{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,19]],"date-time":"2025-08-19T10:38:09Z","timestamp":1755599889007,"version":"3.41.0"},"publisher-location":"Singapore","reference-count":41,"publisher":"Springer Singapore","isbn-type":[{"type":"print","value":"9789811322020"},{"type":"electronic","value":"9789811322037"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-981-13-2203-7_9","type":"book-chapter","created":{"date-parts":[[2018,9,8]],"date-time":"2018-09-08T10:33:22Z","timestamp":1536402802000},"page":"101-121","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Integration of Big Data: A Survey"],"prefix":"10.1007","author":[{"given":"Jingya","family":"Hui","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lingli","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhaogong","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,9,9]]},"reference":[{"key":"9_CR1","doi-asserted-by":"crossref","unstructured":"Wang, Y., He, Y.: Synthesizing mapping relationships using table corpus, pp. 1117\u20131132. ACM (2017)","DOI":"10.1145\/3035918.3064010"},{"issue":"1","key":"9_CR2","first-page":"22","volume":"16","author":"KW Church","year":"1990","unstructured":"Church, K.W., Hanks, P.: Word association norms, mutual information, and lexicography. Comput. Linguist. 16(1), 22\u201329 (1990)","journal-title":"Comput. Linguist."},{"key":"9_CR3","first-page":"1877","volume":"10","author":"J Chamanara","year":"2017","unstructured":"Chamanara, J., K\u00f6nig-Ries, B., et al.: QUIS: InSitu heterogeneous data source querying. VLDB 10, 1877\u20131880 (2017)","journal-title":"VLDB"},{"key":"9_CR4","first-page":"108","volume":"9","author":"PC Arocena","year":"2015","unstructured":"Arocena, P.C., Glavic, B., Ciucanu, R., et al.: The iBench intergration metadata generator. VLDB 9, 108\u2013119 (2015)","journal-title":"VLDB"},{"key":"9_CR5","doi-asserted-by":"crossref","unstructured":"Hai, R., Geisler, S., Quix,C.: Constance: an intelligent data lake system, pp. 2097\u20132100. ACM (2016)","DOI":"10.1145\/2882903.2899389"},{"issue":"9","key":"9_CR6","first-page":"922","volume":"8","author":"L Wang","year":"2015","unstructured":"Wang, L., et al.: Schema management for document stores. PVLDB 8(9), 922\u2013933 (2015)","journal-title":"PVLDB"},{"key":"9_CR7","doi-asserted-by":"crossref","unstructured":"Kolaitis, P.G., Pichler, R., Sallinger, E., et al.: Nested dependencies: structure and reasoning, pp. 176\u2013187. ACM (2014)","DOI":"10.1145\/2594538.2594544"},{"key":"9_CR8","first-page":"1869","volume":"7","author":"G Konstantinidis","year":"2014","unstructured":"Konstantinidis, G., Ambite, J.L.: Optimizing the chase: scalable data integration under constraints. VLDB 7, 1869\u20131880 (2014)","journal-title":"VLDB"},{"key":"9_CR9","doi-asserted-by":"crossref","unstructured":"Rong, C., Lin, C., Silva, Y.N., et al.: Fast and scalable distributed set similarity joins for big data analytics, pp. 1059\u20131070. IEEE (2017)","DOI":"10.1109\/ICDE.2017.151"},{"key":"9_CR10","doi-asserted-by":"crossref","unstructured":"Vernica, R., Carey, M., Li, C.: Efficient parallel set-similarity joins using MapReduce. In: SIGMOD, pp. 495\u2013506. ACM (2010)","DOI":"10.1145\/1807167.1807222"},{"key":"9_CR11","first-page":"2006","volume":"10","author":"G Li","year":"2017","unstructured":"Li, G.: Human-in-the-loop data integration. VLDB 10, 2006\u20132017 (2017)","journal-title":"VLDB"},{"key":"9_CR12","doi-asserted-by":"crossref","unstructured":"Li, F., Lee, M.L., Hsu, W., et al.: Linking temporal records for profiling entities, pp. 593\u2013605. ACM (2015)","DOI":"10.1145\/2723372.2737789"},{"key":"9_CR13","doi-asserted-by":"crossref","unstructured":"Olteanu, D., Papageorgiou, L., van Schaik, S.J.: \u03a0gora: an integration system for probabilistic data, pp. 1324\u20131327. IEEE (2013)","DOI":"10.1109\/ICDE.2013.6544935"},{"key":"9_CR14","doi-asserted-by":"crossref","unstructured":"Huang, J., Antova, L., Koch, C., Olteanu, D.: MayBMS: a probabilistic database management system. In: SIGMOD (2009)","DOI":"10.1145\/1559845.1559984"},{"issue":"4","key":"9_CR15","first-page":"322","volume":"5","author":"A Kumar","year":"2011","unstructured":"Kumar, A., R\u00e9, C.: Probabilistic management of OCR data using an RDBMS. PVLDB 5(4), 322\u2013333 (2011)","journal-title":"PVLDB"},{"key":"9_CR16","doi-asserted-by":"crossref","unstructured":"Olteanu, D., Huang, J., Koch, C.: Approximate confidence computa- tion in probabilistic databases. In: ICDE (2010)","DOI":"10.1109\/ICDE.2010.5447826"},{"key":"9_CR17","unstructured":"Druzdzel, M.: SMILE: structural modeling, inference, and learning engine and GeNIe: a development environment for graphical decision - theoretic models. In: AIII (1999)"},{"key":"9_CR18","first-page":"336","volume":"9","author":"Z Abedjan","year":"2015","unstructured":"Abedjan, Z., Akcora, C.G., Ouzzani, M., et al.: Temporal rules discovery for web data cleaning. VLDB 9, 336\u2013347 (2015)","journal-title":"VLDB"},{"key":"9_CR19","first-page":"365","volume":"8","author":"B Alexe","year":"2014","unstructured":"Alexe, B., Roth, M., Tan, W.-C.: Preference-aware integration of temporal data. VLDB 8, 365\u2013376 (2014)","journal-title":"VLDB"},{"key":"9_CR20","first-page":"1577","volume":"7","author":"A Petermann","year":"2014","unstructured":"Petermann, A., Junghanns, M., M\u00fcller, R., et al.: Graph-based data integration and business intelligence with BIIIG. VLDB 7, 1577\u20131580 (2014)","journal-title":"VLDB"},{"key":"9_CR21","doi-asserted-by":"crossref","unstructured":"Li, Q., Li, Y., Gao, J., et al.: Resolving conflicts in heterogeneous data by truth discovery and source reliability estimation, pp. 1187\u20131198. ACM (2014)","DOI":"10.1145\/2588555.2610509"},{"key":"9_CR22","first-page":"425","volume":"4","author":"Q Li","year":"2014","unstructured":"Li, Q., Li, Y., Gao, J., et al.: A confidence-aware approach for truth discovery on long-tail data. VLDB 4, 425\u2013436 (2014)","journal-title":"VLDB"},{"key":"9_CR23","doi-asserted-by":"crossref","unstructured":"Joglekar, M., Rekatsinas, T., Garcia-Molina, H., et al.: SLiMFast: guaranteed results for data fusion and source reliability, pp. 1399\u20131414. ACM (2017)","DOI":"10.1145\/3035918.3035951"},{"key":"9_CR24","doi-asserted-by":"crossref","unstructured":"Chen, Y. Chen, L., Zhang, C.J.: CrowdFusion: a crowdsource approach on data fusion refinement, pp. 127\u2013130. IEEE (2017)","DOI":"10.1109\/ICDE.2017.56"},{"key":"9_CR25","doi-asserted-by":"crossref","unstructured":"Pradhan, R., Bykau, S., Prabhakar, S.: Staging user feedback toward rapid conflict resolution in data fusion, pp. 603\u2013618. ACM (2017)","DOI":"10.1145\/3035918.3035941"},{"key":"9_CR26","volume-title":"Articial Intelligence: A Modern Approach","author":"SJ Russell","year":"2003","unstructured":"Russell, S.J., Norvig, P.: Articial Intelligence: A Modern Approach, 2nd edn. Prentice Hall, Upper Saddle River (2003)","edition":"2"},{"issue":"1\u20132","key":"9_CR27","first-page":"1358","volume":"3","author":"XL Dong","year":"2010","unstructured":"Dong, X.L., Berti-Equille, L., Hu, Y., Srivastava, D.: Global detection of complex copying relationships between sources. PVLDB 3(1\u20132), 1358\u20131369 (2010)","journal-title":"PVLDB"},{"issue":"1","key":"9_CR28","first-page":"550","volume":"2","author":"XL Dong","year":"2009","unstructured":"Dong, X.L., Berti-Equille, L., Srivastava, D.: Integrating conflicting data: the role of source dependence. PVLDB 2(1), 550\u2013561 (2009)","journal-title":"PVLDB"},{"key":"9_CR29","doi-asserted-by":"crossref","unstructured":"Pochampally, R., Das Sarma, A., Dong, X.L., et al.: Fusing data with correlations, pp. 433-444. ACM (2014)","DOI":"10.1145\/2588555.2593674"},{"key":"9_CR30","doi-asserted-by":"crossref","unstructured":"Yu, R., Gadiraju, U., Fetahu, B., et al.: FuseM: query-centric data fusion on structured web markup, pp. 179\u2013182. IEEE (2017)","DOI":"10.1109\/ICDE.2017.69"},{"key":"9_CR31","doi-asserted-by":"crossref","unstructured":"Pandey,Y., et al.: Safety check \u2013 a semantic web application for emergency management. ACM (2017)","DOI":"10.1145\/3066911.3066917"},{"issue":"10","key":"9_CR32","doi-asserted-by":"publisher","first-page":"1701","DOI":"10.1016\/j.jss.2010.04.065","volume":"83","author":"V Hristidis","year":"2010","unstructured":"Hristidis, V., et al.: Survey of data management and analysis in disaster situations. J. Syst. Softw. 83(10), 1701\u20131714 (2010)","journal-title":"J. Syst. Softw."},{"key":"9_CR33","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1109\/MIC.2002.1067737","volume":"6","author":"B McBride","year":"2002","unstructured":"McBride, B.: Jena: a semantic web toolkit. IEEE Internet Comput. 6, 55\u201359 (2002)","journal-title":"IEEE Internet Comput."},{"key":"9_CR34","doi-asserted-by":"crossref","unstructured":"Zhang, C., Shin, J., et al.: Extracting databases from dark data with DeepDive, pp. 847\u2013859. ACM (2016)","DOI":"10.1145\/2882903.2904442"},{"key":"9_CR35","doi-asserted-by":"publisher","first-page":"e113523","DOI":"10.1371\/journal.pone.0113523","volume":"9","author":"SE Peters","year":"2014","unstructured":"Peters, S.E., et al.: A machine reading system for assembling synthetic paleontological databases. PloS One 9, e113523 (2014)","journal-title":"PloS One"},{"key":"9_CR36","doi-asserted-by":"crossref","unstructured":"Fernandez, R.C., Deng, D., Mansour, E., et al.: A demo of the data civilizer system, pp. 1639\u20131642. ACM (2017)","DOI":"10.1145\/3035918.3058740"},{"key":"9_CR37","first-page":"133","volume":"7","author":"M Salloum","year":"2014","unstructured":"Salloum, M., Dong, X.L., Srivastava, D., et al.: Online ordering of overlapping data source. VLDB 7, 133\u2013144 (2014)","journal-title":"VLDB"},{"key":"9_CR38","doi-asserted-by":"crossref","unstructured":"Rekatsinas, T., Dong, X.L., Srivastava, D.: Characterizing and selecting fresh data sources, pp. 919\u2013930. ACM (2014)","DOI":"10.1145\/2588555.2610504"},{"key":"9_CR39","first-page":"1513","volume":"9","author":"R Bonaque","year":"2016","unstructured":"Bonaque, R., Cao, T.D., Mendoza, O., et al.: Mixedinstance querying: a lightweight integration architecture for data journalism. VLDB 9, 1513\u20131516 (2016)","journal-title":"VLDB"},{"key":"9_CR40","doi-asserted-by":"crossref","unstructured":"Deshpande, O., Lamba, D.S., Tourn, M., et al.: Building, maintaining, and using knowledge bases: a report from the trenches, pp. 1209\u20131220. ACM (2013)","DOI":"10.1145\/2463676.2465297"},{"key":"9_CR41","first-page":"1577","volume":"9","author":"M Rodr\u00edguez","year":"2016","unstructured":"Rodr\u00edguez, M., Goldberg, S., Wang, D.Z.: SigmaKB: multiple probabilistic knowledge base fusion. VLDB 9, 1577\u20131580 (2016)","journal-title":"VLDB"}],"container-title":["Communications in Computer and Information Science","Data Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-13-2203-7_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,7]],"date-time":"2025-07-07T00:44:21Z","timestamp":1751849061000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-13-2203-7_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9789811322020","9789811322037"],"references-count":41,"URL":"https:\/\/doi.org\/10.1007\/978-981-13-2203-7_9","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"9 September 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPCSEE","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference of Pioneering Computer Scientists, Engineers and Educators","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Zhengzhou","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 September 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 September 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ICPCSEE 2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}