{"id":"https://openalex.org/W1982829723","doi":"https://doi.org/10.1145/1779599.1779603","title":"Extracting user profiles from large scale data","display_name":"Extracting user profiles from large scale data","publication_year":2010,"publication_date":"2010-04-26","ids":{"openalex":"https://openalex.org/W1982829723","doi":"https://doi.org/10.1145/1779599.1779603","mag":"1982829723"},"language":"en","primary_location":{"id":"doi:10.1145/1779599.1779603","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1779599.1779603","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2010 Workshop on Massive Data Analytics on the Cloud","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/A5051536706","display_name":"Michal Shmueli-Scheuer","orcid":"https://orcid.org/0000-0002-6386-8726"},"institutions":[{"id":"https://openalex.org/I4210167297","display_name":"IBM Research - Haifa","ror":"https://ror.org/05rw9t746","country_code":"IL","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210167297"]},{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["IL","US"],"is_corresponding":true,"raw_author_name":"Michal Shmueli-Scheuer","raw_affiliation_strings":["IBM Research, Haifa","IBM Research, Haifa,"],"affiliations":[{"raw_affiliation_string":"IBM Research, Haifa","institution_ids":["https://openalex.org/I4210167297"]},{"raw_affiliation_string":"IBM Research, Haifa,","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071848619","display_name":"Haggai Roitman","orcid":"https://orcid.org/0000-0002-5260-2287"},"institutions":[{"id":"https://openalex.org/I4210167297","display_name":"IBM Research - Haifa","ror":"https://ror.org/05rw9t746","country_code":"IL","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210167297"]},{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["IL","US"],"is_corresponding":false,"raw_author_name":"Haggai Roitman","raw_affiliation_strings":["IBM Research, Haifa","IBM Research, Haifa,"],"affiliations":[{"raw_affiliation_string":"IBM Research, Haifa","institution_ids":["https://openalex.org/I4210167297"]},{"raw_affiliation_string":"IBM Research, Haifa,","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103324615","display_name":"David Carmel","orcid":"https://orcid.org/0000-0003-1161-7084"},"institutions":[{"id":"https://openalex.org/I4210167297","display_name":"IBM Research - Haifa","ror":"https://ror.org/05rw9t746","country_code":"IL","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210167297"]},{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["IL","US"],"is_corresponding":false,"raw_author_name":"David Carmel","raw_affiliation_strings":["IBM Research, Haifa","IBM Research, Haifa,"],"affiliations":[{"raw_affiliation_string":"IBM Research, Haifa","institution_ids":["https://openalex.org/I4210167297"]},{"raw_affiliation_string":"IBM Research, Haifa,","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080909766","display_name":"Yosi Mass","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210167297","display_name":"IBM Research - Haifa","ror":"https://ror.org/05rw9t746","country_code":"IL","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210167297"]}],"countries":["IL","US"],"is_corresponding":false,"raw_author_name":"Yosi Mass","raw_affiliation_strings":["IBM Research, Haifa","IBM Research, Haifa,"],"affiliations":[{"raw_affiliation_string":"IBM Research, Haifa","institution_ids":["https://openalex.org/I4210167297"]},{"raw_affiliation_string":"IBM Research, Haifa,","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083688475","display_name":"David Konopnicki","orcid":null},"institutions":[{"id":"https://openalex.org/I4210167297","display_name":"IBM Research - Haifa","ror":"https://ror.org/05rw9t746","country_code":"IL","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210167297"]},{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["IL","US"],"is_corresponding":false,"raw_author_name":"David Konopnicki","raw_affiliation_strings":["IBM Research, Haifa","IBM Research, Haifa,"],"affiliations":[{"raw_affiliation_string":"IBM Research, Haifa","institution_ids":["https://openalex.org/I4210167297"]},{"raw_affiliation_string":"IBM Research, Haifa,","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5051536706"],"corresponding_institution_ids":["https://openalex.org/I1341412227","https://openalex.org/I4210167297"],"apc_list":null,"apc_paid":null,"fwci":12.1521,"has_fulltext":false,"cited_by_count":34,"citation_normalized_percentile":{"value":0.98287307,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.9979000091552734,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.9979000091552734,"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/T11980","display_name":"Human Mobility and Location-Based Analysis","score":0.9926999807357788,"subfield":{"id":"https://openalex.org/subfields/3313","display_name":"Transportation"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10064","display_name":"Complex Network Analysis Techniques","score":0.9617000222206116,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6577123403549194},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5886653661727905},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.09154275059700012},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.06473532319068909}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6577123403549194},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5886653661727905},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.09154275059700012},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.06473532319068909}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1779599.1779603","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1779599.1779603","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2010 Workshop on Massive Data Analytics on the Cloud","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.472.9919","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.472.9919","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.odu.edu/~mukka/cs775s11/Presentations/papers/shmueli-scheuer.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4000000059604645,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1497613135","https://openalex.org/W1511814458","https://openalex.org/W1532325895","https://openalex.org/W1898592871","https://openalex.org/W1965555277","https://openalex.org/W1974390578","https://openalex.org/W2060204748","https://openalex.org/W2067018993","https://openalex.org/W2079280904","https://openalex.org/W2095976990","https://openalex.org/W2116429057","https://openalex.org/W2130769800","https://openalex.org/W2130900715","https://openalex.org/W2133155002","https://openalex.org/W2151312660"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W2350741829","https://openalex.org/W2530322880","https://openalex.org/W1596801655"],"abstract_inverted_index":{"In":[0],"this":[1],"work":[2],"we":[3,15],"present":[4],"the":[5,27,65],"details":[6],"of":[7,22,29,37,64],"a":[8,33,61],"large":[9,35,41],"scale":[10,42],"user":[11,38,49,54],"profiling":[12,50,55],"framework":[13,51,67],"that":[14],"developed":[16],"here":[17],"in":[18,68],"IBM":[19],"on":[20],"top":[21],"Apache":[23,69],"Hadoop.":[24],"We":[25,44,58],"address":[26],"problem":[28],"extracting":[30],"and":[31,71],"maintaining":[32],"very":[34],"number":[36],"profiles":[39],"from":[40],"data.":[43],"first":[45],"describe":[46,60],"an":[47],"efficient":[48],"with":[52],"high":[53],"quality":[56],"guarantees.":[57],"then":[59],"scalable":[62],"implementation":[63],"proposed":[66],"Hadoop":[70],"discuss":[72],"its":[73],"challenges.":[74]},"counts_by_year":[{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":6}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}