@article{HameedNaumann2020,
  author    = {Hameed, Mazhar and Naumann, Felix},
  title     = {Data Preparation},
  series = {SIGMOD record},
  volume    = {49},
  journal   = {SIGMOD record},
  number    = {3},
  publisher = {Association for Computing Machinery},
  address   = {New York},
  issn      = {0163-5808},
  doi       = {10.1145/3444831.3444835},
  pages     = {18 -- 29},
  year      = {2020},
  abstract  = {Raw data are often messy: they follow different encodings, records are not well structured, values do not adhere to patterns, etc. Such data are in general not fit to be ingested by downstream applications, such as data analytics tools, or even by data management systems. The act of obtaining information from raw data relies on some data preparation process. Data preparation is integral to advanced data analysis and data management, not only for data science but for any data-driven applications. Existing data preparation tools are operational and useful, but there is still room for improvement and optimization. With increasing data volume and its messy nature, the demand for prepared data increases day by day. <br /> To cater to this demand, companies and researchers are developing techniques and tools for data preparation. To better understand the available data preparation systems, we have conducted a survey to investigate (1) prominent data preparation tools, (2) distinctive tool features, (3) the need for preliminary data processing even for these tools and, (4) features and abilities that are still lacking. We conclude with an argument in support of automatic and intelligent data preparation beyond traditional and simplistic techniques.},
  language  = {en}
}
@article{KoumarelasJiangNaumann2020,
  author    = {Koumarelas, Ioannis and Jiang, Lan and Naumann, Felix},
  title     = {Data preparation for duplicate detection},
  series = {Journal of data and information quality : (JDIQ)},
  volume    = {12},
  journal   = {Journal of data and information quality : (JDIQ)},
  number    = {3},
  publisher = {Association for Computing Machinery},
  address   = {New York},
  issn      = {1936-1955},
  doi       = {10.1145/3377878},
  pages     = {24},
  year      = {2020},
  abstract  = {Data errors represent a major issue in most application workflows. Before any important task can take place, a certain data quality has to be guaranteed by eliminating a number of different errors that may appear in data. Typically, most of these errors are fixed with data preparation methods, such as whitespace removal. However, the particular error of duplicate records, where multiple records refer to the same entity, is usually eliminated independently with specialized techniques. Our work is the first to bring these two areas together by applying data preparation operations under a systematic approach prior to performing duplicate detection. <br /> Our process workflow can be summarized as follows: It begins with the user providing as input a sample of the gold standard, the actual dataset, and optionally some constraints to domain-specific data preparations, such as address normalization. The preparation selection operates in two consecutive phases. First, to vastly reduce the search space of ineffective data preparations, decisions are made based on the improvement or worsening of pair similarities. Second, using the remaining data preparations an iterative leave-one-out classification process removes preparations one by one and determines the redundant preparations based on the achieved area under the precision-recall curve (AUC-PR). Using this workflow, we manage to improve the results of duplicate detection up to 19\% in AUC-PR.},
  language  = {en}
}
@phdthesis{Jiang2022,
  author    = {Jiang, Lan},
  title     = {Discovering metadata in data files},
  doi       = {10.25932/publishup-56620},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-566204},
  school      = {Universit{\"a}t Potsdam},
  pages     = {x, ii, 117},
  year      = {2022},
  abstract  = {It is estimated that data scientists spend up to 80\% of the time exploring, cleaning, and transforming their data. A major reason for that expenditure is the lack of knowledge about the used data, which are often from different sources and have heterogeneous structures. As a means to describe various properties of data, metadata can help data scientists understand and prepare their data, saving time for innovative and valuable data analytics. However, metadata do not always exist: some data file formats are not capable of storing them; metadata were deleted for privacy concerns; legacy data may have been produced by systems that were not designed to store and handle meta- data. As data are being produced at an unprecedentedly fast pace and stored in diverse formats, manually creating metadata is not only impractical but also error-prone, demanding automatic approaches for metadata detection. In this thesis, we are focused on detecting metadata in CSV files - a type of plain-text file that, similar to spreadsheets, may contain different types of content at arbitrary positions. We propose a taxonomy of metadata in CSV files and specifically address the discovery of three different metadata: line and cell type, aggregations, and primary keys and foreign keys. Data are organized in an ad-hoc manner in CSV files, and do not follow a fixed structure, which is assumed by common data processing tools. Detecting the structure of such files is a prerequisite of extracting information from them, which can be addressed by detecting the semantic type, such as header, data, derived, or footnote, of each line or each cell. We propose the supervised- learning approach Strudel to detect the type of lines and cells. CSV files may also include aggregations. An aggregation represents the arithmetic relationship between a numeric cell and a set of other numeric cells. Our proposed AggreCol algorithm is capable of detecting aggregations of five arithmetic functions in CSV files. Note that stylistic features, such as font style and cell background color, do not exist in CSV files. Our proposed algorithms address the respective problems by using only content, contextual, and computational features. Storing a relational table is also a common usage of CSV files. Primary keys and foreign keys are important metadata for relational databases, which are usually not present for database instances dumped as plain-text files. We propose the HoPF algorithm to holistically detect both constraints in relational databases. Our approach is capable of distinguishing true primary and foreign keys from a great amount of spurious unique column combinations and inclusion dependencies, which can be detected by state-of-the-art data profiling algorithms.},
  language  = {en}
}