{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/121511"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/121511","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"A conceptual model for transparent, reusable, and collaborative data cleaning","abstract":"Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2023-12-04 without embargo terms","abstract_html":"Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2023-12-04 without embargo terms","abstract_has_math":false,"creators":["Parulian, Nikolaus Nova"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"Ph.D.","degree_level":"Dissertation","degree_discipline":"Information Sciences","degree_department":null,"school":null,"contributors":["Ludäscher, Bertram","Downie, John Stephen","Diesner, Jana","Bosch, Nigel"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2023,"date_issued":"2023-08","date_published":"2023-08","updated_at":"2026-07-22T22:25:00Z","subjects":["Data Cleaning","Data Quality","Provenance","Data Preparation","Machine Learning","Artificial Intelligence","Workflows","Metadata","Visualization"],"languages":["en","eng"],"rights":["Copyright 2023 Nikolaus Parulian"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/2142/121511","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Ludäscher, Bertram","Downie, John Stephen","Diesner, Jana","Bosch, Nigel"]},{"key":"dc:creator","label":"Author","values":["Parulian, Nikolaus Nova"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2023-08","2023-07-13"]},{"key":"dc:type","label":"Dc Type","values":["text"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Information Sciences"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Dissertation"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Ph.D."]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Illinois at Urbana-Champaign"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Data Cleaning","Data Quality","Provenance","Data Preparation","Machine Learning","Artificial Intelligence","Workflows","Metadata","Visualization"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en","eng"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2023 Nikolaus Parulian"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://hdl.handle.net/2142/121511"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2023-12-04 without embargo terms","The student, Nikolaus Parulian, accepted the attached license on 2023-07-12 at 12:15.","The student, Nikolaus Parulian, submitted this Dissertation for approval on 2023-07-12 at 12:16.","This Dissertation was approved for publication on 2023-07-13 at 16:25.","DSpace SAF Submission Ingestion Package generated from Vireo submission #19650 on 2023-12-04 at 17:02:16","Data cleaning is an essential component of data preparation in machine learning and other data science workflows. It is a time-consuming and error-prone task that can greatly affect the reliability of subsequent analyses. Tools must capture provenance information to ensure transparent and auditable data-cleaning processes. However, existing provenance models have limitations in tracing and querying changes at different levels of granularity. To address this, we proposed a new conceptual model that captures fine-grained retrospective provenance and extends it with prospective provenance to represent operations or workflows that change the datasets. This hybrid model allows powerful queries and supports advanced use cases like auditing data cleaning workflows. Additionally, we extended the model to present a conceptual model focusing on reusability and collaboration in data cleaning. It addresses scenarios where multiple users contribute to dataset changes and enables tracking of curator actions, identifying dependencies between cleaning operations, and facilitating collaboration. Through an experimental case study, we demonstrated the reusability of data-cleaning workflows, different users' contributions, and collaboration's effectiveness in improving data quality."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["A conceptual model for transparent, reusable, and collaborative data cleaning"]}]}],"canonical_facts":{"dc:contributor":["Ludäscher, Bertram","Downie, John Stephen","Diesner, Jana","Bosch, Nigel"],"dc:creator":["Parulian, Nikolaus Nova"],"dc:date":["2023-08","2023-07-13"],"dc:description":["Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2023-12-04 without embargo terms","The student, Nikolaus Parulian, accepted the attached license on 2023-07-12 at 12:15.","The student, Nikolaus Parulian, submitted this Dissertation for approval on 2023-07-12 at 12:16.","This Dissertation was approved for publication on 2023-07-13 at 16:25.","DSpace SAF Submission Ingestion Package generated from Vireo submission #19650 on 2023-12-04 at 17:02:16","Data cleaning is an essential component of data preparation in machine learning and other data science workflows. It is a time-consuming and error-prone task that can greatly affect the reliability of subsequent analyses. Tools must capture provenance information to ensure transparent and auditable data-cleaning processes. However, existing provenance models have limitations in tracing and querying changes at different levels of granularity. To address this, we proposed a new conceptual model that captures fine-grained retrospective provenance and extends it with prospective provenance to represent operations or workflows that change the datasets. This hybrid model allows powerful queries and supports advanced use cases like auditing data cleaning workflows. Additionally, we extended the model to present a conceptual model focusing on reusability and collaboration in data cleaning. It addresses scenarios where multiple users contribute to dataset changes and enables tracking of curator actions, identifying dependencies between cleaning operations, and facilitating collaboration. Through an experimental case study, we demonstrated the reusability of data-cleaning workflows, different users' contributions, and collaboration's effectiveness in improving data quality."],"dc:format":["application/pdf"],"dc:identifier":["https://hdl.handle.net/2142/121511"],"dc:language":["en","eng"],"dc:rights":["Copyright 2023 Nikolaus Parulian"],"dc:subject":["Data Cleaning","Data Quality","Provenance","Data Preparation","Machine Learning","Artificial Intelligence","Workflows","Metadata","Visualization"],"dc:title":["A conceptual model for transparent, reusable, and collaborative data cleaning"],"dc:type":["text"],"thesis:degree_discipline":["Information Sciences"],"thesis:degree_level":["Dissertation"],"thesis:degree_name":["Ph.D."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:25:00Z"}