​

Abstract: Water pollution poses a severe threatto ecological integrity, humanhealth, and sustainable development globally.With the exponential growth of data from diverse sources such as remote sensing, environmental monitoring sensors,andcomputational models, big data has emerged as a transformative tool to address water pollution challenges. By using a new Bibliometrics and Text Mining tool (LitTopicMiner), this review synthesizes recentacademic literature (1995-2025)to explorehow big data analytics, including machine learning, remote sensing, and integrated modeling, enhances water pollution monitoring, source identification, risk assessment, and mitigation strategies. The findings highlight the multifacetedapplications of big data in improving the accuracyof pollutantdetection, optimizingpollution controlmeasures, and supporting evidence-based decision-making. Additionally, the review discusses currentlimitations and future directions for leveraging bigdata to achieve more effective water pollution reduction.

 

Keywords: Water pollution; Big data; Bibliometrics; Text Mining