A Survey on Data Cleaning Methods in Cyberspace
Jinlin Wang, Hongli Zhang, Binxing Fang, Xing Min Wang, Lin Ye · 2017
Cyberspace offers users and information communication systems the opportunity to interact with each other for business. Data, as the carrier of information, represents the processing content of different business work. In order to improve the quality of data, data cleaning plays an important role in various cyberspace scenarios, such as RFID and sensor, ETL process etc. This paper presents a survey of the art-of-the-state data cleaning methods in cyberspace. According to the characteristics of data cleaning, we extract the relevant key elements of cyberspace to classify the existing works. After elaborating and analyzing each category, we summarize the description and challenges of data cleaning core technologies, such as data quality rules, models and crowdsourcing. Furthermore, we give suggestions for future research on data cleaning in cyberspace from both technology and interactive perspective.