Islam and Data Science Roundup

In “Beyond Gender, Number, and Rationality: Modeling Extended Arabic Morpho-Syntactic Agreement with Aggregation” (ACL Anthology), Bailasan Zaina (Georgetown University) and others observe that “Arabic gender–number morpho-syntactic agreement exhibits systematic variation beyond functional gender, number, and rationality (GNR) (Alkuhlani and Habash, 2011). [They] identify and classify agreement patterns involving plural-to-unit and unit-to-members shifts, and introduce aggregation… CONTINUE READING

Islam and Data Science Roundup

In “IsnadGuard: Detecting Fabricated Chains of Narration in Hadith Transmission Networks” (Open Review), Ghaleb Aldoboni (Mohamed bin Zayed University University of Artificial Intelligence) and others “study a focused task: detecting and localizing fabricated chains from the narrator-transmission structure alone. Using Sanadset 650K, [they] construct a directed narrator graph and generate corruptions grounded in classical defect… CONTINUE READING

Islam and Data Science Roundup

In “Just the Two of Us: Italian Qurʾan Translations Synopsis and a Computational Framework for a Fine-Grained Lexical Dispersion through Multilingual Embeddings” (Islam in History), Riccardo Amerigo Vigliermo (University of Modena and Reggio Emilia) “proposes a set of artificial intelligence and machine learning applications grounded in a human-curated synopsis of Italian Qurʾan translations conceived as… CONTINUE READING

Islam and Data Science Roundup

In “The Limits and Potential of Artificial Intelligence in Studying Hadith Defects (‘Ilal) and Reconciling Conflicting Narrations (Mukhtalif)” (Bulletin of the Faculty of Islamic and Arabic Studies for Girls in Alexandria), Sumaya Ali Ahmed Laban (Qassim University) concludes that artificial intelligence should be considered “merely as a ‘desk assistant and research secretary; for drafting and… CONTINUE READING

Islam and Data Science Roundup

In “ILM: An AI-Powered Storytelling Educational Tool,” Suhaila Mohammed (McMaster University) and others “present ILM, an interactive educational platform for Stories of the Prophets that combines Arabic natural language processing, structured knowledge representation, and retrieval-based question generation.”

Islam and Data Science Roundup

In “Beyond Keywords: AI-Mediated Access to the Islam West Africa Collection through an MCP Server and Agent Skill” (Eighth Conference on Digital Humanities and Digital History), Frédérick Madore (University of Bayreuth) observes that “over the past two years, AI has transformed the development of the Islam West Africa Collection (IWAC), an open-access database of over… CONTINUE READING

Islam and Data Science Roundup

In “Introducing Text Evaluation using LabelStudio” (KitLab) Mathew Barber (Aga Khan University’s Institute for the Study of Muslim Civilisations) and Peter Verkinderen (Aga Khan University’s Institute for the Study of Muslim Civilisations) introduce the KITAB-Transform project focused on “training language models to identify ‘transformative’ text reuse (such as paraphrase and translation) in the OpenITI corpus.”… CONTINUE READING

Islam and Data Science Roundup

In “Digital Eschatology in Islamicate Traditions: a Comparative Study of Inter-Religious Prophecies” (Journal of Digital Islamicate Research), Mohammed Qasim Khan (University of Malaya) suggests that “AI-produced religious texts tend to support conventional theological doctrines and, at the same time, allow the emergence of novel links between Islamic, Christian and Jewish apocalypticism.” [login required] In “Artificial… CONTINUE READING

Islam and Data Science Roundup

In “YallaMorph: A Benchmark for Evaluating Arabic Morphological Generation in Large Language Models” (ArXiv), Mahmoud Reda (New York University Abu Dhabi) and others debut “YallaMorph, a large-scale benchmark for Arabic morphological generation covering verbs, nouns, adjectives, their cliticized forms, and invalid configurations.… [The] results show that Arabic morphological generation remains difficult, especially for cliticized, unseen,… CONTINUE READING

Islam and Data Science Roundup

In “The Disruption of Islamic Religious Education Curricula in the Artificial Intelligence Era and the Problem of Intolerance Among Modern Multicultural Students” (Jurnal Hasil Penelitian dan Pengabdian Masyarakat), Robiatul Adawiyah (University of Indonesia) and others conclude that, “AI disruption has transformed the PAI [Islamic Religious Education] learning paradigm into a more digital, flexible, and interactive… CONTINUE READING