine Learning Algorithms

Abstract: Bangla language is an enriched language and many words are used frequently for the sentence formation purpose holding negligible information value. These words are stop words, widely used in the field of text mining, information retrieval, text summarizer, indexing, search and retrieval systems, Bangla Language Processing (BLP), etc. For the better performance of the system, stop words should be eliminated properly, as it can decrease the calculation speed, take lots of space, and deteriorate the system performance. But there is no standard stop word detection approach without using a pre-defined stop word list. But the main disadvantage is, it cannot detect stop word which is used as a content word in the text sometimes as the word is not analyzed contextwise. So, a new method is proposed to detect stop word from sentences without using a pre-defined stop word list by creating a dictionary for the conversion of words to numeric values, where each 61 available Bengali character is assigned with a distinct numerical value, also words are checked according to the stored index position and highest accuracy 89% is achieved by applying random forest classifiers. The proposed approach is the first attempt for this task in the Bengali language.

Classifications of Skull Fractures using CT Scan Images via CNN with Lazy Learning Approach

Abstract: Department of Computer Science and Engineering, Sylhet Engineering College, School of Applied Sciences and Technology, Shahjalal University of Science and Technology, Sylhet, Bangladesh Department of Computer Science and Engineering, School of Applied Sciences and Technology, Shahjalal University of Science and Technology, Sylhet, Bangladesh Department of Computer Science and Engineering, Shahjalal University of Science and Technology, Sylhet, Bangladesh

Predicting skull fractures via CNN with classification algorithms

Abstract: Computer Tomography (CT) images have become quite important to diagnose diseases. CT scan slice contains a vast amount of data that may not be properly examined with the requisite precision and speed using normal visual inspection. A computer-assisted skull fracture classification expert system is needed to assist physicians. Convolutional Neural Networks (CNNs) are the most extensively used deep learning models for image categorization since most often time they outperform other models in terms of accuracy and results. The CNN models were then developed and tested, and several convolutional neural network (CNN) architectures were compared. ResNet50, which was used for feature extraction combined with a gradient boosted decision tree machine learning algorithm to act as a classifier for the categorization of skull fractures from brain CT scans into three fracture categories, had the best overall F1-score of 96%, Hamming Score of 95%, Balanced accuracy Score of 94% & ROC AUC curve of 96% for the classification of skull fractures.

Sentiment Analysis and Product Review Classification in E-commerce Platform

Abstract: Online shopping is becoming one of the most de-manding everyday needs, nowadays. These days people are feeling comfortable shopping online. The number of its customers is increasing day by day as well as raising some problems. The major problem is that the customers can not choose the quality-full product by reading every review of an online product. Besides, the product reviews are helpful to improve the services of an e-commerce site but required huge manpower and time. We have focused on Bangla text and aimed to solve these problems by the application of Deep Neural Network (DNN) and Natural Language Processing (NLP). In this study, we have proposed two deep learning NLP models: one is for sentiment analysis and the other one is for Product Review Classification intended to improve both the quality and services. Significantly, our proposed models result in high accuracy: 0.84 and 0.69 for both Sentiment Analysis and Product Review Classification, respectively. Undoubtedly, these models can help the customers to choose the right product and the service provider to improve their services.

Bangla Document Classification using Character Level Deep Learning

Abstract: Last few decades, the availability and accessibility of the Bangla document and its content have rapidly increased due to the rapid technological advancement. Intense research needs to be performed on various Bangla documents due to the diversity of the language and associated sentiment. Document classification is one of the fundamental problems of Natural Language Processing. To handle miss-classification and convenient indexing and searching of Bangla documents on the web, researchers nowadays exploring different fields of computer science to classify Bangla documents. In this paper, Deep Learning based approaches are implemented to classify Bangla text documents. Convolutional Neural Network (CNN) and Long Short Term Memory (LSTM) is used here for the classification task. Here we have implemented an advanced technique that encoded the documents at their character level. Documents from three different data sources are used to validate and test of the working models. The highest classification accuracy is 95.42% that is achieved on the Prothom Alo data set using LSTM. Furthermore, we presented a comparison between two models and explained how well the classification task can be carried out using our character level approach with higher accuracy.

Sentiment Analysis of Bangla Language Using Deep Learning Approaches

Abstract: Emotion is the most important gear for human textual communication with each other via social media. Nowadays, people use text for reviewing or recommending things, sharing opinions, rating their choices or unlikeness, providing feedback for different services, and so on. Bangladeshi people use Bangla to express their emotions. Current research based on sentiment analysis has got low-performance output by using several approaches on detecting sentiment polarity and emotion from Bangla texts. In this study, we have developed four models with the hybrid of Convolutional Neural Network (CNN) and Long Short Term Memory (LSTM) with various Word Embeddings including Embedding Layer, Word2Vec, Global Vectors (Glove), and Continuous Bag of Words (CBOW) to detect emotion from Bangla texts (words, sentences). Our models can define the basic three emotions; happiness, anger, and sadness. It will make interaction lively and interesting. Our comparisons are bestowed against CNN, LSTM with different Word Embeddings, and also against some previous researches with the same dataset based on classical Machine Learning techniques such as Support Vector Machine (SVM), Naive Bayes, and K-Nearest Neighbors (K-NN). In our proposed study, we have used Facebook Bangla comments for a suitable dataset. In our study, we have tried to detect the exact emotion from the text. And in result, the best model integrating Word2Vec embedding layer with a hybrid of CNN-LSTM detected emotions from raw textual data with an accuracy of 90.49% and F1 score of 92.83%.

Text Classification Using Convolution Neural Networks with FastText Embedding

Abstract: Text classification has a growing interest among NLP researchers due to its tremendous availability on online platforms and emergence on various Web 2.0 applications. Recently, text classification in resource-constrained languages has been bringing much attention due to the sharp increase of digital resources. This paper presents a CNN based text classification model for one of the low resource languages like Bengali. The goal of the Bengali text classification is to assign a particular category to a text into one of the pre-defined categories based on its semantic and syntactic meaning. The proposed system comprises of four key modules: embedding model generation, Text to feature representation, training, and testing. The classification system trained and validated with 39, 079 and 6, 000 text datasets. Experimental evaluation with 9, 779 test datasets shows the accuracy of \(96.85\%\), which indicates the superior performance compared to the existing techniques.

Using Machine Learning to Detect Events on the Basis of Bengali and Banglish Facebook Posts

Abstract: In modern times, ensuring social security has become the prime concern for security administrators. The widespread and recurrent use of social media sites is creating a huge risk for the lives of the general people, as these sites are frequently becoming potential sources of the organization of various types of immoral events. For protecting society from these dangers, a prior detection system which can effectively detect events by analyzing these social media data is essential. However, automating the process of event detection has been difficult, as existing processes must account for diverse writing styles, languages, dialects, post lengths, and et cetera. To overcome these difficulties, we developed an effective model for detecting events, which, for our purposes, were classified as either protesting, celebrating, religious, or neutral, using Bengali and Banglish Facebook posts. At first, the collected posts’ text were processed for language detection, and then, detected posts were pre-processed using stopwords removal and tokenization. Features were then extracted from these pre-processed texts using three sub-processes: filtering, phrase matching of specific events, and sentiment analysis. The collected features were ultimately used to train our Bernoulli Naive Bayes classification model, which was capable of detecting events with 90.41% accuracy (for Bengali-language posts) and 70% (for the Banglish-form posts). For evaluating the effectiveness of our proposed model more precisely, we compared it with two other classifiers: Support Vector Machine and Decision Tree.