Scholarlink

<p>The accelerating digital transformation across the Arab region has highlighted significant challenges related to the quality, governance, and interoperability of Arabic data—challenges that directly constrain the development of reliable artificial intelligence (AI) applications. Despite the growing availability of Arabic digital content, persistent issues such as linguistic ambiguity, inconsistent data standards, fragmented data ecosystems, and limited cross-sector integration continue to hinder effective data-driven decision-making. Addressing these limitations requires innovative conceptual models that integrate technological, linguistic, and governance dimensions. This study introduces HADQEF, a Hybrid AI Data Quality and Governance Enhancement Framework designed to strengthen the reliability, accessibility, and governance of Arabic datasets through a context-sensitive integration of existing AI techniques, aligned with national digitization goals, particularly Saudi Vision 2030. The framework integrates rule-based mechanisms, machine learning methods, semantic technologies, and governance principles into a unified architecture aimed at diagnosing and mitigating data quality issues. Through a structured analysis of existing Arabic data quality approaches and governance models, the study identifies critical gaps—including the lack of domain-specific quality metrics, insufficient standardization, and limited integration of hybrid AI methods—that motivated the development of HADQEF. The contribution of this work lies in the formulation of a comprehensive and domain-sensitive framework that supports scalable data quality enhancement, governance consistency, and improved readiness of Arabic data for AI-driven applications. The implemented components of the proposed framework indicate empirically observed improvements in Arabic data quality across multiple dimensions, including accuracy, consistency, completeness, and intelligibility, within the evaluated datasets and implemented components. In addition to these empirical findings, the study introduces a governance-aligned framework whose organizational and policy implications are analytically derived to support future empirical governance validation and real-world deployment across governmental and industrial contexts.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

HADQEF: a hybrid AI framework for enhancing Arabic data quality and governance in alignment with Saudi Vision 2030

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年7月15日

查看全文
  • Elham Albaroudi,
  • Mohammad Hatamleh,
  • Taha Mansouri,
  • Ali Alameer

摘要

The accelerating digital transformation across the Arab region has highlighted significant challenges related to the quality, governance, and interoperability of Arabic data—challenges that directly constrain the development of reliable artificial intelligence (AI) applications. Despite the growing availability of Arabic digital content, persistent issues such as linguistic ambiguity, inconsistent data standards, fragmented data ecosystems, and limited cross-sector integration continue to hinder effective data-driven decision-making. Addressing these limitations requires innovative conceptual models that integrate technological, linguistic, and governance dimensions. This study introduces HADQEF, a Hybrid AI Data Quality and Governance Enhancement Framework designed to strengthen the reliability, accessibility, and governance of Arabic datasets through a context-sensitive integration of existing AI techniques, aligned with national digitization goals, particularly Saudi Vision 2030. The framework integrates rule-based mechanisms, machine learning methods, semantic technologies, and governance principles into a unified architecture aimed at diagnosing and mitigating data quality issues. Through a structured analysis of existing Arabic data quality approaches and governance models, the study identifies critical gaps—including the lack of domain-specific quality metrics, insufficient standardization, and limited integration of hybrid AI methods—that motivated the development of HADQEF. The contribution of this work lies in the formulation of a comprehensive and domain-sensitive framework that supports scalable data quality enhancement, governance consistency, and improved readiness of Arabic data for AI-driven applications. The implemented components of the proposed framework indicate empirically observed improvements in Arabic data quality across multiple dimensions, including accuracy, consistency, completeness, and intelligibility, within the evaluated datasets and implemented components. In addition to these empirical findings, the study introduces a governance-aligned framework whose organizational and policy implications are analytically derived to support future empirical governance validation and real-world deployment across governmental and industrial contexts.