{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:51:46Z","timestamp":1761897106927,"version":"3.37.3"},"reference-count":43,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2019,8,21]],"date-time":"2019-08-21T00:00:00Z","timestamp":1566345600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2019,8,21]],"date-time":"2019-08-21T00:00:00Z","timestamp":1566345600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Big Data"],"published-print":{"date-parts":[[2019,12]]},"DOI":"10.1186\/s40537-019-0237-9","type":"journal-article","created":{"date-parts":[[2019,8,21]],"date-time":"2019-08-21T05:02:28Z","timestamp":1566363748000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":15,"title":["VADA: an architecture for end user informed data preparation"],"prefix":"10.1186","volume":"6","author":[{"given":"Nikolaos","family":"Konstantinou","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Edward","family":"Abel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luigi","family":"Bellomarini","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alex","family":"Bogatu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cristina","family":"Civili","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Endri","family":"Irfanie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Martin","family":"Koehler","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lacramioara","family":"Mazilu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Emanuel","family":"Sallinger","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alvaro A. A.","family":"Fernandes","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Georg","family":"Gottlob","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"John A.","family":"Keane","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2008-6617","authenticated-orcid":false,"given":"Norman W.","family":"Paton","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,8,21]]},"reference":[{"key":"237_CR1","volume-title":"Data wrangling with python: tips and tools to make your life easier","author":"J Kazil","year":"2016","unstructured":"Kazil J, Jarmul K. Data wrangling with python: tips and tools to make your life easier. Newton: O\u2019Reilly; 2016."},{"issue":"6","key":"237_CR2","doi-asserted-by":"publisher","first-page":"777","DOI":"10.1007\/s00778-017-0477-2","volume":"26","author":"SMF Ali","year":"2017","unstructured":"Ali SMF, Wrembel R. From conceptual design to performance optimization of ETL workflows: current state of research and open problems. VLDB J. 2017;26(6):777\u2013801. \n                    https:\/\/doi.org\/10.1007\/s00778-017-0477-2\n                    \n                  .","journal-title":"VLDB J."},{"key":"237_CR3","doi-asserted-by":"publisher","unstructured":"Kandel S, Paepcke A, Hellerstein J, Heer J. Wrangler: interactive visual specification of data transformation scripts. Human factors in computing systems. ACM. 2011. p. 3363\u201372: \n                    https:\/\/doi.org\/10.1145\/1978942.1979444\n                    \n                  .","DOI":"10.1145\/1978942.1979444"},{"key":"237_CR4","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1109\/ICDE.2009.208","volume":"23","author":"W Fan","year":"2011","unstructured":"Fan W, Geerts F, Lakshmanan LVS, Xiong M. Discovering conditional functional dependencies. Proc Int Conf Data Eng. 2011;23:5. \n                    https:\/\/doi.org\/10.1109\/ICDE.2009.208\n                    \n                  .","journal-title":"Proc Int Conf Data Eng"},{"issue":"2","key":"237_CR5","doi-asserted-by":"publisher","first-page":"236","DOI":"10.1006\/jcss.2000.1708","volume":"61","author":"S Abiteboul","year":"2000","unstructured":"Abiteboul S, Vianu V, Fordham B, Yesha Y. Relational transducers for electronic commerce. J Comput Syst Sci. 2000;61(2):236\u201369. \n                    https:\/\/doi.org\/10.1006\/jcss.2000.1708\n                    \n                  .","journal-title":"J Comput Syst Sci"},{"issue":"9","key":"237_CR6","doi-asserted-by":"publisher","first-page":"975","DOI":"10.14778\/3213880.3213888","volume":"11","author":"L Bellomarini","year":"2018","unstructured":"Bellomarini L, Sallinger E, Gottlob G. The vadalog system: datalog-based reasoning for knowledge graphs. Proc VLDB Endow. 2018;11(9):975\u201387. \n                    https:\/\/doi.org\/10.14778\/3213880.3213888\n                    \n                  .","journal-title":"Proc VLDB Endow."},{"key":"237_CR7","doi-asserted-by":"publisher","DOI":"10.1002\/9781118644898","volume-title":"Multi-criteria decision analysis: methods and software","author":"A Ishizaka","year":"2013","unstructured":"Ishizaka A, Nemery P. Multi-criteria decision analysis: methods and software. New York: Wiley; 2013."},{"key":"237_CR8","doi-asserted-by":"publisher","unstructured":"Galpin I, Abel E, Paton NW. Source selection languages: a usability evaluation. In: Proceedings of the workshop on human-in-the-loop data analytics, HILDA@SIGMOD, 2018; p. 8\u2013186. \n                    https:\/\/doi.org\/10.1145\/3209900.3209906\n                    \n                  .","DOI":"10.1145\/3209900.3209906"},{"key":"237_CR9","doi-asserted-by":"publisher","unstructured":"Konstantinou N, Koehler M, Abel E, Civili C, Neumayr B, Sallinger E, Fernandes AAA, Gottlob G, Keane JA, Libkin L, Paton NW. The vada architecture for cost-effective data wrangling. In: ACM SIGMOD. SIGMOD \u201917, 2017; p. 1599\u2013602. ACM. \n                    https:\/\/doi.org\/10.1145\/3035918.3058730\n                    \n                  .","DOI":"10.1145\/3035918.3058730"},{"key":"237_CR10","doi-asserted-by":"publisher","unstructured":"Calvanese D, Montali M, De Giacomo G. Foundations of data-aware process analysis: a database theory perspective. ACM PODS. 2013. p. 1\u201312 \n                    https:\/\/doi.org\/10.1145\/2463664.2467796\n                    \n                  .","DOI":"10.1145\/2463664.2467796"},{"key":"237_CR11","doi-asserted-by":"publisher","first-page":"615","DOI":"10.1007\/s00778-013-0323-0","volume":"22","author":"T Furche","year":"2013","unstructured":"Furche T, Gottlob G, Grasso G, Guo X, Orsi G, Schallhart C. The ontological key: automatically understanding and integrating forms to access the deep Web. VLDB J. 2013;22:615\u201340. \n                    https:\/\/doi.org\/10.1007\/s00778-013-0323-0\n                    \n                  .","journal-title":"VLDB J."},{"issue":"14","key":"237_CR12","doi-asserted-by":"publisher","first-page":"1845","DOI":"10.14778\/2733085.2733091","volume":"7","author":"T Furche","year":"2014","unstructured":"Furche T, Gottlob G, Grasso G, Guo X, Orsi G, Schallhart C, Wang C. DIADEM: thousands of websites to a single database. Proc VLDB Endowm. 2014;7(14):1845\u201356.","journal-title":"Proc VLDB Endowm."},{"key":"237_CR13","unstructured":"Tan W-C. Provenance in databases : past , current , and future. In: IEEE data engineering bulletin 2007."},{"issue":"2","key":"237_CR14","doi-asserted-by":"publisher","first-page":"37","DOI":"10.14778\/2535568.2448938","volume":"6","author":"XL Dong","year":"2012","unstructured":"Dong XL, Saha B, Srivastava D. Less is more: selecting sources wisely for integration. Proc VLDB Endowm. 2012;6(2):37\u201348.","journal-title":"Proc VLDB Endowm"},{"key":"237_CR15","doi-asserted-by":"publisher","first-page":"179","DOI":"10.1016\/j.ins.2017.11.019","volume":"430","author":"E Abel","year":"2018","unstructured":"Abel E, Keane J, Paton NW, Fernandes AAA, Koehler M, Konstantinou N, Cortes Rios JC, Azuan NA, Embury SM. User driven multi-criteria source selection. Inform Sci. 2018;430:179\u201399. \n                    https:\/\/doi.org\/10.1016\/j.ins.2017.11.019\n                    \n                  .","journal-title":"Inform Sci"},{"key":"237_CR16","unstructured":"Irfanie ME. Blocking-based matching of data sources. Master\u2019s thesis, University of Manchester 2017."},{"issue":"12","key":"237_CR17","doi-asserted-by":"publisher","first-page":"1860","DOI":"10.14778\/2824032.2824086","volume":"8","author":"T Papenbrock","year":"2015","unstructured":"Papenbrock T, Bergmann T, Finke M, Zwiener J, Naumann F. Data profiling with metanome. Proc VLDB Endowm. 2015;8(12):1860\u20133. \n                    https:\/\/doi.org\/10.14778\/2824032.2824086\n                    \n                  .","journal-title":"Proc VLDB Endowm"},{"key":"237_CR18","unstructured":"Papenbrock T, Naumann F. A hybrid approach for efficient unique column combination discovery. In: BTW, Gesellschaft f\u00fcr Informatik, Bonn 2017. p. 195\u2013204."},{"key":"237_CR19","unstructured":"Kruse S, Papenbrock T, Naumann F. Scaling out the discovery of inclusion dependencies. In: BTW 2015."},{"key":"237_CR20","doi-asserted-by":"publisher","first-page":"701","DOI":"10.1109\/ICSE.2015.227","volume":"2","author":"S Gulwani","year":"2015","unstructured":"Gulwani S, Mayer M, Niksic F, Piskac R. StriSynth: synthesis for live programming. Proc Int Conf Softw Eng. 2015;2:701\u20134. \n                    https:\/\/doi.org\/10.1109\/ICSE.2015.227\n                    \n                  .","journal-title":"Proc Int Conf Softw Eng"},{"key":"237_CR21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1093\/comjnl\/bxy118","volume":"1","author":"A Bogatu","year":"2019","unstructured":"Bogatu A, Paton NW, Fernandes AAA, Koehler M. Towards automatic data format transformations: data wrangling at scale. Comput J. 2019;1:1. \n                    https:\/\/doi.org\/10.1093\/comjnl\/bxy118\n                    \n                  .","journal-title":"Comput J."},{"key":"237_CR22","unstructured":"Wu B, Knoblock CA. An iterative approach to synthesize data transformation programs. In: Proc. IJCAI 2015, 2015; p. 1726\u201332. \n                    http:\/\/ijcai.org\/Abstract\/15\/246\n                    \n                  ."},{"key":"237_CR23","doi-asserted-by":"publisher","unstructured":"Koehler M, Bogatu A, Civili C, Konstantinou N, Abel E, Fernandes AAA, Keane J, Libkin L, Paton NW. Data context informed data wrangling. In: 2017 IEEE big data, 2017; p. 956\u201363. \n                    https:\/\/doi.org\/10.1109\/BigData.2017.8258015\n                    \n                  .","DOI":"10.1109\/BigData.2017.8258015"},{"key":"237_CR24","doi-asserted-by":"publisher","unstructured":"Kruse S, Papotti P, Naumann F. Estimating data integration and cleaning effort. In: EDBT. 2015. p. 61\u201372 \n                    https:\/\/doi.org\/10.5441\/002\/edbt.2015.07\n                    \n                  .","DOI":"10.5441\/002\/edbt.2015.07"},{"issue":"7","key":"237_CR25","doi-asserted-by":"publisher","first-page":"813","DOI":"10.14778\/3192965.3192973","volume":"11","author":"F Nargesian","year":"2018","unstructured":"Nargesian F, Zhu E, Pu KQ, Miller RJ. Table union search on open data. Proc VLDB Endowm. 2018;11(7):813\u201325. \n                    https:\/\/doi.org\/10.14778\/3192965.3192973\n                    \n                  .","journal-title":"Proc VLDB Endowm"},{"key":"237_CR26","doi-asserted-by":"publisher","first-page":"198","DOI":"10.1007\/978-3-642-02463-4_12","volume-title":"Clio: schema mapping creation and data exchange","author":"R Fagin","year":"2009","unstructured":"Fagin R, Haas LM, Hern\u00e1ndez M, Miller RJ, Popa L, Velegrakis Y. Clio: schema mapping creation and data exchange. Berlin: Springer; 2009. p. 198\u2013236. \n                    https:\/\/doi.org\/10.1007\/978-3-642-02463-4_12\n                    \n                  ."},{"key":"237_CR27","doi-asserted-by":"crossref","unstructured":"Marnette B, Mecca G, Papotti P, Raunich S, Santoro D. ++ Spicy: an OpenSource Tool for second-generation schema mapping and data exchange. In: Proceedings of the VLDB endowment. 2011. p. 1438\u201341.","DOI":"10.14778\/3402755.3402790"},{"issue":"9","key":"237_CR28","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1145\/1378727.1378745","volume":"51","author":"PA Bernstein","year":"2008","unstructured":"Bernstein PA, Haas LM. Information integration in the enterprise. Commun ACM. 2008;51(9):72\u20139. \n                    https:\/\/doi.org\/10.1145\/1378727.1378745\n                    \n                  .","journal-title":"Commun ACM"},{"key":"237_CR29","doi-asserted-by":"publisher","unstructured":"Khayyat Z, Ilyas IF, Madden S, Ouzzani M, Papotti P, Quian\u00e9-Ruiz J-A, Tang N, Yin S. BigDansing : a system for big data cleansing. In: SIGMOD. 2015. \n                    https:\/\/doi.org\/10.1145\/2723372.2747646\n                    \n                  .","DOI":"10.1145\/2723372.2747646"},{"key":"237_CR30","doi-asserted-by":"crossref","unstructured":"Dallachiesa M, Elmagarmid A, Ilyas IF, Tang N. NADEEF : a commodity data cleaning system categories and subject descriptors. In: SIGMOD. 2013.","DOI":"10.1145\/2463676.2465327"},{"issue":"9","key":"237_CR31","doi-asserted-by":"publisher","first-page":"625","DOI":"10.14778\/2536360.2536363","volume":"6","author":"F Geerts","year":"2013","unstructured":"Geerts F, Mecca G, Papotti P, Santoro D. The LLUNATIC data-cleaning framework. Proc VLDB Endowm. 2013;6(9):625\u201336.","journal-title":"Proc VLDB Endowm"},{"issue":"3","key":"237_CR32","doi-asserted-by":"publisher","first-page":"1","DOI":"10.4018\/jdwm.2009070101","volume":"5","author":"P Vassiliadis","year":"2009","unstructured":"Vassiliadis P. A survey of extract\u2013transform\u2013load technology. Int J Data Wareh Mining. 2009;5(3):1\u201327. \n                    https:\/\/doi.org\/10.4018\/jdwm.2009070101\n                    \n                  .","journal-title":"Int J Data Wareh Mining"},{"key":"237_CR33","doi-asserted-by":"publisher","unstructured":"Aumueller D, Do H-H, Massmann S, Rahm E. COMA++ - Schema and ontology matching with COMA. In: ACM SIGMOD. 2005. \n                    https:\/\/doi.org\/10.1145\/1066157.1066283\n                    \n                  .","DOI":"10.1145\/1066157.1066283"},{"key":"237_CR34","doi-asserted-by":"publisher","unstructured":"Morcos J, Abedjan Z, Ilyas IF, Ouzzani M, Papotti P, Stonebraker M. DataXFormer: an interactive data transformation tool. In: ACM SIGMOD. 2015. p. 883\u201388 \n                    https:\/\/doi.org\/10.1145\/2723372.2735366\n                    \n                  .","DOI":"10.1145\/2723372.2735366"},{"issue":"1","key":"237_CR35","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10115-017-1057-x","volume":"53","author":"V Crescenzi","year":"2017","unstructured":"Crescenzi V, Fernandes AAA, Merialdo P, Paton NW. Crowdsourcing for data management. Knowl Inf Syst. 2017;53(1):1\u201341. \n                    https:\/\/doi.org\/10.1007\/s10115-017-1057-x\n                    \n                  .","journal-title":"Knowl Inf Syst"},{"issue":"9","key":"237_CR36","doi-asserted-by":"publisher","first-page":"2296","DOI":"10.1109\/TKDE.2016.2535242","volume":"28","author":"G Li","year":"2016","unstructured":"Li G, Wang J, Zheng Y, Franklin MJ. Crowdsourced data management: a survey. IEEE Trans Knowl Data Eng. 2016;28(9):2296\u2013319. \n                    https:\/\/doi.org\/10.1109\/TKDE.2016.2535242\n                    \n                  .","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"237_CR37","unstructured":"Stonebraker M, Bruckner D, Ilyas I. Data curation at scale: the data tamer system. Cidr. 2013. 10.1.1.302.8817."},{"key":"237_CR38","unstructured":"Deng D, Castro R, Ziawasch F, Sibo A, Elmagarmid A, Ilyas IF, Madden S, Ouzzani M, Tang N. The data civilizer system. Cidr 2017."},{"key":"237_CR39","unstructured":"Fernandez RC, Deng D, Mansour E, Qahtan AA, Tao W, Abedjan Z, Elmagarmid AK, Ilyas IF, Madden S, Ouzzani M, Stonebraker M, Tang N. A demo of the data civilizer system. In: ACM SIGMOD, 2017. p. 1639\u201342."},{"key":"237_CR40","doi-asserted-by":"crossref","unstructured":"Mansour E, Deng D, Fernandez RC, Qahtan AA, Tao W, Abedjan Z, Elmagarmid AK, Ilyas IF, Madden S, Ouzzani M, Stonebraker M, Tang N. Building data civilizer pipelines with an advanced workflow engine. In: IEEE ICDE, 2018. p. 1593\u20136.","DOI":"10.1109\/ICDE.2018.00184"},{"key":"237_CR41","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1186\/s40537-018-0123-x","volume":"5","author":"H Alrehamy","year":"2018","unstructured":"Alrehamy H, Walker C. Semlinker: automating big data integration for casual users. J Big Data. 2018;5:14. \n                    https:\/\/doi.org\/10.1186\/s40537-018-0123-x\n                    \n                  .","journal-title":"J Big Data."},{"issue":"1","key":"237_CR42","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1007\/s00778-012-0286-6","volume":"22","author":"T Furche","year":"2013","unstructured":"Furche T, Gottlob G, Grasso G, Schallhart C, Sellers A. Oxpath: a language for scalable data extraction, automation, and crawling on the deep web. VLDB J. 2013;22(1):47\u201372. \n                    https:\/\/doi.org\/10.1007\/s00778-012-0286-6\n                    \n                  .","journal-title":"VLDB J"},{"issue":"12","key":"237_CR43","doi-asserted-by":"publisher","first-page":"1996","DOI":"10.14778\/2824032.2824120","volume":"8","author":"S Ortona","year":"2015","unstructured":"Ortona S, Orsi G, Buoncristiano M, Furche T, Matematica D, Economia I. WADaR : joint wrapper and data repair. Proc VLDB Endowm. 2015;8(12):1996\u20139. \n                    https:\/\/doi.org\/10.14778\/2824032.2824120\n                    \n                  .","journal-title":"Proc VLDB Endowm"}],"container-title":["Journal of Big Data"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s40537-019-0237-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1186\/s40537-019-0237-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s40537-019-0237-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,19]],"date-time":"2020-08-19T23:07:55Z","timestamp":1597878475000},"score":1,"resource":{"primary":{"URL":"https:\/\/journalofbigdata.springeropen.com\/articles\/10.1186\/s40537-019-0237-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,8,21]]},"references-count":43,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2019,12]]}},"alternative-id":["237"],"URL":"https:\/\/doi.org\/10.1186\/s40537-019-0237-9","relation":{},"ISSN":["2196-1115"],"issn-type":[{"type":"electronic","value":"2196-1115"}],"subject":[],"published":{"date-parts":[[2019,8,21]]},"assertion":[{"value":"30 April 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 August 2019","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 August 2019","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare that they have no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"74"}}