October 30 ~ 31, 2025, Virtual Conference
Taimur Khan, Ramoza Ahsan, and Mohib Hameed, Department of Data Science and Artificial Intelligence, FAST National University of Computer and Emerging Science (FAST-NUCES), Islamabad, Pakistan
Story understanding and analysis have been a challenging domain of Natural Language Understanding. The need for automated narrative analysis demands deep computational semantic captures, along with the syntactic analysis of the text. Moreover, a large amount of narrative data requires automated semantic analysis and computational learning rather than manual approaches to the analytical tasks. In this paper, we propose a framework that analyzes the sentiment arcs of movie scripts and performs an extended analysis regarding the context of the characters involved in the movie. The framework enables us to extract high and low concepts being delivered through the narrative. Using the methodologies of dictionary-based sentiment analysis, our proposed framework proceeded with a custom lexicon based sentiment analysis using LabMTsimple storylab module. The custom lexicon is based upon the Valence, Arousal, and Dominance scores (NRC-VAD lexicon). Furthermore, the framework advances the analysis by clustering similar sentiment plots using Ward’s hierarchical clustering technique. Our experimental evaluation using movie dataset demonstrates that the retrieved analysis is helpful to consumers and readers during the selection of a Narrative/Story.
Sentiment Analysis, Story Analysis, Natural Language Processing, Information Retrieval.
Zahiduzzaman Zahid1, Mohammad Enayet Hossain2, Basharat Ali Khan Mohammed3, 1University of the Cumberlands, USA, 2International Islamic University Malaysia, Malaysia, 3Campbellsville University, KY 42718, USA
This paper explores the integration of Green Artificial Intelligence (AI)—AI designed for energy efficiency and minimal environmental impact—with Islamic finance to advance sustainable resource management. Islamic finance, grounded in ethical principles such as justice, risk-sharing, and the prohibition of riba (interest), manages over $3.5 trillion in global assets as of 2024 (Islamic Financial Services Board, 2024). However, its potential to address environmental sustainability remains underexplored. Green AI offers a solution by optimizing resource allocation in sectors critical to Muslim-majority economies, such as agriculture and renewable energy, while aligning with Maqasid al-Shariah (objectives of Islamic law), including hifz al-bi'ah (environmental preservation). Using a mixed-methods approach with case studies from the Middle East and Southeast Asia, we propose a novel framework that embeds Green AI into Sharia-compliant financial tools, demonstrating potential carbon emission reductions of up to 30% in optimized sukuk portfolios. This research contributes to theory by extending Maqasid al-Shariah to ecological stewardship, to practice by providing actionable AI models for Islamic banks, and to policy by recommending regulatory incentives for Green AI adoption. Our findings pave the way for mobilizing sustainable investments, bridging ethical finance with environmental sustainability.
Green AI, Islamic finance, sustainable resource management, ethical finance, environmental sustainability, Maqasid al-Shariah, financial innovation
Prakhar Rai, IIT GUWAHATI, India
The integration of Natural Language Processing (NLP), Artificial Intelligence (AI), and Information Retrieval (IR) has reached a pivotal stage where semantic understanding, contextual embeddings, and reasoning over heterogeneous data modalities must converge. Building upon recent advances in tensor-based semantic fusion and neuro-symbolic hyperdimensional architectures, this paper proposes a unified research framework that advances both theoretical mathematics and practical algorithmic design. We introduce two novel algorithms specifically developed for this paper: (1) the Quantum Topos Graph Embedding (QTGE) algorithm, which blends category theory, tensor decomposition, and quantum-inspired annealing for semantic retrieval; and (2) the Stochastic Hyperdimensional Reasoning Network (SHRN), a diffusion-driven architecture that exploits measure-valued stochastic processes for adaptive contextual reasoning. These contributions are integrated with prior state-of-the-art methods, including the Semantic Contextual Embedding Fusion (SCEF), Dynamic Knowledge Graph Reasoning (DKGR), SheafTheoretic Hyperdimensional Encoding (SHE), and Quantum-Inspired Differentiable Reasoning (QIDR), to form a multi-layered architecture for next-generation NLP and IR. Rigorous mathematical formulations are provided, including tensor algebra, tropical algebra, non-commutative geometry, stochastic analysis, and probabilistic inference. The resulting framework achieves strong theoretical guarantees, expanded expressivity, and enhanced empirical performance in tasks such as cross-modal retrieval, question answering, and semantic search.
Natural Language Processing, Artificial Intelligence, Information Retrieval, Tensor
Mohammad Saiduzzaman1, Md. Mehedi Morshed2, Farhana Afroz3, Zahiduzzaman Zahid4, 1Ministry of Textile & Jute, Dhaka, Bangladesh,2Ministry of Local Government, Bangladesh, 3Rupali Bank PLC, Dhaka, Bangladesh, 4University of the Cumberlands, Kentucky, USA
This research explores the potential of integrating digital e-learning and AI-driven tools to empower Bangladesh's Imams, Muazzins, and rural farmers. The study investigates how equipping religious leaders with agricultural knowledge and digital skills can improve agricultural productivity, enhance market access, and promote sustainable farming practices in rural communities. This model aims to foster economic resilience, reduce poverty, and promote socio-economic equality in rural Bangladesh by addressing the digital literacy gap. Despite significant barriers such as poor infrastructure, digital illiteracy, and resistance to new technologies, the study identifies several opportunities for scaling this model, including expanding mobile networks, increasing smartphone usage, and partnerships with NGOs, government agencies, and tech companies. The research highlights the role of Imams and Muazzins as potential mentors and advocates for change, bridging the gap between technology and rural communities. The findings suggest that integrating AI tools in agriculture can significantly improve farming practices and enhance economic stability for rural populations.
Digital E-learning, AI in Agriculture, Rural Development, Imams, Muazzins, Digital Literacy, Sustainable Farming, Bangladesh, Agricultural Entrepreneurship, Socio-economic Empowerment
Youssef Alothman, Lalit Maurya & Mohamed Bader-El-Den, Computer science /University of Portsmouth, Portsmouth, United Kingdom
We introduce SemCom-Synth, a privacy-preserving synthetic corpus of semiconductor operations text produced by a dual-track pipeline: a language model trained with DP-SGD and a privacy-aware paraphraser. A risk-aware hybrid selector enforces k-syntheticity (string/edit and embedding distances), layered PII/domain-jargon redaction, and canary audits before release. Utility is assessed with Train-on-Synthetic, Test-on-Real (TSTR) across five tasks—root-cause taxonomy, actionability, role/shift, severity, and fault-span extraction—reporting macro-F1, macro-recall, AUROC, calibration (ECE), and asymmetric cost curves. We chart the privacy–utility frontier across ε∈{1,2,4,8} (δ≈10⁻⁵) and show that ≤10% few-shot fine-tuning on real text closes most of the remaining gap to full-real baselines. We release dataset shards, prompts, cards (Data/Privacy/Model), and an open audit harness (membership inference, nearest-neighbor, canary) to support reproducible assessment and safe reuse.
Differential Privacy; Synthetic Text; Semiconductor Manufacturing; Root Cause Analysis; Benchmarking; Membership Inference.