arXiv subjects

Md. Saiful Islam

Publications and source records attributed to Md. Saiful Islam.

At least 37 records · Page 2Linked to original sources

arXiv2021

A transformer based approach for fighting COVID-19 fake news

The rapid outbreak of COVID-19 has caused humanity to come to a stand-still and brought with it a plethora of other problems. COVID-19 is the first pandemic in history when humanity is the most technologically advanced and relies heavily on social media platforms for connectivity and other benefits. Unfortunately, fake news and misinformation regarding this virus is also available to people and causing some massive problems. So, fighting this infodemic has become a significant challenge. We present our solution for the "Constraint@AAAI2021 - COVID19 Fake News Detection in English" challenge in this work. After extensive experimentation with numerous architectures and techniques, we use eight different transformer-based pre-trained models with additional layers to construct a stacking ensemble classifier and fine-tuned them for our purpose. We achieved 0.979906542 accuracy, 0.979913119 precision, 0.979906542 recall, and 0.979907901 f1-score on the test dataset of the competition.

cs.CL↗

arXiv2020

Detecting Parkinson's Disease From an Online Speech-task

In this paper, we envision a web-based framework that can help anyone, anywhere around the world record a short speech task, and analyze the recorded data to screen for Parkinson's disease (PD). We collected data from 726 unique participants (262 PD, 38% female; 464 non-PD, 65% female; average age: 61) -- from all over the US and beyond. A small portion of the data was collected in a lab setting to compare quality. The participants were instructed to utter a popular pangram containing all the letters in the English alphabet "the quick brown fox jumps over the lazy dog..". We extracted both standard acoustic features (Mel Frequency Cepstral Coefficients (MFCC), jitter and shimmer variants) and deep learning based features from the speech data. Using these features, we trained several machine learning algorithms. We achieved 0.75 AUC (Area Under The Curve) performance on determining presence of self-reported Parkinson's disease by modeling the standard acoustic features through the XGBoost -- a gradient-boosted decision tree model. Further analysis reveal that the widely used MFCC features and a subset of previously validated dysphonia features designed for detecting Parkinson's from verbal phonation task (pronouncing 'ahh') contains the most distinct information. Our model performed equally well on data collected in controlled lab environment as well as 'in the wild' across different gender and age groups. Using this tool, we can collect data from almost anyone anywhere with a video/audio enabled device, contributing to equity and access in neurological care.

eess.AS↗

arXiv2020

Sentiment analysis in Bengali via transfer learning using multi-lingual BERT

Sentiment analysis (SA) in Bengali is challenging due to this Indo-Aryan language's highly inflected properties with more than 160 different inflected forms for verbs and 36 different forms for noun and 24 different forms for pronouns. The lack of standard labeled datasets in the Bengali domain makes the task of SA even harder. In this paper, we present manually tagged 2-class and 3-class SA datasets in Bengali. We also demonstrate that the multi-lingual BERT model with relevant extensions can be trained via the approach of transfer learning over those novel datasets to improve the state-of-the-art performance in sentiment classification tasks. This deep learning model achieves an accuracy of 71\% for 2-class sentiment classification compared to the current state-of-the-art accuracy of 68\%. We also present the very first Bengali SA classifier for the 3-class manually tagged dataset, and our proposed model achieves an accuracy of 60\%. We further use this model to analyze the sentiment of public comments in the online daily newspaper. Our analysis shows that people post negative comments for political or sports news more often, while the religious article comments represent positive sentiment. The dataset and code is publicly available at https://github.com/KhondokerIslam/Bengali\_Sentiment.

cs.CL↗

arXiv2020

A Continuous Space Neural Language Model for Bengali Language

Language models are generally employed to estimate the probability distribution of various linguistic units, making them one of the fundamental parts of natural language processing. Applications of language models include a wide spectrum of tasks such as text summarization, translation and classification. For a low resource language like Bengali, the research in this area so far can be considered to be narrow at the very least, with some traditional count based models being proposed. This paper attempts to address the issue and proposes a continuous-space neural language model, or more specifically an ASGD weight dropped LSTM language model, along with techniques to efficiently train it for Bengali Language. The performance analysis with some currently existing count based models illustrated in this paper also shows that the proposed architecture outperforms its counterparts by achieving an inference perplexity as low as 51.2 on the held out data set for Bengali.

cs.CL↗

arXiv2020

Authorship Attribution in Bangla literature using Character-level CNN

Characters are the smallest unit of text that can extract stylometric signals to determine the author of a text. In this paper, we investigate the effectiveness of character-level signals in Authorship Attribution of Bangla Literature and show that the results are promising but improvable. The time and memory efficiency of the proposed model is much higher than the word level counterparts but accuracy is 2-5% less than the best performing word-level models. Comparison of various word-based models is performed and shown that the proposed model performs increasingly better with larger datasets. We also analyze the effect of pre-training character embedding of diverse Bangla character set in authorship attribution. It is seen that the performance is improved by up to 10% on pre-training. We used 2 datasets from 6 to 14 authors, balancing them before training and compare the results.

cs.CL↗

arXiv2019

Keyword Aware Influential Community Search in Large Attributed Graphs

We introduce a novel keyword-aware influential community query KICQ that finds the most influential communities from an attributed graph, where an influential community is defined as a closely connected group of vertices having some dominance over other groups of vertices with the expertise (a set of keywords) matching with the query terms (words or phrases). We first design the KICQ that facilitates users to issue an influential CS query intuitively by using a set of query terms, and predicates (AND or OR). In this context, we propose a novel word-embedding based similarity model that enables semantic community search, which substantially alleviates the limitations of exact keyword based community search. Next, we propose a new influence measure for a community that considers both the cohesiveness and influence of the community and eliminates the need for specifying values of internal parameters of a network. Finally, we propose two efficient algorithms for searching influential communities in large attributed graphs. We present detailed experiments and a case study to demonstrate the effectiveness and efficiency of the proposed approaches.

cs.SI↗

arXiv2019

A Subword Level Language Model for Bangla Language

Language models are at the core of natural language processing. The ability to represent natural language gives rise to its applications in numerous NLP tasks including text classification, summarization, and translation. Research in this area is very limited in Bangla due to the scarcity of resources, except for some count-based models and very recent neural language models being proposed, which are all based on words and limited in practical tasks due to their high perplexity. This paper attempts to approach this issue of perplexity and proposes a subword level neural language model with the AWD-LSTM architecture and various other techniques suitable for training in Bangla language. The model is trained on a corpus of Bangla newspaper articles of an appreciable size consisting of more than 28.5 million word tokens. The performance comparison with various other models depicts the significant reduction in perplexity the proposed model provides, reaching as low as 39.84, in just 20 epochs.

cs.CL↗

arXiv2019

On Event Causality Detection in Tweets

Nowadays, Twitter has become a great source of user-generated information about events. Very often people report causal relationships between events in their tweets. Automatic detection of causality information in these events might play an important role in predictive event analytics. Existing approaches include both rule-based and data-driven supervised methods. However, it is challenging to correctly identify event causality using only linguistic rules due to the highly unstructured nature and grammatical incorrectness of social media short text such as tweets. Also, it is difficult to develop a data-driven supervised method for event causality detection in tweets due to insufficient contextual information. This paper proposes a novel event context word extension technique based on background knowledge. To demonstrate the effectiveness of our proposed event context word extension technique, we develop a feed-forward neural network based approach to detect event causality from tweets. Extensive experiments demonstrate the superiority of our approach.

cs.IR↗

arXiv2018

Real Time Bangladeshi Sign Language Detection using Faster R-CNN

Bangladeshi Sign Language (BdSL) is a commonly used medium of communication for the hearing-impaired people in Bangladesh. Developing a real time system to detect these signs from images is a great challenge. In this paper, we present a technique to detect BdSL from images that performs in real time. Our method uses Convolutional Neural Network based object detection technique to detect the presence of signs in the image region and to recognize its class. For this purpose, we adopted Faster Region-based Convolutional Network approach and developed a dataset $-$ BdSLImset $-$ to train our system. Previous research works in detecting BdSL generally depend on external devices while most of the other vision-based techniques do not perform efficiently in real time. Our approach, however, is free from such limitations and the experimental results demonstrate that the proposed method successfully identifies and recognizes Bangladeshi signs in real time.

cs.CV↗

arXiv2018

A Comprehensive Survey on Bengali Phoneme Recognition

Hidden Markov model based various phoneme recognition methods for Bengali language is reviewed. Automatic phoneme recognition for Bengali language using multilayer neural network is reviewed. Usefulness of multilayer neural network over single layer neural network is discussed. Bangla phonetic feature table construction and enhancement for Bengali speech recognition is also discussed. Comparison among these methods is discussed.

cs.SD↗

arXiv2018

Sentiment Analysis of Comments on Rohingya Movement with Support Vector Machine

The Rohingya Movement and Crisis caused a huge uproar in the political and economic state of Bangladesh. Refugee movement is a recurring event and a large amount of data in the form of opinions remains on social media such as Facebook, with very little analysis done on them.To analyse the comments based on all Rohingya related posts, we had to create and modify a classifier based on the Support Vector Machine algorithm. The code is implemented in python and uses scikit-learn library. A dataset on Rohingya analysis is not currently available so we had to use our own data set of 2500 positive and 2500 negative comments. We specifically used a support vector machine with linear kernel. A previous experiment was performed by us on the same dataset using the naive bayes algorithm, but that did not yield impressive results.

cs.IR↗

arXiv2017

A Policy Model and Framework for Context-Aware Access Control to Information Resources

In today's dynamic ICT environments, the ability to control users' access to resources becomes ever important. On the one hand, it should adapt to the users' changing needs; on the other hand, it should not be compromised. Therefore, it is essential to have a flexible access control model, incorporating dynamically changing context information. Towards this end, this paper introduces a policy framework for context-aware access control (CAAC) applications that extends the role-based access control model with both dynamic associations of user-role and role-permission capabilities. We first present a formal model of CAAC policies for our framework. Using this model, we then introduce an ontology-based approach and a software prototype for modelling and enforcing CAAC policies. In addition, we evaluate our policy ontology model and framework by considering (i) the completeness of the ontology concepts, specifying different context-aware user-role and role-permission assignment policies from the healthcare scenarios; (ii) the correctness and consistency of the ontology semantics, assessing the core and domain-specific ontologies through the healthcare case study; and (iii) the performance of the framework by means of response time. The evaluation results demonstrate the feasibility of our framework and quantify the performance overhead of achieving context-aware access control to information resources.

cs.CR↗

arXiv2017

No-But-Semantic-Match: Computing Semantically Matched XML Keyword Search Results

Users are rarely familiar with the content of a data source they are querying, and therefore cannot avoid using keywords that do not exist in the data source. Traditional systems may respond with an empty result, causing dissatisfaction, while the data source in effect holds semantically related content. In this paper we study this no-but-semantic-match problem on XML keyword search and propose a solution which enables us to present the top-k semantically related results to the user. Our solution involves two steps: (a) extracting semantically related candidate queries from the original query and (b) processing candidate queries and retrieving the top-k semantically related results. Candidate queries are generated by replacement of non-mapped keywords with candidate keywords obtained from an ontological knowledge base. Candidate results are scored using their cohesiveness and their similarity to the original query. Since the number of queries to process can be large, with each result having to be analyzed, we propose pruning techniques to retrieve the top-$k$ results efficiently. We develop two query processing algorithms based on our pruning techniques. Further, we exploit a property of the candidate queries to propose a technique for processing multiple queries in batch, which improves the performance substantially. Extensive experiments on two real datasets verify the effectiveness and efficiency of the proposed approaches.

cs.DB↗

arXiv2017

Frequent Query Matching in Dynamic Data Warehousing

With the need for flexible and on-demand decision support, Dynamic Data Warehouses (DDW) provide benefits over traditional data warehouses due to their dynamic characteristics in structuring and access mechanism. A DDW is a data framework that accommodates data source changes easily to allow seamless querying to users. Materialized Views (MV) are proven to be an effective methodology to enhance the process of retrieving data from a DDW as results are pre-computed and stored in it. However, due to the static nature of materialized views, the level of dynamicity that can be provided at the MV access layer is restricted. As a result, the collection of materialized views is not compatible with ever-changing reporting requirements. It is important that the MV collection is consistent with current and upcoming queries. The solution to the above problem must consider the following aspects: (a) MV must be matched against an OLAP query in order to recognize whether the MV can answer the query, (b) enable scalability in the MV collection, an intuitive mechanism to prune it and retrieve closely matching MVs must be incorporated, (c) MV collection must be able to evolve in correspondence to the regularly changing user query patterns. Therefore, the primary objective of this paper is to explore these aspects and provide a well-rounded solution for the MV access layer to remove the mismatch between the MV collection and reporting requirements. Our contribution to solve the problem includes a Query Matching Technique, a Domain Matching Technique and Maintenance of the MV collection. We developed an experimental platform using real data-sets to evaluate the effectiveness in terms of performance and precision of the proposed techniques.

cs.DB↗

arXiv2017

Computing Influence of a Product through Uncertain Reverse Skyline

Understanding the influence of a product is crucially important for making informed business decisions. This paper introduces a new type of skyline queries, called uncertain reverse skyline, for measuring the influence of a probabilistic product in uncertain data settings. More specifically, given a dataset of probabilistic products P and a set of customers C, an uncertain reverse skyline of a probabilistic product q retrieves all customers c in C which include q as one of their preferred products. We present efficient pruning ideas and techniques for processing the uncertain reverse skyline query of a probabilistic product using R-Tree data index. We also present an efficient parallel approach to compute the uncertain reverse skyline and influence score of a probabilistic product. Our approach significantly outperforms the baseline approach derived from the existing literature. The efficiency of our approach is demonstrated by conducting extensive experiments with both real and synthetic datasets.

cs.DB↗

arXiv2017

Statistical Analysis on Bangla Newspaper Data to Extract Trending Topic and Visualize Its Change Over Time

Trending topic of newspapers is an indicator to understand the situation of a country and also a way to evaluate the particular newspaper. This paper represents a model describing few techniques to select trending topics from Bangla Newspaper. Topics that are discussed more frequently than other in Bangla newspaper will be marked and how a very famous topic loses its importance with the change of time and another topic takes its place will be demonstrated. Data from two popular Bangla Newspaper with date and time were collected. Statistical analysis was performed after on these data after preprocessing. Popular and most used keywords were extracted from the stream of Bangla keyword with this analysis. This model can also cluster category wise news trend or a list of news trend in daily or weekly basis with enough data. A pattern can be found on their news trend too. Comparison among past news trend of Bangla newspapers will give a visualization of the situation of Bangladesh. This visualization will be helpful to predict future trending topics of Bangla Newspaper.

cs.IR↗

arXiv2017

A Comparative Study on Different Types of Approaches to Bengali document Categorization

Document categorization is a technique where the category of a document is determined. In this paper three well-known supervised learning techniques which are Support Vector Machine(SVM), Naïve Bayes(NB) and Stochastic Gradient Descent(SGD) compared for Bengali document categorization. Besides classifier, classification also depends on how feature is selected from dataset. For analyzing those classifier performances on predicting a document against twelve categories several feature selection techniques are also applied in this article namely Chi square distribution, normalized TFIDF (term frequency-inverse document frequency) with word analyzer. So, we attempt to explore the efficiency of those three-classification algorithms by using two different feature selection techniques in this article.

cs.CL↗

arXiv2017

Document Decomposition of Bangla Printed Text

Today all kind of information is getting digitized and along with all this digitization, the huge archive of various kinds of documents is being digitized too. We know that, Optical Character Recognition is the method through which, newspapers and other paper documents convert into digital resources. But, it is a fact that this method works on texts only. As a result, if we try to process any document which contains non-textual zones, then we will get garbage texts as output. That is why; in order to digitize documents properly they should be prepossessed carefully. And while preprocessing, segmenting document in different regions according to the category properly is most important. But, the Optical Character Recognition processes available for Bangla language have no such algorithm that can categorize a newspaper/book page fully. So we worked to decompose a document into its several parts like headlines, sub headlines, columns, images etc. And if the input is skewed and rotated, then the input was also deskewed and de-rotated. To decompose any Bangla document we found out the edges of the input image. Then we find out the horizontal and vertical area of every pixel where it lies in. Later on the input image was cut according to these areas. Then we pick each and every sub image and found out their height-width ratio, line height. Then according to these values the sub images were categorized. To deskew the image we found out the skew angle and de skewed the image according to this angle. To de-rotate the image we used the line height, matra line, pixel ratio of matra line.

cs.CV↗