Abstract
Knowledge mining systems are increasingly used to extract actionable insights from large-scale heterogeneous data. However, the reliability of mined knowledge is often questioned due to issues such as data noise, bias, incomplete context, and lack of traceability. Provenance tracking has emerged as a key mechanism to enhance trustworthiness by recording the origin, transformation history, and processing lineage of data and derived knowledge. This paper presents a comprehensive review of trustworthy knowledge mining with provenance tracking, covering conceptual foundations, provenance models, integration architectures, algorithms, and evaluation metrics. We discuss how provenance enables transparency, reproducibility, and accountability in knowledge discovery workflows. The study also examines applications in healthcare, finance, scientific data management, and knowledge graphs. Challenges such as scalability, privacy, and standardization are highlighted, and future research directions are proposed. The paper aims to provide a structured understanding of how provenance-aware mining frameworks can support trustworthy and explainable knowledge extraction in modern data-driven systems.
Keywords: Trustworthy AI, Knowledge Mining, Data Provenance, Explainability, Knowledge Graphs, Data Lineage, Reproducibility, Provenance Models
Full Issue
| View or download the full issue | PDF 54-72 |