A SYSTEMATIC MAPPING REVIEW ON DATA CLEANING METHODS IN BIG DATA ENVIRONMENTS

The evolution of information technology combined with artificial intelligence, IoT (Internet of Things) and robotics has made processes integrated and intelligent. The increased use of technology and the need for evidence-based decisions have contributed to the rapid expansion of a large volume of data in recent years. The quality of data generated mainly by humans must be given special attention, as errors can occur more frequently, making the pre-processing phase, such as data cleaning, a determining factor for better results in data analysis. The aim of this article is therefore to analyze data cleaning methods applied in Big Data environments by conducting a systematic review. The review method was based on the Kitchenham protocol, and the search databases were Scopus, Web of Science and CAPES. After searching and selecting the articles according to the protocol, 69 articles were analyzed, revealing the use of a wide variety of techniques, such as machine learning, data mining, natural language processing and others. The review also emphasized the various publication formats and the wide dissemination and discussion of research on data cleaning in Big Data in the academic community. Finally, this study provides the state of the art of data cleansing techniques that have been used in a Big Data context, offering insights and directions for future research.