Distance-based Data Cleaning: A Survey (Technical Report)

TL;DR

This survey reviews distance-based data cleaning methods that leverage similarity measures to improve data quality, especially in scenarios with sparse or heterogeneous data, by classifying tasks like error detection and data repair.

Contribution

It provides a comprehensive classification and review of distance-based data cleaning techniques across four main tasks, highlighting their importance and potential for future research.

Findings

Distance-based methods effectively handle data heterogeneity.

Similarity neighbors improve error detection accuracy.

Distance relationships guide data repair processes.

Abstract

With the rapid development of the internet technology, dirty data are commonly observed in various real scenarios, e.g., owing to unreliable sensor reading, transmission and collection from heterogeneous sources. To deal with their negative effects on downstream applications, data cleaning approaches are designed to preprocess the dirty data before conducting applications. The idea of most data cleaning methods is to identify or correct dirty data, referring to the values of their neighbors which share the same information. Unfortunately, owing to data sparsity and heterogeneity, the number of neighbors based on equality relationship is rather limited, especially in the presence of data values with variances. To tackle this problem, distance-based data cleaning approaches propose to consider similarity neighbors based on value distance. By tolerance of small variants, the enriched similarity neighbors can be identified and used for data cleaning tasks. At the same time, distance relationship between tuples is also helpful to guide the data cleaning, which contains more information and includes the equality relationship. Therefore, distance-based technology plays an important role in the data cleaning area, and we also have reason to believe that distance-based data cleaning technology will attract more attention in data preprocessing research in the future. Hence this survey provides a classification of four main data cleaning tasks, i.e., rule profiling, error detection, data repair and data imputation, and comprehensively reviews the state of the art for each class.