Sadia Rahman

Sadia Rahman

Auto-generated profile, based on publicly available information

Sadia Rahman

Department of Computer Science and Engineering, Chittagong University of Engineering and Technology, Chattogram 4349, Bangladesh

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
3 January 2026 in Discover Applied Sciences
Verified
Journal Article
Open access
PDF file
SRSuhana Binta Rashid
Suhana Binta Rashid
Fahmid Al FaridFahmid Al Farid
Fahmid Al Farid
Md. Shafiul Alam ForhadMd. Shafiul Alam Forhad
Md. Shafiul Alam Forhad
SRSadia Rahman
Sadia Rahman
BPBijoy Roy Chowdhury Preenon
Bijoy Roy Chowdhury Preenon
MHMohammad Hasan
Mohammad Hasan
Aggression detection refers to the identification of offensive or harmful expressions in online communications and is crucial due to its significant societal implications and impact on online safety. However, detecting aggression in Bengali texts is particularly challenging due to the language’s complex morphology and the scarcity of annotated datasets and computational tools. Although the task has been extensively studied in high-resource languages, research in the resource-constrained Bengali language remains limited. To address the gap, in this paper, we developed a new dataset BOLT (Bangla Offensive and Lethal Texts) consisting of 4027 annotated instances classified into four classes based on severity of aggression- no aggression, hate speech, vandalism, and atrocity. To optimize model performance, we proposed a modified attention mechanism within transformers. Unlike conventional self-attention, which computes pairwise interactions between all tokens and treats their importance uniformly, our approach introduces a learnable token-wise weight matrix to assess the relevance of each token for aggressive text classification. The attention scores are obtained by multiplying the transformer’s token embeddings with this matrix to generate task-specific weights that better capture contextual significance. Moreover, we utilized a weighted ensemble of the optimized transformer models to combine their individual strengths. Experimental results show that our proposed approach outperforms existing methods and baseline models, achieving both accuracy and weighted F1-score of 87%. Our developed dataset and proposed method pave the way for impactful advancements in Bengali NLP and support content moderation tools and create safer digital platforms through automated aggression detection.

23 September 2025 in Data in Brief
Verified
Journal Article
Open access
SRSuhana Binta Rashid
Suhana Binta Rashid
BPBibhas Roy Chowdhury Piyas
Bibhas Roy Chowdhury Piyas
SRSadia Rahman
Sadia Rahman
BPBijoy Roy Chowdhury Preenon
Bijoy Roy Chowdhury Preenon
The widespread proliferation of religiously aggressive contents on social media platforms poses significant threats to societal harmony and communal solidarity. It often incites religious animosity, provokes violence and disseminates life-threatening messages that intensifies societal divisions and undermines social harmony. Despite significant advancements in identifying such contents in high-resource languages like English, there exists a notable scarcity of resources for regional languages like Bengali which constrains the development of effective detection and prevention tools. To address this gap, we introduce ALERT (Analysis of Linguistic Extremism in Religious Texts), a newly developed Bengali dataset along with English translation which includes 4027 annotated instances classified into four categories: hate speech (995), vandalism (909), atrocity (1117), and no aggression (1006). The dataset was sourced from many online platforms, including Facebook, YouTube, online news websites, blogs and group chats. Each of the instances in the dataset was annotated by any two annotators from the list of four having diverse religious, ethnic, geographical, and academic backgrounds. Any conflicts or disagreements between annotators during the annotation process were resolved through consultation with a domain expert. The preprocessing stages include the elimination of English words, duplication and alphanumeric characters to ensure data integrity. The dataset attains a Cohen’s kappa score of 72 % that signifies a strong inter-annotator agreement and a Jaccard similarity score between 16 % and 23 % which reflects the degree of overlap between classes. Moreover, Experiments with various machine learning, deep learning and transformer-based models yield promising results. ALERT serves as a benchmark dataset for religiously aggressive text classification that may contribute to the advancement of research in this field. The dataset is publicly accessible for research purposes to promote innovation and collaboration within the Bengali NLP community.

11 December 2025 in Data in Brief
Verified
Journal Article
Open access
BPBibhas Roy Chowdhury Piyas
Bibhas Roy Chowdhury Piyas
FTFatama Jannat Tisha
Fatama Jannat Tisha
SRSadia Rahman
Sadia Rahman
SIShahrin Islam
Shahrin Islam
BPBijoy Roy Chowdhury Preenon
Bijoy Roy Chowdhury Preenon
The rapid spread of counterfeit currency threatens global economic stability by undermining public confidence and distorting financial systems. These challenges are particularly severe in cash-dependent economies, where reduced trust in paper currency limits transactions and hinders financial inclusion. Although substantial research exists on banknote recognition and classification, studies specifically targeting counterfeit detection remain limited. The challenges and barriers associated with collecting counterfeit banknotes are a key factor behind the limited resources in this field. To bridge this gap, we present a benchmark dataset named, “JaalTaka”, consisting of 1390 images of Bangladeshi banknotes, including 802 real and 588 counterfeit notes. Due to the subtle differences in security features between real and fake banknotes, six separate images of different segments were captured for each note to highlight these critical elements. Genuine banknotes were obtained from three national banks in Bangladesh, while counterfeit notes were sourced from the Rapid Action Battalion (RAB), a specialized security unit, for research purposes. To ensure robustness, the dataset includes banknotes in diverse conditions including, new, worn, user-marked and stained. This is the first publicly available dataset providing a reliable foundation for developing effective Bangladeshi counterfeit banknote detection systems. The dataset can serve as a benchmark resource for research on counterfeit banknote detection and improving financial security.

5 June 2026 in Data in Brief
Verified
Journal Article
Open access
SIShahrin Islam
Shahrin Islam
BPBibhas Roy Chowdhury Piyas
Bibhas Roy Chowdhury Piyas
FTFatama Jannat Tisha
Fatama Jannat Tisha
HNHumayun Kabir Nayem
Humayun Kabir Nayem
SRSadia Rahman
Sadia Rahman
SHShazzad Hossen
Shazzad Hossen
Career anxiety has become a significant issue in today’s world, particularly in developing countries where job opportunities are scarce compared to the rising number of university graduates. The rapid advancement of artificial intelligence (AI) has heightened this anxiety by reshaping labour markets and automating an increasing number of job roles. Although numerous studies have examined general career anxiety among students, research particularly addressing career anxiety triggered by AI remains scarce. To address this gap, this article presents findings from an online survey conducted across five prominent public and private universities in Bangladesh. The survey examined students’ perceptions of artificial intelligence (AI) and its potential impact on their future careers. A total of 3156 students from various departments and academic years participated in the survey. The study covers students’ knowledge of AI, frequency of AI tool usage and perceptions of AI as a potential threat to their chosen professions and future employment. The dataset also records self-reported levels of career anxiety and strategies students use to prepare for an AI-driven job market. Statistical analyses and visualizations reveal variations of career anxiety across age, gender, academic year, department and AI knowledge level, as well as document the specific AI tools students perceive as potential threats to future employment. The dataset provides meaningful guidance for educators and policymakers in reshaping curriculum to prepare students for new workforce realities. It may also act as a foundation for future research in predictive modelling, labour market analysis, behavioural patterns and human–AI collaboration.


1 June 2026 in IAES International Journal of Artificial Intelligence (IJ-AI)
Verified
Journal Article
Open access
SIShahrin Islam
Shahrin Islam
BPBibhas Roy Chowdhury Piyas
Bibhas Roy Chowdhury Piyas
FTFatama Jannat Tisha
Fatama Jannat Tisha
Abu Saleh Musa MiahAbu Saleh Musa Miah
Abu Saleh Musa Miah
SRSadia Rahman
Sadia Rahman
Md Abdus Samad KamalMd Abdus Samad Kamal
Md Abdus Samad Kamal
The growing sophistication of deepfake technologies has emerged as a critical threat to the credibility of digital media by generating highly realistic yet fabricated visual content. This erodes public trust, elevates security vulnerabilities, and challenges information integrity across online platforms. Despite notable advancements, existing research still suffers from limited data diversity, insufficient model explainability, and inadequate model evaluation. To overcome this limitation, a framework for detecting deepfake video manipulation by using a transfer learning approach was introduced. Each extracted frame was processed by a convolutional neural network (CNN)-based model to obtain frame-level predictions, which were subsequently aggregated to produce the final video-level prediction using a predefined threshold. The publicly available, widely adopted FaceForensics++ dataset was used, which contains high-quality videos generated using advanced manipulation techniques. Various CNN architectures, including Xception, Densenet121, InceptionResNetV2, ResNet50, and EfficientNetB3, were explored along with rigorous hyperparameter tuning. Among these, the Xception architecture outperformed others by achieving a test accuracy of 94.5%. Gradient-weighted class activation mapping (Grad-CAM), generalized gradient-based visual explanations (Grad-CAM++), and Shapley additive explanations (SHAP) were employed to enhance model explainability by visualizing the key regions that influence deepfake detection. The research offers an effective approach to address deepfake threats and safeguard information integrity in contemporary industry 4.0.