{"id":"https://openalex.org/W2118165382","doi":"https://doi.org/10.1007/s10115-009-0266-3","title":"xCrawl: a high-recall crawling method for Web mining","display_name":"xCrawl: a high-recall crawling method for Web mining","publication_year":2009,"publication_date":"2009-11-17","ids":{"openalex":"https://openalex.org/W2118165382","doi":"https://doi.org/10.1007/s10115-009-0266-3","mag":"2118165382"},"language":"en","primary_location":{"id":"doi:10.1007/s10115-009-0266-3","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10115-009-0266-3","pdf_url":null,"source":{"id":"https://openalex.org/S81770430","display_name":"Knowledge and Information Systems","issn_l":"0219-1377","issn":["0219-1377","0219-3116"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Knowledge and Information Systems","raw_type":"journal-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/A5112547698","display_name":"Kostyantyn Shchekotykhin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210166741","display_name":"University of Klagenfurt","ror":"https://ror.org/05q9m0937","country_code":"AT","type":"education","lineage":["https://openalex.org/I4210166741"]}],"countries":["AT"],"is_corresponding":true,"raw_author_name":"Kostyantyn Shchekotykhin","raw_affiliation_strings":["University Klagenfurt, 9020, Klagenfurt, Austria","University Klagenfurt, 9020, Klagenfurt, Austria#TAB#"],"affiliations":[{"raw_affiliation_string":"University Klagenfurt, 9020, Klagenfurt, Austria","institution_ids":["https://openalex.org/I4210166741"]},{"raw_affiliation_string":"University Klagenfurt, 9020, Klagenfurt, Austria#TAB#","institution_ids":["https://openalex.org/I4210166741"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005545405","display_name":"Dietmar Jannach","orcid":"https://orcid.org/0000-0002-4698-8507"},"institutions":[{"id":"https://openalex.org/I200332995","display_name":"TU Dortmund University","ror":"https://ror.org/01k97gp34","country_code":"DE","type":"education","lineage":["https://openalex.org/I200332995"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Dietmar Jannach","raw_affiliation_strings":["Technische Universit\u00e4t Dortmund, 44221, Dortmund, Germany","Technische Universit\u00e4t Dortmund, 44221 Dortmund (Germany)"],"affiliations":[{"raw_affiliation_string":"Technische Universit\u00e4t Dortmund, 44221, Dortmund, Germany","institution_ids":["https://openalex.org/I200332995"]},{"raw_affiliation_string":"Technische Universit\u00e4t Dortmund, 44221 Dortmund (Germany)","institution_ids":["https://openalex.org/I200332995"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037543382","display_name":"Gerhard Friedrich","orcid":"https://orcid.org/0000-0002-1992-4049"},"institutions":[{"id":"https://openalex.org/I4210166741","display_name":"University of Klagenfurt","ror":"https://ror.org/05q9m0937","country_code":"AT","type":"education","lineage":["https://openalex.org/I4210166741"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Gerhard Friedrich","raw_affiliation_strings":["University Klagenfurt, 9020, Klagenfurt, Austria","University Klagenfurt, 9020, Klagenfurt, Austria#TAB#"],"affiliations":[{"raw_affiliation_string":"University Klagenfurt, 9020, Klagenfurt, Austria","institution_ids":["https://openalex.org/I4210166741"]},{"raw_affiliation_string":"University Klagenfurt, 9020, Klagenfurt, Austria#TAB#","institution_ids":["https://openalex.org/I4210166741"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5112547698"],"corresponding_institution_ids":["https://openalex.org/I4210166741"],"apc_list":{"value":2290,"currency":"EUR","value_usd":2890},"apc_paid":null,"fwci":4.6661,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.95362719,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"25","issue":"2","first_page":"303","last_page":"326"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":1.0,"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":1.0,"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/T11478","display_name":"Caching and Content Delivery","score":0.98580002784729,"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"}},{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.9767000079154968,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.8757033348083496},{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.861327588558197},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7989656329154968},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6680858135223389},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.5849393010139465},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.549055814743042},{"id":"https://openalex.org/keywords/web-mining","display_name":"Web mining","score":0.5216648578643799},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.46126657724380493},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.45477908849716187},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.4483729600906372},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.41091442108154297},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.3932808041572571},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3837648928165436}],"concepts":[{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.8757033348083496},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.861327588558197},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7989656329154968},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6680858135223389},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.5849393010139465},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.549055814743042},{"id":"https://openalex.org/C197046077","wikidata":"https://www.wikidata.org/wiki/Q785337","display_name":"Web mining","level":3,"score":0.5216648578643799},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.46126657724380493},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.45477908849716187},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.4483729600906372},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.41091442108154297},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.3932808041572571},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3837648928165436},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10115-009-0266-3","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10115-009-0266-3","pdf_url":null,"source":{"id":"https://openalex.org/S81770430","display_name":"Knowledge and Information Systems","issn_l":"0219-1377","issn":["0219-1377","0219-3116"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Knowledge and Information Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1485536830","https://openalex.org/W1489992655","https://openalex.org/W1491950495","https://openalex.org/W1506122440","https://openalex.org/W1506845741","https://openalex.org/W1975414584","https://openalex.org/W2005579877","https://openalex.org/W2005677600","https://openalex.org/W2013761541","https://openalex.org/W2015136191","https://openalex.org/W2015415022","https://openalex.org/W2017726337","https://openalex.org/W2028514612","https://openalex.org/W2029341294","https://openalex.org/W2033709196","https://openalex.org/W2044807464","https://openalex.org/W2065096648","https://openalex.org/W2065843886","https://openalex.org/W2096891167","https://openalex.org/W2102189859","https://openalex.org/W2103224511","https://openalex.org/W2119012894","https://openalex.org/W2123504579","https://openalex.org/W2124168655","https://openalex.org/W2124673015","https://openalex.org/W2125672377","https://openalex.org/W2129620481","https://openalex.org/W2130760429","https://openalex.org/W2138621811","https://openalex.org/W2142507092","https://openalex.org/W2156772624","https://openalex.org/W2162502927","https://openalex.org/W2169463693","https://openalex.org/W2286363244","https://openalex.org/W2466512847","https://openalex.org/W2913668833","https://openalex.org/W2914929854","https://openalex.org/W2915063781","https://openalex.org/W4247551517"],"related_works":["https://openalex.org/W2566658409","https://openalex.org/W3119324922","https://openalex.org/W2352686120","https://openalex.org/W2372594123","https://openalex.org/W2358310581","https://openalex.org/W2964752624","https://openalex.org/W2026132847","https://openalex.org/W4385695127","https://openalex.org/W2137810919","https://openalex.org/W2089702591"],"abstract_inverted_index":null,"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
