Browsing by Author "Hasan, Md. Arid"

Now showing 1 - 12 of 12

A Collaborative Platform to Collect Data for Developing Machine Translation System
(Daffodil International University, 2018-12-11) Hasan, Md. Arid
The emergence of neural machine translation techniques has opened up a new era for developing translation systems. However, it requires a very large amount of parallel corpus, which is scarce for many under-resourced languages, e.g., Bangla. In order to develop a corpus, currently, there is a lack of publicly available collaborative system. In this paper, we report an online collaborative system for the development of the parallel corpus. The system is developed for supporting any language, however, we only evaluated for developing Bangla-English parallel corpus. In a task completion evaluation experiment, the system outperforms the widely used offline system i.e., OmegaT.
BlackOps at CheckThat! 2021
(Scopus, 2021) Sohan, S.M.; Khushbu, Shrun Akter; Islam, Md. Sanzidul; Hasan, Md. Arid
An expensive task is fake news detection for recent trends among the concept of misinformation or rumors. In everywhere most of the times information lead or play emergent preface but forthwith misinformation also in everywhere to mislead the peoples mind and activity. Therefore, detecting fake content in any system can be a weapon over fictitious news. In any language cross over the exponential growth of fake news in social sites. Hence, it is the real time process to produce online fake news so that it has been needed to implement an automated technique whenever detect true from false. According to the solution of this approach made a research On English language textual inputs as twitter news from user profiles. At this point, due to accurate analysis for social media we experimented with supervised learning such as Decision tree, Random forest and gradient boosting. In between all the ML classifiers outperformed with 88% detection accuracy that mention the research of detection is more accurate.
Brain Tumor Analysis Using Deep Neural Network
(Proceedings - 5th International Conference on Intelligent Computing and Control Systems, IEEE, 2021-05-26) Khan, Iftekhar; Ahsan, Kuheli; Hasan, Md. Arid; Sattar, Abdus
The identification of tumors is one of the most tenacious and emerging fields in medical image processing. A tumor means the unrestricted existence of a bunch of cells in a precise area of the human body which destroys the normal body cells and keeps increasing. In human body, brain tumor is measured as the most common tumor which affects the nervous system, memory functional cells, glands, and membranes that surround the brain and can conduct to a high mortality rate if the affected one is unsuccessful to reach proper medical treatment. For effective treatment, precise and early recognition of the tumors is critical work and also a vital step in diagnosis and treatment preparation for affected one which not only benefits to arise with improved medications but also saves the affected life in due time. This research work uses Magnetic Resonance Imaging (MRI), which is a prominent imaging procedure in terms of brain tumor recognition. For features extraction, segmentation and classification, the proposed research work includes the deep neural network integrated method and Convolutional Neural Network (CNN) to classify the MRI images and an accuracy of about 97.92% has been achieved.
FakeDTML at CheckThat! 2023: Identifying Check-Worthiness of Tweets and Debate Snippets
(Conference and Labs of the Evaluation Forum, 2023-09-18) Sardar, Abdullah Al Mamun; Karim, Md. Ziaul; Dey, Krishno; Hasan, Md. Arid
"There is a wealth of knowledge available online. Some are trustworthy, while others are deceptive and phony. The need to identify such false information arises from the danger it poses to society at a mass. Nowadays, there is a significant need for information that requires fact-checking. As a result, we need a layer preceding fact-checking, where it can be determined whether a claim is check-worthy. This will streamline the automated fact-checking process by filtering out a lot of unnecessary data that is nonetheless necessary. We carried out such a study as part of CLEF 2023 CheckThat! Lab (CTL) task 1B, where we were provided with a dataset of tweets and debate snippets and were asked to conduct an experiment to verify whether a particular news tweet/debate snippet is check worthy. The dataset contains 3 languages (English, Arabic, Spanish). We used several machine learning and deep learning algorithms in our experiments. Among them, XLM-RoBERTa which outperformed other algorithms for English and Arabic but for Spanish we found that Logistic Regression can outperform other models."
MEDIC: A Multi-Task Learning Dataset for Disaster Image Classification
(Springer Nature, 2022-09-03) Alam, Firoj; Alam, Tanvirul; Hasan, Md. Arid; Hasnat, Abul; Imran, Muhammad; Ofli, Ferda
Recent research in disaster informatics demonstrates a practical and important use case of artificial intelligence to save human lives and suffering during natural disasters based on social media contents (text and images). While notable progress has been made using texts, research on exploiting the images remains relatively under-explored. To advance image-based approaches, we propose MEDIC (https://crisisnlp.qcri.org/medic/index.html), which is the largest social media image classification dataset for humanitarian response consisting of 71,198 images to address four different tasks in a multi-task learning setup. This is the first dataset of its kind: social media images, disaster response, and multi-task learning research. An important property of this dataset is its high potential to facilitate research on multi-task learning, which recently receives much interest from the machine learning community and has shown remarkable results in terms of memory, inference speed, performance, and generalization capability. Therefore, the proposed dataset is an important resource for advancing image-based disaster management and multi-task machine learning research. We experiment with different deep learning architectures and report promising results, which are above the majority baselines for all tasks. Along with the dataset, we also release all relevant scripts
NN at CheckThat! 2023: Subjectivity in News Articles Classification with Transformer Based Models
(CEUR Workshop Proceedings, 2023-08-31) Dey, Krishno; Tarannum, Prerona; Hasan, Md. Arid; Noori, Sheak Rashed Haider
The CheckThat! Lab is a challenging lab designed to address the issue of disinformation. We participated in CheckThat! Lab Task 2, which is focused on classification of subjectivity in news articles. This shared task included datasets in six different languages, as well as a multilingual dataset created by combining all six languages. We followed standard preprocessing steps for Arabic, Dutch, English, German, Italian, Turkish, and multilingual text data. We employed a transformer-based pretrained model, specifically XLM-RoBERTa large, for our official submission to the CLEF Task 2. Our results were impressive, as we achieved the 1st, 1st, 2nd, 5th, 2nd, 2nd, and 3rd positions on the leaderboard for the multilingual, Arabic, Dutch, English, German, Italian, and Turkish text data, respectively. Furthermore, we also applied BERT and BERT multilingual (BERT-m) models to assess the subjectivity of the text data. Our study revealed that XLM-RoBERTa large outperformed BERT and BERT-m in all performance measures for this particular dataset provided in the shared task.
Simulating Using Deep Learning The World Trade Forecasting of Export-Import Exchange Rate Convergence Factor During COVID-19
(Daffodil International University, 2022-04-20) Lucky, Effat Ara Easmin; Sany, Md. Mahadi Hasan; Keya, Mumenunnesa; Rahaman, Md. Moshiur; Happy, Umme Habiba; Khushbu, Sharun Akter; Hasan, Md. Arid
By trade we usually mean the exchange of goods between states and countries. International trade acts as a barometer of the economic prosperity index and every country is overly dependent on resources, so international trade is essential. Trade is significant to the global health crisis, saving lives and livelihoods. By collecting the dataset called "Effects of COVID19 on trade" from the state website NZ Tatauranga Aotearoa, we have developed a sustainable prediction process on the effects of COVID-19 in world trade using a deep learning model. In the research, we have given a 180-day trade forecast where the ups and downs of daily imports and exports have been accurately predicted in the Covid-19 period. In order to fulfill this prediction, we have taken data from 1st January 2015 to 30th May 2021 for all countries, all commodities, and all transport systems and have recovered what the world trade situation will be in the next 180 days during the Covid-19 period. The deep learning method has received equal attention from both investors and researchers in the field of in-depth observation. This study predicts global trade using the Long-Short Term Memory. Time series analysis can be useful to see how a given asset, security, or economy changes over time. Time series analysis plays an important role in past analysis to get different predictions of the future and it can be observed that some factors affect a particular variable from period to period. Through the time series it is possible to observe how various economic changes or trade effects change over time. By reviewing these changes, one can be aware of the steps to be taken in the future and a country can be more careful in terms of imports and exports accordingly. From our time series analysis, it can be said that the LSTM model has given a very gracious thought of the future world import and export situation in terms of trade.
Text Extraction through Video Lip Reading Using Deep Learning
(Scopus, 2020) Chowdhury, S.M. Mazharul Hoque; Rahman, Mushfiqur; Oyshi, Marzan Tasnim; Hasan, Md. Arid
Automated text extraction from video data through lip reading can overcome the language barrier and open the door of opportunities in terms of security, connectivity and physical challenges. The conversion is possible by analyzing facial expression using deep learning method. But this conversion is a challenging task due to the varieties of pronunciation and accents of the same word causing different countenance. In this research, a method of converting video data to text data through lip reading has been proposed. The proposed method includes test dataset, image frame analysis and having text output from identified words. In the proposed technique, the test dataset will be organized by combining all the possible facial expressions of different words.
Z-Index at CheckThat! 2023:
(Daffodil International University, 2023-08) Tarannum, Prerona; Hasan, Md. Arid; Alam, Firoj; Noori, Sheak Rashed Haider
"In this study, we report our participation in CheckThat! lab’s Task 1. The aim is to determine whether a claim made in either unimodal or multimodal content is worth fact-checking. We implemented standard preprocessing and fine-tuned the XLM-RoBERTa-large model. Additionally, we applied zero-shot learning and utilized a feed-forward network with embeddings for unimodal content. For subtask 1A submission, we used combined BERT-based models (BERT and BERT multilingual), ResNet50, and Feed Forward network and we ranked as 3rd (Arabic) and 5th (English). We used feed forward network with embeddings for subtask 1B submission and ranked as 3rd in Arabic and 6th in both English and Spanish. In further experiments, our evaluation shows that XLM-RoBERTa-large model outperforms the other models"
Zero- and Few-Shot Prompting with LLMs:
(Daffodil International University, 2024-05-30) Hasan, Md. Arid; Das, Shudipta; Anjum, Afiyat; Alam, Firoj; Anjum, Anika; Sarke, Avijit; Noori, Sheak Rashed Haider
The rapid expansion of the digital world has propelled sentiment analysis into a critical tool across diverse sectors such as marketing, politics, customer service, and healthcare. While there have been significant advancements in sentiment analysis for widely spoken languages, low-resource languages, such as Bangla, remain largely under-researched due to resource constraints. Furthermore, the recent unprecedented performance of Large Language Models (LLMs) in various applications highlights the need to evaluate them in the context of low-resource languages. In this study, we present a sizeable manually annotated dataset encompassing 33,606 Bangla news tweets and Facebook comments. We also investigate zero- and few-shot in-context learning with several language models, including Flan-T5, GPT-4, and Bloomz, offering a comparative analysis against fine-tuned models. Our findings suggest that monolingual transformer-based models consistently outperform other models, even in zero and few-shot scenarios. To foster continued exploration, we intend to make this dataset and our research tools publicly available to the broader research community.
Zero- and Few-Shot Prompting with LLMs: A Comparative Study with Fine-tuned Models for Bangla Sentiment Analysis
(Scopus, 2024) Hasan, Md. Arid; Das, Shudipta; Anjum, Afiyat; Alam, Firoj; Anjum, Anika; Sarker, Avijit; Noori, Sheak Rashed Haider
The rapid expansion of the digital world has propelled sentiment analysis into a critical tool across diverse sectors such as marketing, politics, customer service, and healthcare. While there have been significant advancements in sentiment analysis for widely spoken languages, low-resource languages, such as Bangla, remain largely under-researched due to resource constraints. Furthermore, the recent unprecedented performance of Large Language Models (LLMs) in various applications highlights the need to evaluate them in the context of low-resource languages. In this study, we present a sizeable manually annotated dataset encompassing 33,606 Bangla news tweets and Facebook comments. We also investigate zero- and few-shot in-context learning with several language models, including Flan-T5, GPT-4, and Bloomz, offering a comparative analysis against fine-tuned models. Our findings suggest that monolingual transformer-based models consistently outperform other models, even in zero and few-shot scenarios. To foster continued exploration, we intend to make this dataset and our research tools publicly available to the broader research community.
Zero- and Few-Shot Prompting with LLMs: A Comparative Study with Fine-tuned Models for Bangla Sentiment Analysis
(Elsevier, 2024-05-25) Hasan, Md. Arid; Das, Shudipta; Anjum, Afiyat; Alam, Firoj; Anjum, Anika; Sarker, Avijit; Sheak Rashed Haider; Noori, Sheak Rashed Haider
The rapid expansion of the digital world has propelled sentiment analysis into a critical tool across diverse sectors such as marketing, politics, customer service, and healthcare. While there have been significant advancements in sentiment analysis for widely spoken languages, low-resource languages, such as Bangla, remain largely under-researched due to resource constraints. Furthermore, the recent unprecedented performance of Large Language Models (LLMs) in various applications highlights the need to evaluate them in the context of low-resource languages. In this study, we present a sizeable manually annotated dataset encompassing 33,606 Bangla news tweets and Facebook comments. We also investigate zero- and few-shot in-context learning with several language models, including Flan-T5, GPT-4, and Bloomz, offering a comparative analysis against fine-tuned models. Our findings suggest that monolingual transformer-based models consistently outperform other models, even in zero and few-shot scenarios. To foster continued exploration, we intend to make this dataset and our research tools publicly available to the broader research community.