{"id":"https://openalex.org/W1979101951","doi":"https://doi.org/10.1145/2588555.2610504","title":"Characterizing and selecting fresh data sources","display_name":"Characterizing and selecting fresh data sources","publication_year":2014,"publication_date":"2014-06-18","ids":{"openalex":"https://openalex.org/W1979101951","doi":"https://doi.org/10.1145/2588555.2610504","mag":"1979101951"},"language":"en","primary_location":{"id":"doi:10.1145/2588555.2610504","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2588555.2610504","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2014 ACM SIGMOD International Conference on Management of Data","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002060759","display_name":"Theodoros Rekatsinas","orcid":"https://orcid.org/0000-0001-6148-1854"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Theodoros Rekatsinas","raw_affiliation_strings":["University of Maryland, College Park, MD, USA"],"affiliations":[{"raw_affiliation_string":"University of Maryland, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001402526","display_name":"Xin Luna Dong","orcid":"https://orcid.org/0009-0000-8667-322X"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xin Luna Dong","raw_affiliation_strings":["Google Inc., Mountainview, CA, USA","Google Inc., Mountainview, CA, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Google Inc., Mountainview, CA, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Inc., Mountainview, CA, USA#TAB#","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088315797","display_name":"Divesh Srivastava","orcid":"https://orcid.org/0000-0002-7609-9217"},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Divesh Srivastava","raw_affiliation_strings":["AT&T Labs-Research, Bedminster, NJ, USA"],"affiliations":[{"raw_affiliation_string":"AT&T Labs-Research, Bedminster, NJ, USA","institution_ids":["https://openalex.org/I1283103587"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5002060759"],"corresponding_institution_ids":["https://openalex.org/I66946132"],"apc_list":null,"apc_paid":null,"fwci":26.9954,"has_fulltext":false,"cited_by_count":59,"citation_normalized_percentile":{"value":0.99448533,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"919","last_page":"930"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.993399977684021,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9872000217437744,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/data-integration","display_name":"Data integration","score":0.8805952072143555},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7423945665359497},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.7265305519104004},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.6235687136650085},{"id":"https://openalex.org/keywords/data-pre-processing","display_name":"Data pre-processing","score":0.5877159833908081},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5116587281227112},{"id":"https://openalex.org/keywords/profit","display_name":"Profit (economics)","score":0.48957952857017517},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.48670151829719543},{"id":"https://openalex.org/keywords/information-integration","display_name":"Information integration","score":0.48418405652046204},{"id":"https://openalex.org/keywords/data-source","display_name":"Data source","score":0.43690967559814453},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3407641053199768},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.30264562368392944},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.1510927379131317},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1331450343132019}],"concepts":[{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.8805952072143555},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7423945665359497},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.7265305519104004},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.6235687136650085},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.5877159833908081},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5116587281227112},{"id":"https://openalex.org/C181622380","wikidata":"https://www.wikidata.org/wiki/Q26911","display_name":"Profit (economics)","level":2,"score":0.48957952857017517},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.48670151829719543},{"id":"https://openalex.org/C33326189","wikidata":"https://www.wikidata.org/wiki/Q17092450","display_name":"Information integration","level":2,"score":0.48418405652046204},{"id":"https://openalex.org/C2983685735","wikidata":"https://www.wikidata.org/wiki/Q5227355","display_name":"Data source","level":2,"score":0.43690967559814453},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3407641053199768},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30264562368392944},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.1510927379131317},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1331450343132019},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2588555.2610504","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2588555.2610504","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2014 ACM SIGMOD International Conference on Management of Data","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.588.6750","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.588.6750","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.research.att.com/export/sites/att_labs/techdocs/TD_101403.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W38194800","https://openalex.org/W203380713","https://openalex.org/W1521736627","https://openalex.org/W1728753295","https://openalex.org/W1979300931","https://openalex.org/W2003684739","https://openalex.org/W2026338082","https://openalex.org/W2026770972","https://openalex.org/W2038378248","https://openalex.org/W2050882265","https://openalex.org/W2086893508","https://openalex.org/W2124170079","https://openalex.org/W2142048776","https://openalex.org/W2157316274","https://openalex.org/W2169585110","https://openalex.org/W2251214202","https://openalex.org/W2288244345","https://openalex.org/W2792631716","https://openalex.org/W4232801011","https://openalex.org/W4293241248","https://openalex.org/W4301885439","https://openalex.org/W6637495128"],"related_works":["https://openalex.org/W2355440778","https://openalex.org/W8795902","https://openalex.org/W2064717691","https://openalex.org/W2381518157","https://openalex.org/W2062592733","https://openalex.org/W2368917030","https://openalex.org/W2207032858","https://openalex.org/W2164160537","https://openalex.org/W2085627709","https://openalex.org/W2150355991"],"abstract_inverted_index":{"Data":[0],"integration":[1,78],"is":[2],"a":[3,54],"challenging":[4],"task":[5],"due":[6],"to":[7,21,75],"the":[8,17,24,34,41,47,58,70,77],"large":[9],"numbers":[10],"of":[11,19,28,36,43,72],"autonomous":[12],"data":[13,73],"sources.":[14],"This":[15],"necessitates":[16],"development":[18],"techniques":[20],"reason":[22],"about":[23],"benefits":[25],"and":[26,30,68],"costs":[27],"acquiring":[29],"integrating":[31],"data.":[32],"Recently":[33],"problem":[35,62],"source":[37],"selection":[38],"(i.e.,":[39],"identifying":[40],"subset":[42],"sources":[44,67],"that":[45],"maximizes":[46],"profit":[48],"from":[49],"integration)":[50],"was":[51,63],"introduced":[52],"as":[53],"preprocessing":[55],"step":[56],"before":[57],"actual":[59],"integration.":[60],"The":[61],"studied":[64],"for":[65],"static":[66],"used":[69],"accuracy":[71],"fusion":[74],"quantify":[76],"profit.":[79]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":10},{"year":2015,"cited_by_count":13},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}