{"id":"https://openalex.org/W2161785519","doi":"https://doi.org/10.1109/isi.2011.5984780","title":"heteroHarvest: Harvesting information from heterogeneous sources","display_name":"heteroHarvest: Harvesting information from heterogeneous sources","publication_year":2011,"publication_date":"2011-07-01","ids":{"openalex":"https://openalex.org/W2161785519","doi":"https://doi.org/10.1109/isi.2011.5984780","mag":"2161785519"},"language":"en","primary_location":{"id":"doi:10.1109/isi.2011.5984780","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isi.2011.5984780","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of 2011 IEEE International Conference on Intelligence and Security Informatics","raw_type":"proceedings-article"},"type":"conference-paper","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/A5075172632","display_name":"Pir Abdul Rasool Qureshi","orcid":null},"institutions":[{"id":"https://openalex.org/I177969490","display_name":"University of Southern Denmark","ror":"https://ror.org/03yrrjy16","country_code":"DK","type":"education","lineage":["https://openalex.org/I177969490"]},{"id":"https://openalex.org/I184886455","display_name":"Maersk (Denmark)","ror":"https://ror.org/046gbzb64","country_code":"DK","type":"company","lineage":["https://openalex.org/I184886455"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Pir Abdul Rasool Qureshi","raw_affiliation_strings":["The Maersk Mc-Kinney Moller Institute, University of Southern Denmark, Odense, Denmark","Maersk Mc-Kinney Moller Institute, University of Southern Denmark, Odense, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Maersk Mc-Kinney Moller Institute, University of Southern Denmark, Odense, Denmark","institution_ids":["https://openalex.org/I177969490","https://openalex.org/I184886455"]},{"raw_affiliation_string":"Maersk Mc-Kinney Moller Institute, University of Southern Denmark, Odense, Denmark","institution_ids":["https://openalex.org/I177969490","https://openalex.org/I184886455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041548828","display_name":"Nasrullah Memon","orcid":"https://orcid.org/0000-0001-9667-2490"},"institutions":[{"id":"https://openalex.org/I177969490","display_name":"University of Southern Denmark","ror":"https://ror.org/03yrrjy16","country_code":"DK","type":"education","lineage":["https://openalex.org/I177969490"]},{"id":"https://openalex.org/I184886455","display_name":"Maersk (Denmark)","ror":"https://ror.org/046gbzb64","country_code":"DK","type":"company","lineage":["https://openalex.org/I184886455"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Nasrullah Memon","raw_affiliation_strings":["The Maersk Mc-Kinney Moller Institute, University of Southern Denmark, Odense, Denmark","Syddansk Universitet, Odense, Syddanmark, DK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Maersk Mc-Kinney Moller Institute, University of Southern Denmark, Odense, Denmark","institution_ids":["https://openalex.org/I177969490","https://openalex.org/I184886455"]},{"raw_affiliation_string":"Syddansk Universitet, Odense, Syddanmark, DK","institution_ids":["https://openalex.org/I177969490"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089302640","display_name":"Uffe Kock Wiil","orcid":"https://orcid.org/0000-0001-6898-4083"},"institutions":[{"id":"https://openalex.org/I177969490","display_name":"University of Southern Denmark","ror":"https://ror.org/03yrrjy16","country_code":"DK","type":"education","lineage":["https://openalex.org/I177969490"]},{"id":"https://openalex.org/I184886455","display_name":"Maersk (Denmark)","ror":"https://ror.org/046gbzb64","country_code":"DK","type":"company","lineage":["https://openalex.org/I184886455"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Uffe Kock Wiil","raw_affiliation_strings":["The Maersk Mc-Kinney Moller Institute, University of Southern Denmark, Odense, Denmark","Maersk Mc-Kinney Moller Institute, University of Southern Denmark, Odense, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Maersk Mc-Kinney Moller Institute, University of Southern Denmark, Odense, Denmark","institution_ids":["https://openalex.org/I177969490","https://openalex.org/I184886455"]},{"raw_affiliation_string":"Maersk Mc-Kinney Moller Institute, University of Southern Denmark, Odense, Denmark","institution_ids":["https://openalex.org/I177969490","https://openalex.org/I184886455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034281379","display_name":"Panagiotis Karampelas","orcid":"https://orcid.org/0000-0003-1684-7612"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Panagiotis Karampelas","raw_affiliation_strings":["Hellenic American University, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hellenic American University, Greece","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080860685","display_name":"Jose Ignacio Nieto Sancheze","orcid":null},"institutions":[{"id":"https://openalex.org/I177969490","display_name":"University of Southern Denmark","ror":"https://ror.org/03yrrjy16","country_code":"DK","type":"education","lineage":["https://openalex.org/I177969490"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Jose Ignacio Nieto Sancheze","raw_affiliation_strings":["University of Southern Denmark, Odense, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern Denmark, Odense, Denmark","institution_ids":["https://openalex.org/I177969490"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.25445216,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"231","last_page":"231"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9991999864578247,"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":0.9991999864578247,"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/T12607","display_name":"Personal Information Management and User Behavior","score":0.9958999752998352,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"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/T10742","display_name":"Peer-to-Peer Network Technologies","score":0.9945999979972839,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/computer-science","display_name":"Computer science","score":0.8465713858604431},{"id":"https://openalex.org/keywords/hypertext","display_name":"Hypertext","score":0.6270278692245483},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.6083402633666992},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5517992377281189},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.49397164583206177},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.485720694065094},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.467781662940979},{"id":"https://openalex.org/keywords/information-filtering-system","display_name":"Information filtering system","score":0.44126033782958984},{"id":"https://openalex.org/keywords/information-resource","display_name":"Information resource","score":0.4334626793861389},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3722665011882782},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.35233259201049805},{"id":"https://openalex.org/keywords/knowledge-management","display_name":"Knowledge management","score":0.13234436511993408},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.08871227502822876}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8465713858604431},{"id":"https://openalex.org/C162215914","wikidata":"https://www.wikidata.org/wiki/Q93241","display_name":"Hypertext","level":2,"score":0.6270278692245483},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.6083402633666992},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5517992377281189},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.49397164583206177},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.485720694065094},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.467781662940979},{"id":"https://openalex.org/C178674793","wikidata":"https://www.wikidata.org/wiki/Q6031077","display_name":"Information filtering system","level":2,"score":0.44126033782958984},{"id":"https://openalex.org/C3017942907","wikidata":"https://www.wikidata.org/wiki/Q16797616","display_name":"Information resource","level":2,"score":0.4334626793861389},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3722665011882782},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35233259201049805},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.13234436511993408},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.08871227502822876},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/isi.2011.5984780","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isi.2011.5984780","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of 2011 IEEE International Conference on Intelligence and Security Informatics","raw_type":"proceedings-article"},{"id":"pmh:oai:sdu.dk:openaire_cris_publications/13d4da60-4cd0-419a-ae80-4170223a5b87","is_oa":false,"landing_page_url":"https://portal.findresearcher.sdu.dk/da/publications/13d4da60-4cd0-419a-ae80-4170223a5b87","pdf_url":null,"source":{"id":"https://openalex.org/S4306400423","display_name":"University of Southern Denmark Research Portal (University of Southern Denmark)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I177969490","host_organization_name":"University of Southern Denmark","host_organization_lineage":["https://openalex.org/I177969490"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Qureshi, P A R, Memon, N, Wiil, U K, Karampelas, P & Sanchez, J I N 2011, heteroHarvest: Harvesting Information from Heterogeneous Sources. in IEEE Intelligence and Security Informatics Conference 2011 (IEEE ISI 2011). IEEE, pp. 231-231.","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W256861921","https://openalex.org/W2005562532","https://openalex.org/W6609691951"],"related_works":["https://openalex.org/W2391903610","https://openalex.org/W2387606565","https://openalex.org/W1004067228","https://openalex.org/W2354890392","https://openalex.org/W2386856507","https://openalex.org/W2099413755","https://openalex.org/W2389191773","https://openalex.org/W2375697679","https://openalex.org/W2367771667","https://openalex.org/W2361617952"],"abstract_inverted_index":{"The":[0,119],"abundance":[1],"of":[2,30,42,52,116],"information":[3,31,37,55,75,83,99,104],"regarding":[4],"any":[5],"topic":[6],"makes":[7,69],"the":[8,17,28,34,40,45,48,53,97,103,114],"Internet":[9,18],"a":[10,106],"very":[11,20,77],"good":[12],"resource.":[13],"Even":[14],"though":[15],"searching":[16],"is":[19,25,56,87],"easy,":[21],"what":[22],"remains":[23],"difficult":[24],"to":[26,39,91,130],"automate":[27],"process":[29],"extraction":[32],"from":[33],"available":[35],"online":[36],"due":[38],"lack":[41],"structure":[43],"and":[44,66,74,100],"diversity":[46],"in":[47,58,105],"sharing":[49],"methods.":[50],"Most":[51],"times,":[54],"stored":[57],"different":[59,64],"proprietary":[60],"formats,":[61],"complying":[62],"with":[63,89,124],"standards":[65],"protocols":[67],"which":[68],"tasks":[70],"like":[71],"data":[72],"mining":[73],"harvesting":[76,84],"difficult.":[78],"In":[79],"this":[80],"paper,":[81],"an":[82,125],"tool":[85],"(heteroHarvest)":[86],"presented":[88],"objectives":[90],"address":[92],"these":[93],"problems":[94],"by":[95],"filtering":[96],"useful":[98],"then":[101],"normalizing":[102],"singular":[107],"non":[108],"hypertext":[109],"format.":[110],"Finally":[111],"we":[112],"describe":[113],"results":[115,120],"experimental":[117],"evaluation.":[118],"are":[121],"found":[122],"promising":[123],"overall":[126],"error":[127],"rate":[128],"equal":[129],"6.5%":[131],"across":[132],"heterogeneous":[133],"formats.":[134]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}