Browsing by Author "Islam, Taminul"

Now showing 1 - 20 of 20

A Proposed Bi-LSTM Method to Fake News Detection
(Daffodil International University, 2022-04-22) Islam, Taminul; Hosen, MD Alamin; Mony, Akhi; Hasan, MD Touhid; Jahan, Israt; Kundu, Arindom
Recent years have seen an explosion in social media usage, allowing people to connect with others. Since the appearance of platforms such as Facebook and Twitter, such platforms influence how we speak, think, and behave. This problem negatively undermines confidence in content because of the existence of fake news. For instance, false news was a determining factor in influencing the outcome of the U.S. presidential election and other sites. Because this information is so harmful, it is essential to make sure we have the necessary tools to detect and resist it. We applied Bidirectional Long Short-Term Memory (Bi-LSTM) to determine if the news is false or real in order to showcase this study. A number of foreign websites and newspapers were used for data collection. After creating & running the model, the work achieved 84% model accuracy and 62.0 F1-macro scores with training data.
AI-Enabled Risk Assessment and Safety Management in Construction
(Scopus, 2024) Usama, Muhammad; Ullah, Ubaid; Muhammad, Zaid; Islam, Taminul; Hashmi, Syeda saba
The construction industry is characterized by its complex and dynamic nature, where risk assessment and safety management play pivotal roles in ensuring project success and worker well-being. Integrating Artificial Intelligence (AI) technologies has introduced transformative possibilities for enhancing risk assessment methodologies and safety management practices in construction projects. This chapter explores the synergistic relationship between AI and construction safety, shedding light on the innovative applications, benefits, and challenges that emerge when AI is harnessed to improve risk analysis and safety protocols. Furthermore, the ethical and social considerations associated with adopting AI in construction safety are explored, underlining the importance of striking a balance between technological advancement and the human element. The potential challenges related to data privacy, algorithm transparency, and workforce upskilling are addressed, offering insights into the responsible deployment of AI-enabled safety solutions. This chapter underscores the transformative potential of AI-enabled risk assessment and safety management in construction. By leveraging cutting-edge AI technologies, construction stakeholders can revolutionize traditional safety practices, leading to enhanced project outcomes, reduced incidents, and improved overall industry sustainability.
Analysis of Arrhythmia Classification on ECG Dataset
(Daffodil International University, 2022-08-04) Islam, Taminul; Kundu, Arindom; Ahmed, Tanzim; Khan, Nazmul Islam
The heart is one of the most vital organs in the human body. It supplies blood and nutrients in other parts of the body. Therefore, maintaining a healthy heart is essential. As a heart disorder, arrhythmia is a condition in which the heart's pumping mechanism becomes aberrant. The Electrocardiogram is used to analyze the arrhythmia problem from the ECG signals because of its fewer difficulties and cheapness. The heart peaks shown in the ECG graph are used to detect heart diseases, and the R peak is used to analyze arrhythmia disease. Arrhythmia is grouped into two groups - Tachycardia and Bradycardia for detection. In this paper, we discussed many different techniques such as Deep CNNs, LSTM, SVM, NN classifier, Wavelet, TQWT, etc., that have been used for detecting arrhythmia using various datasets throughout the previous decade. This work shows the analysis of some arrhythmia classification on the ECG dataset. Here, Data preprocessing, feature extraction, classification processes were applied on most research work and achieved better performance for classifying ECG signals to detect arrhythmia. Automatic arrhythmia detection can help cardiologists make the right decisions immediately to save human life. In addition, this research presents various previous research limitations with some challenges in detecting arrhythmia that will help in future research.
Cardiovascular Disease Prediction Using Machine Learning Approaches
(IEEE, 2023-07-22) Islam, Taminul; Vuyia, Adifa; Hasan, Mahadi; Rana, Md Masum
As of the release of COVID-19, cardiovascular disease has surpassed all other causes of mortality among both sexes. In most cases, this condition is associated with atherosclerosis and the formation of blood clots. Heart disease, stroke, and other CVDs are major causes of mortality worldwide. Because even a small inaccuracy might lead to exhaustion or death, increased precision, perfection, and accuracy are required for diagnosing and predicting heart-related disorders. In this paper, data was collected from 1189 patients with some attributes related to heart disease and kept 80% data for training, and 20% data for testing and determining their accuracy using different models. In this study, enhanced preprocessing steps were used to increase the accuracy of cardiovascular disease prediction. It aids in determining whether a patient has heart disease and helps a doctor to determine whether or not a patient has cardiovascular disease. The applied models are Extreme Gradient Boosting, Random Forest, CART, Extra Tree Classifier, and Gradient Boosting Machine. This work compared the performance of several Machine Learning algorithms that make use of the accuracy of the metrics, $F_1$ -score, recall, and precision to demonstrate the validity of our findings. The Extreme Gradient Boosting model has achieved the best 91.9% accuracy in this research.
Child and Maternal Mortality Risk Factor Analysis Using Machine Learning Approaches
(IEEE, 2023-05-26) Sheakh, Md. Alif; Tahosin, Mst. Sazia; Hasan, Md Maruf; Islam, Taminul
Global attention is now being paid to maternal and child mortality. The incidence of maternal mortality is high in low and middle-income countries, particularly among adolescents and young adults. Healthcare professionals can monitor the mother's heartbeat during pregnancy to determine fetal viability using CTGs to prevent these deaths. To reduce child and maternal mortality, this work presented a risk factor analysis using machine learning approaches. As part of this study, this work evaluated seven machine learning algorithms. To assess the performance of different categorization algorithms, accuracy, precision, and recall were used. The random forest has achieved the highest 99.98% accuracy among the other algorithms. Initially, the dataset was imbalanced, after applying undersampling and oversampling methods, all algorithms performed excellently. A major focus of the present study was to predict the risk factor of child and maternal mortality using clinical data. Sending an ultrasound pulse and reading the response is how ultrasound devices work. To prevent child and maternal mortality, this analysis is an effective and cost-effective option for healthcare professionals.
Convolutional Neural Network Based Partial Face Detection
(Daffodil International University, 2022-08-01) Islam, Md. Towfiqul; Ahmed, Tanzim; Rashid, A.B.M. Raihanur; Islam, Taminul; Rahman, Md. Sadekur; Habib, Md. Tarek
Due to the massive explanation of artificial intelligence, machine learning technology is being used in various areas of our day-to-day life. In the world, there are a lot of scenarios where a simple crime can be prevented before it may even happen or find the person responsible for it. A face is one distinctive feature that we have and can differentiate easily among many other species. But not just different species, it also plays a significant role in determining someone from the same species as us, humans. Regarding this critical feature, a single problem occurs most often nowadays. When the camera is pointed, it cannot detect a person’s face, and it becomes a poor image. On the other hand, where there was a robbery and a security camera installed, the robber’s identity is almost indistinguishable due to the low-quality camera. But just making an excellent algorithm to work and detecting a face reduces the cost of hardware, and it doesn’t cost that much to focus on that area. Facial recognition, widget control, and such can be done by detecting the face correctly. This study aims to create and enhance a machine learning model that correctly recognizes faces. Total 627 Data have been collected from different Bangladeshi people's faces on four angels. In this work, CNN, Harr Cascade, Cascaded CNN, Deep CNN & MTCNN are these five machine learning approaches implemented to get the best accuracy of our dataset. After creating and running the model, Multi-Task Convolutional Neural Network (MTCNN) achieved 96.2% best model accuracy with training data rather than other machine learning models.
Data Traffic Management in AI-IOt Network to Reduce Congestion
(CRC Press, 2024-07-15) Usama, Muhammad; Ullah, Ubaid; Muhammad, Zaid; Bux, Muhammad; Ullah, Inam; Rouf, Muhammad; Islam, Taminul
As the artificial intelligence–internet of things (AI-IoT) network expands, the exponential growth in data generated by connected devices is leading to increased data traffic in AI-IoT networks. The surge in data traffic poses significant challenges to network infrastructure, causing congestion, latency, and inefficiencies. To address this issue, effective data traffic management techniques are crucial. This book chapter focuses on data traffic management in AI-AI-IoT networks to reduce congestion. It explores the underlying causes of congestion in AI-IoT networks and presents a comprehensive overview of existing congestion control mechanisms. Additionally, the chapter highlights the unique characteristics and requirements of AI-AI-IoT networks that differentiate them from traditional networks. It also examines various congestion detection and avoidance techniques designed explicitly for AI-AI-IoT environments, considering AI-IoT devices’ heterogeneity, scalability, and resource constraints. It discusses the importance of intelligent routing algorithms, traffic classification, and prioritization mechanisms in managing data traffic effectively. Moreover, the chapter delves into emerging technologies such as edge computing, fog computing, and network slicing, which can be leveraged to alleviate congestion in AI-IoT networks. It explores how off-loading computation and data processing tasks to the network edge can enhance traffic management and reduce latency. So this chapter provides valuable insights into the domain of data traffic management in AI-AI-IoT networks. It is a comprehensive resource for researchers, practitioners, and professionals interested in understanding and implementing effective congestion control mechanisms to ensure optimal performance and scalability in AI-IoT environments.
Disaster Related Tweets Analysis with Machine Learning Approaches
(Elsevier, 2023-11-26) Islam, Taminul; Islam, Monjurul; Rudra, Rahul; Pranto, Ismail Hossain; Mahmud, Md.Tanvir; Foysal, Md. Musfiqur Rahman
It's no secret that the microblogging service Twitter (X) has quickly risen to prominence as one of the most reliable places to get the latest updates on breaking events. Tweets, Twitter's information streams, are sent out voluntarily by registered users and can reach even non-registered users, often before more conventional sources of mass news. In this research, we use machine learning to create models that can find helpful tweets on disasters automatically. Social media users provide massive amounts of data during natural catastrophe situations, some of which are useful for relief operations and emergency management. In this work, we analyze the material shared on social media during two hurricanes and one earthquake. This research has shown a machine-learning approach to categorizing tweets in relation to disasters and labeling Twitter data. This study has applied five machine learning algorithms to predict disaster and nondisaster tweets. In our model and among these five machine learning algorithms three perform similarly, but Logistic Regression has achieved the best 80.5% model accuracy among all other algorithms.
Early-Stage Diabetes Risk Prediction Using Supervised Machine Learning Algorithms
(Institute of Electrical and Electronics Engineers Inc., 2023-01-04) Islam, Taminul; Sadik, Md Rezwane; Islam, Md. Fajle Rabbi; Mona, Tanzina Rahman; Rahman, Tanjila; Foysal, Md. Musfiqur Rahman
Diabetes is a common health problem worldwide; it is especially pervasive in Bangladesh. The condition manifests in a person when his blood sugar is consistently high. It also contributes to other health problems like blindness, renal failure, heart attack, and stroke. If you know about the early stage, you can take charge and maybe save someone's life. Sadly, this illness is spreading rapidly. The purpose of this research was to quantitatively evaluate the effectiveness of many widely used Machine Learning methods. The medical field is only one area that has benefited greatly from recent advancements in Machine Learning technology. Machine learning algorithms come in a wide variety. Nevertheless, in this research we employ five well-known machine learning algorithms to determine performance metrics: Gaussian Naive Bayes, Random Forest, Support Vector Machine, Logistic Regression, and the Decision Tree classifier. Using real data from diabetic patients in Bangladesh, these algorithms were developed and evaluated. There are 3837 patient records in the dataset, 3057 of which correspond to affected cases and 396 were normal. Out of 5 different machine learning algorithms, Random Forest achieved the highest 98% accuracy.
Enhancing Bangla Fake News Detection Using Bidirectional Gated Recurrent Units and Deep Learning Techniques
(Scopus, 2024-03-31) Roy, Utsha; Tahosin, Mst. Sazia; Hassan, Md. Mahedi; Islam, Taminul; Imtiaz, Fahim; Sadik, Md Rezwane; Maleh, Yassine; Sulaiman, Rejwan Bin; Talukder, Md. Simul Hasan
The rise of fake news has made the need for effective detection methods, including in languages other than English, increasingly important. The study aims to address the challenges of Bangla which is considered a less important language. To this end, a complete dataset containing about 50,000 news items is proposed. Several deep learning models have been tested on this dataset, including the bidirectional gated recurrent unit (GRU), the long short-term memory (LSTM), the 1D convolutional neural network (CNN), and hybrid architectures. For this research, we assessed the efficacy of the model utilizing a range of useful measures, including recall, precision, F1 score, and accuracy. This was done by employing a big application. We carry out comprehensive trials to show the effectiveness of these models in identifying bogus news in Bangla, with the Bidirectional GRU model having a stunning accuracy of 99.16%. Our analysis highlights the importance of dataset balance and the need for continual improvement efforts to a substantial degree. This study makes a major contribution to the creation of Bangla fake news detecting systems with limited resources, thereby setting the stage for future improvements in the detection process.
Improving Hepatitis C Diagnosis Using Machine Learning Techniques an Experimental Analysis
(CRC Press, 2024-07-15) Sheakh, Alif; Sazia, Tahosin; Islam, Taminul; Lima, Rishalatun Jannat
Hepatitis C is a major global health problem; the right diagnosis is critical to effective disease management. In recent years, machine learning techniques have shown promise in improving diagnostic accuracy in various medical applications. We aim to improve the diagnosis of hepatitis C by comprehensively analyzing several machine learning algorithms in this study. We compared and evaluated the classification accuracy, precision, and recall of 12 different models, including random forest, gradient boosting, k-nearest neighbors, extreme gradient boost, extra trees, AdaBoost, LogitBoost, CatBoost, support vector machine, naive Bayes, neural network (multilayer perceptrons) and Gaussian process classifiers. Here, we train and test these machine learning models to determine the most effective way to classify hepatitis C diagnoses. We evaluate the algorithm’s accuracy and compare our results with existing literature. The highest model accuracy in this study using LogitBoost was 98%, while extra trees achieved 99% accuracy after undersampling the data. This experimental analysis demonstrates the potential of machine learning techniques to improve hepatitis C diagnosis. The high accuracy of the LogitBoost and extra trees models highlights their effectiveness in identifying hepatitis C cases. By harnessing the power of machine learning algorithms, we can improve hepatitis C diagnostics, enabling early detection, timely intervention, and improved patient outcomes. The results of this study have major implications for the medical community and may improve the development of more accurate and effective hepatitis C diagnostic tools.
Machine Learning Approach on Multiclass Classification of Internet Firewall Log Files
(IEEE, 2023-01-15) Rahman, Md Habibur; Islam, Taminul; Rana, Md Masum; Tasnim, Rehnuma; Mona, Tanzina Rahman; Sakib, Md. Mamun
"Firewalls are critical components in securing communication networks by screening all incoming (and occasionally exiting) data packets. Filtering is carried out by comparing incoming data packets to a set of rules designed to prevent malicious code from entering the network. To regulate the flow of data packets entering and leaving a network, an Internet firewall keeps a track of all activity. While the primary function of log files is to aid in troubleshooting and diagnostics, the information they contain is also very relevant to system audits and forensics. Firewall’s primary function is to prevent malicious data packets from being sent. In order to better defend against cyberattacks and understand when and how malicious actions are influencing the internet, it is necessary to examine log files. As a result, the firewall decides whether to 'allow,' 'deny,' 'drop,' or 'reset-both' the incoming and outgoing packets. In this research, we apply various categorization algorithms to make sense of data logged by a firewall device. Harmonic mean F1 score, recall, and sensitivity measurement data with a 99% accuracy score in the random forest technique are used to compare the classifier's performance. To be sure, the proposed characteristics did significantly contribute to enhancing the firewall classification rate, as seen by the high accuracy rates generated by the other methods.
Machine Learning Approaches to Predict Breast Cancer
(Daffodil International University, 2022-06-20) Islam, Taminul; Kundu, Arindom; Khan, Nazmul Islam; Bonik, Choyon Chandra; Akter, Flora; Islam, Md. Jihadul
Nowadays, Breast cancer has risen to become one of the most prominent causes of death in recent years. Among all malignancies, this is the most frequent and the major cause of death for women globally. Manually diagnosing this disease requires a good amount of time and expertise. Breast cancer detection is time-consuming, and the spread of the disease can be reduced by developing machine-based breast cancer predictions. In Machine learning, the system can learn from prior instances and find hard-to-detect patterns from noisy or complicated data sets using various statistical, probabilistic, and optimization approaches. This work compares several machine learning algorithms' classification accuracy, precision, sensitivity, and specificity on a newly collected dataset. In this work Decision tree, Random Forest, Logistic Regression, Naïve Bayes, and XGBoost, these five machine learning approaches have been implemented to get the best performance on our dataset. This study focuses on finding the best algorithm that can forecast breast cancer with maximum accuracy in terms of its classes. This work evaluated the quality of each algorithm's data classification in terms of efficiency and effectiveness. And also compared with other published work on this domain. After implementing the model, this study achieved the best model accuracy, 94% on Random Forest and XGBoost.
Optimizing Brain Tumor Classification Through Feature Selection and Hyperparameter Tuning In Machine Learning Models
(Elsevier, 2023-11-24) Tahosin, Mst Sazia; Sheakh, Md Alif; Islam, Taminul; Lima, Rishalatun Jannat; Begum, Mahbuba
"Accurately classifying brain tumors using images is extremely important for prognosis and treatment planning. In this study, we have developed an optimized approach using machine learning techniques to classify brain tumors. Our method involves preprocessing the images, extracting features, selecting the most significant ones, and tuning the model parameters. We utilized filtering, morphological opening, and normalization techniques to enhance image quality and reduce noise. We have extracted 17 features that capture the characteristics of the tumors and identify the seven most distinguishing features through importance analysis. By employing a range of models such as Random Forest, Support Vector Machines, Extreme Gradient Boosting, K Nearest Neighbors, Categorical Boosting, Extra Trees, and Naive Bayes, we achieve an accuracy of 98.0 % after thorough hyperparameter optimization. This research highlights the impact of the feature selection process, along with model tuning, on maximizing classification performance. This approach provides a framework that enables the diagnosis of brain tumors for enhanced clinical decision-making and patient care.
Potato Leaf Disease Classification Using K-Means Cluster Segmentation and Effective Deep Learning Networks
(Elsevier, 2023-07-31) Talukder, Md. Simul Hasan; Sulaiman, Rejwan Bin; Chowdhury, Mohammad Raziuddin; Nipun, Musarrat Saberin; Islam, Taminul
Potatoes are the third-largest food crop globally, but their production frequently encounters difficulties because of aggressive pest infestations. Early classification those potato pests plays an important role in the detection and prevention of their notorious attack. The aim of this study is to investigate the various types and characteristics of these pests and propose an efficient PotatoPestNet AI-based automatic potato pest identification system. To accomplish this, we curated a reliable dataset consisting of eight types of potato pests. We leveraged the power of transfer learning by employing five customized, pre-trained transfer learning models: CMobileNetV2, CNASLargeNet, CXception, CDenseNet201, and CInceptionV3, in proposing a robust PotatoPestNet model to accurately classify potato pests. To improve the models' performance, we applied various augmentation techniques, incorporated a global average pooling layer, and implemented proper regularization methods. To further enhance the performance of the models, we utilized random search (RS) optimization for hyperparameter tuning. This optimization technique played a significant role in fine-tuning the models and achieving improved performance. We evaluated the models both visually and quantitatively, utilizing different evaluation metrics. The robustness of the models in handling imbalanced datasets was assessed using the Receiver Operating Characteristic (ROC) curve. Among the models, the Customized Tuned Inception V3 (CTInceptionV3) model, optimized through random search, demonstrated outstanding performance. It achieved the highest accuracy (91%), precision (91%), recall (91%), and F1-score (91%), showcasing its superior ability to accurately identify and classify potato pests.
Predictive modeling for breast cancer classification in the context of Bangladeshi patients by use of machine learning approach with explainable AI
(Scopus, 2024) Islam, Taminul; Sheakh, Md. Alif; Tahosin, Mst. Sazia; Hena, Most. Hasna; Akash, Shopnil; Jardan, Yousef A. Bin; Wondmie, Gezahign Fentahun; Nafidi, Hiba-Allah; Bourhia, Mohammed
Breast cancer has rapidly increased in prevalence in recent years, making it one of the leading causes of mortality worldwide. Among all cancers, it is by far the most common. Diagnosing this illness manually requires significant time and expertise. Since detecting breast cancer is a time-consuming process, preventing its further spread can be aided by creating machine-based forecasts. Machine learning and Explainable AI are crucial in classification as they not only provide accurate predictions but also offer insights into how the model arrives at its decisions, aiding in the understanding and trustworthiness of the classification results. In this study, we evaluate and compare the classification accuracy, precision, recall, and F1 scores of five different machine learning methods using a primary dataset (500 patients from Dhaka Medical College Hospital). Five different supervised machine learning techniques, including decision tree, random forest, logistic regression, naive bayes, and XGBoost, have been used to achieve optimal results on our dataset. Additionally, this study applied SHAP analysis to the XGBoost model to interpret the model’s predictions and understand the impact of each feature on the model’s output. We compared the accuracy with which several algorithms classified the data, as well as contrasted with other literature in this field. After final evaluation, this study found that XGBoost achieved the best model accuracy, which is 97%.
Predictive Modeling for Breast Cancer Classification in the Context of Bangladeshi Patients by Use of Machine Learning Approach with Explainable Ai
(Springer Nature, 2024-04-11) Islam, Taminul; Sheakh, Md. Alif; Tahosin, Mst. Sazia; Hena, Most. Hasna; Akash, Shopnil; Jardan, Yousef A. Bin; Wondmie, Gezahign Fentahun; Nafidi, Hiba‑Allah; Bourhia, Mohammed
Breast cancer has rapidly increased in prevalence in recent years, making it one of the leading causes of mortality worldwide. Among all cancers, it is by far the most common. Diagnosing this illness manually requires significant time and expertise. Since detecting breast cancer is a time-consuming process, preventing its further spread can be aided by creating machine-based forecasts. Machine learning and Explainable AI are crucial in classification as they not only provide accurate predictions but also offer insights into how the model arrives at its decisions, aiding in the understanding and trustworthiness of the classification results. In this study, we evaluate and compare the classification accuracy, precision, recall, and F1 scores of five different machine learning methods using a primary dataset (500 patients from Dhaka Medical College Hospital). Five different supervised machine learning techniques, including decision tree, random forest, logistic regression, naive bayes, and XGBoost, have been used to achieve optimal results on our dataset. Additionally, this study applied SHAP analysis to the XGBoost model to interpret the model’s predictions and understand the impact of each feature on the model’s output. We compared the accuracy with which several algorithms classified the data, as well as contrasted with other literature in this field. After final evaluation, this study found that XGBoost achieved the best model accuracy, which is 97%.
Predictive modeling for breast cancer classification in the context of Bangladeshi patients by use of machine learning approach with explainable AI
(Scopus, 2024-04-11) Islam, Taminul; Sheakh, Md. Alif; Tahosin, Mst. Sazia; Hena, Most. Hasna; Akash, Shopnil; Jardan, Yousef A. Bin; Wondmie, Gezahign Fentahun; Nafidi, Hiba-Allah; Bourhia, Mohammed
Breast cancer has rapidly increased in prevalence in recent years, making it one of the leading causes of mortality worldwide. Among all cancers, it is by far the most common. Diagnosing this illness manually requires significant time and expertise. Since detecting breast cancer is a time-consuming process, preventing its further spread can be aided by creating machine-based forecasts. Machine learning and Explainable AI are crucial in classification as they not only provide accurate predictions but also offer insights into how the model arrives at its decisions, aiding in the understanding and trustworthiness of the classification results. In this study, we evaluate and compare the classification accuracy, precision, recall, and F1 scores of five different machine learning methods using a primary dataset (500 patients from Dhaka Medical College Hospital). Five different supervised machine learning techniques, including decision tree, random forest, logistic regression, naive bayes, and XGBoost, have been used to achieve optimal results on our dataset. Additionally, this study applied SHAP analysis to the XGBoost model to interpret the model’s predictions and understand the impact of each feature on the model’s output. We compared the accuracy with which several algorithms classified the data, as well as contrasted with other literature in this field. After final evaluation, this study found that XGBoost achieved the best model accuracy, which is 97%.
Review Analysis of Ride-sharing Application Using BILSTM Based RNN Model- Bangladesh Perspective
(Daffodil International University, 2022-01-02) Islam, Taminul; Lima, Rishalatun Jannat; Kundu, Arindom
Technology and ride-sharing services have become more accessible and convenient as a result of the growth of the internet. Passengers increasingly focus on digital reviews to help them make purchasing decisions. Online reviews are incredibly inaccurate, as we've seen time and time again. False reviews were created to deceive customers for commercial purposes. A misleading review might have major repercussions for any organization. Providing good feedback to attract passengers and grow the market. It's possible that a bad review of an app would reduce interest in it. These false reviews endanger the reputation of a product. Because of this, it is critical to have a system in place for detecting fraudulent reviews. The goal of this research is to improve the performance of machine learning models that classify fake reviews. In this work Decision tree, Random Forest, Gradient Boosting, AdaBoost, and Bi-LSTM these five machine learning approaches have been implemented to get the best performance on our dataset. Data was collected from the current Bangladesh ride-sharing applications review section. After creating & running the model, Bidirectional Long Short-Term Memory (Bi-LSTM) achieved 85% best model accuracy and 89.0 F1-macro scores with training data rather than other machine learning algorithms.
Review Analysis of Ride-Sharing Applications Using Machine Learning Approaches Bangladesh Perspective
(CRC Press, 2023-01-01) Islam, Taminul; Kundu, Arindom; Lima, Rishalatun Jannat; Hena, Most Hasna; Sharif, Omar; Rahman, Azizur; Hasan, Md Zobaer
Technology and ride-sharing services have become more accessible and convenient as a result of the growth of the Internet. Passengers increasingly focus on digital reviews to help them make purchasing decisions. Online reviews are incredibly inaccurate, as we have seen time and time again. False reviews were created to deceive customers for commercial purposes. A misleading review might have major repercussions for any organization. Organization is focused on providing good feedback to attract passengers and grow the market. It is possible that a bad review of an app would reduce interest in it. These false reviews endanger the reputation of a product. Because of this, it is critical to have a system in place for detecting fraudulent reviews. This research aims to improve the performance of machine learning models that classify fake reviews. This research aims to contribute to the authenticity of reviews using contemporary techniques and the data from ride-sharing apps. This contribution is vital and significant in a country where ride-sharing apps are becoming more convenient and useful. We created a fresh dataset using different apps-based reviews from the current Bangladesh ride-sharing users’ review section. In this work Decision tree, Random Forest, Gradient Boosting, AdaBoost, and Bi-LSTM machine learning approaches were implemented to get the best performance on our dataset. After creating and running the model, Bidirectional Long Short-Term Memory (Bi-LSTM) achieved 85% best accuracy and 85.0 F1 score with training data rather than other machine learning algorithms.