publications

Artificial Intelligence (AI) rapidly transforms many areas, including education, healthcare, and daily life. A major dri- ver of this change is Large Language Models(LLMs), pow- erful AI systems capable of understanding and generating human-like text. In this study, we explore how LLMs can support qualitative research in software engineering. Quali- tative research involves analyzing non-numerical data such as interview transcripts or open-ended survey responses to identify patterns and themes. In this study, we focus on a method known as closed coding, where researchers apply predefined codes to the data to systematically identify key ideas. To help LLMs perform close coding, we use prompt engineering, the practice of carefully designing questions or instructions to get accurate and useful responses from the model. Our results show that LLMs can effectively assist with close coding, potentially making qualitative analysis in software engineering faster and more efficient

Large Language Models (LLMs) are increasingly used in software development tasks such as code generation and debugging. This study investigates how developers utilize LLM-generated code and the methods they adopt to address errors within it. Based on a survey of professional developers, we find that while LLMs are commonly used for generating small code snippets with explanations, they often produce incorrect logic, syntax errors, inefficient code, and security vulnerabilities. Developers rely on a mix of traditional debugging techniques, such as print statements and interactive debuggers, and LLMs themselves to correct these issues. Our findings reveal both the potential and the limitations of current LLM tools, highlighting the need for more reliable outputs and better debugging support. This study contributes to the broader understanding of how LLMs are integrated into development workflows and provides direction for future improvements in tool design and developer support systems.

Text summarization involves reducing extensive documents to short sentences that encapsulate the essential ideas. The goal is to create a brief summary that effectively conveys the main points of the original text. We spend a significant amount of time each day reading the newspaper to stay informed about current events both domestically and internationally. While reading newspapers enriches our knowledge, we sometimes come across unnecessary content that isn't particularly relevant to our lives. In this paper, we introduce a neural network model designed to summarize Bangla text into concise and straightforward paragraphs, aiming for greater stability and efficiency.

Over the years, the number of users of social media has increased drastically. People frequently share their thoughts through social platforms, and this leads to an increase in hate content. In this virtual community, individuals share their views, express their feelings, and post photos, videos, blogs, and more. Social networking sites like Facebook and Twitter provide platforms to share vast amounts of content with a single click. However, these platforms do not impose restrictions on the uploaded content, which may include abusive language and explicit images unsuitable for social media. To resolve this issue, a new idea must be implemented to divide the inappropriate content. Numerous studies have been done to automate the process. In this paper, we propose a new Bi-GRU-CNN model to classify whether the text is offensive or not. The combination of the Bi-GRU and CNN models outperforms the existing models.

Texting stands out as the most prominent form of communication worldwide. Individual spend significant amount of time writing whole texts to send emails or write something on social media, which is time consuming in this modern era. Word prediction and sentence completion will be suitable and appropriate in the Bangla language to make textual information easier and more convenient. This paper expands the scope of Bangla language processing by introducing a Bi-LSTM model that effectively handles Bangla next-word prediction and Bangla sentence generation, demonstrating its versatility and potential impact. We proposed a new Bi-LSTM model to predict a following word and complete a sentence. We constructed a corpus dataset from various news portals, including bdnews24, BBC News Bangla, and Prothom Alo. The proposed approach achieved superior results in word prediction, reaching 99% accuracy for both 4- gram and 5-gram word predictions. Moreover, it demonstrated significant improvement over existing methods, achieving 35%, 75%, and 95% accuracy for uni-gram, bi-gram, and tri-gram word prediction, respectively.

The Internet has become an essential tool for people in the modern world. Humans, like all living organisms, have essential requirements for survival. These include access to atmospheric oxygen, potable water, protective shelter, and sustenance. The constant flux of the world is making our existence less complicated. A significant portion of the population utilizes online food ordering services to have meals delivered to their residences. Although there are numerous methods for ordering food, customers sometimes experience disappointment with the food they receive. Our endeavor was to establish a model that could determine if food is of good or poor quality. We compiled an extensive dataset of over 1484 online reviews from prominent food ordering platforms, including Food Panda and HungryNaki. Leveraging the collected data, a rigorous assessment of various deep learning and machine learning techniques was performed to determine the most accurate approach for predicting food quality. Out of all the algorithms evaluated, logistic regression emerged as the most accurate, achieving an impressive 90.91% accuracy. The review offers valuable insights that will guide the user in deciding whether or not to order the food.

Cybersecurity is one of the global issues because of the extensive dependence on cyber systems of individuals, industries, and organizations. Among the cyber attacks, phishing is increasing tremendously and affecting the global economy. Therefore, this phenomenon highlights the vital need for enhancing user awareness and robust support at both individual and organizational levels. Phishing URL identification is the best way to address the problem. Various machine learning and deep learning methods have been proposed to automate the detection of phishing URLs. However, these approaches often need more convincing accuracy and rely on datasets consisting of limited samples. Furthermore, these black-box intelligent models’ decision to detect Suspicious URLs needs proper explanation to understand the features affecting the output. To address the issues, we propose a 1D Convolutional Neural Network (CNN) and trained the model with extensive features and a substantial amount of data. The proposed model outperforms existing works by attaining an accuracy of 99.85%. Additionally, our explainability analysis highlights certain features that significantly contribute to identifying the phishing URL.