{"id":"https://openalex.org/W2014766608","doi":"https://doi.org/10.1145/2756406.2756925","title":"iCrawl","display_name":"iCrawl","publication_year":2015,"publication_date":"2015-06-12","ids":{"openalex":"https://openalex.org/W2014766608","doi":"https://doi.org/10.1145/2756406.2756925","mag":"2014766608"},"language":"en","primary_location":{"id":"doi:10.1145/2756406.2756925","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2756406.2756925","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th ACM/IEEE-CS Joint Conference on Digital Libraries","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1612.06202","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Gerhard Gossen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136150","display_name":"L3S Research Center","ror":"https://ror.org/039t4wk02","country_code":"DE","type":"facility","lineage":["https://openalex.org/I114112103","https://openalex.org/I4210136150","https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Gerhard Gossen","raw_affiliation_strings":["L3S Research Center, Hannover, Germany"],"affiliations":[{"raw_affiliation_string":"L3S Research Center, Hannover, Germany","institution_ids":["https://openalex.org/I4210136150"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Elena Demidova","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136150","display_name":"L3S Research Center","ror":"https://ror.org/039t4wk02","country_code":"DE","type":"facility","lineage":["https://openalex.org/I114112103","https://openalex.org/I4210136150","https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Elena Demidova","raw_affiliation_strings":["L3S Research Center, Hannover, Germany"],"affiliations":[{"raw_affiliation_string":"L3S Research Center, Hannover, Germany","institution_ids":["https://openalex.org/I4210136150"]}]},{"author_position":"last","author":{"id":null,"display_name":"Thomas Risse","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136150","display_name":"L3S Research Center","ror":"https://ror.org/039t4wk02","country_code":"DE","type":"facility","lineage":["https://openalex.org/I114112103","https://openalex.org/I4210136150","https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Thomas Risse","raw_affiliation_strings":["L3S Research Center, Hannover, Germany"],"affiliations":[{"raw_affiliation_string":"L3S Research Center, Hannover, Germany","institution_ids":["https://openalex.org/I4210136150"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210136150"],"apc_list":null,"apc_paid":null,"fwci":8.2344,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.9725858,"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":"75","last_page":"84"},"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9754999876022339,"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"}},{"id":"https://openalex.org/T11478","display_name":"Caching and Content Delivery","score":0.972100019454956,"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/exploit","display_name":"Exploit","score":0.6219000220298767},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.6017000079154968},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.5655999779701233},{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.4505000114440918},{"id":"https://openalex.org/keywords/digital-media","display_name":"Digital media","score":0.41920000314712524},{"id":"https://openalex.org/keywords/web-2.0","display_name":"Web 2.0","score":0.4025999903678894},{"id":"https://openalex.org/keywords/digital-content","display_name":"Digital content","score":0.3517000079154968},{"id":"https://openalex.org/keywords/web-application","display_name":"Web application","score":0.32190001010894775}],"concepts":[{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6219000220298767},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.6017000079154968},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5932000279426575},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.5655999779701233},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4788999855518341},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.4505000114440918},{"id":"https://openalex.org/C17632256","wikidata":"https://www.wikidata.org/wiki/Q1076968","display_name":"Digital media","level":2,"score":0.41920000314712524},{"id":"https://openalex.org/C136699151","wikidata":"https://www.wikidata.org/wiki/Q131164","display_name":"Web 2.0","level":3,"score":0.4025999903678894},{"id":"https://openalex.org/C2779344036","wikidata":"https://www.wikidata.org/wiki/Q11320476","display_name":"Digital content","level":2,"score":0.3517000079154968},{"id":"https://openalex.org/C118643609","wikidata":"https://www.wikidata.org/wiki/Q189210","display_name":"Web application","level":2,"score":0.32190001010894775},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.31290000677108765},{"id":"https://openalex.org/C101293273","wikidata":"https://www.wikidata.org/wiki/Q579716","display_name":"User-generated content","level":3,"score":0.30300000309944153},{"id":"https://openalex.org/C162446236","wikidata":"https://www.wikidata.org/wiki/Q653137","display_name":"Content analysis","level":2,"score":0.2874999940395355},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.28619998693466187},{"id":"https://openalex.org/C2776324614","wikidata":"https://www.wikidata.org/wiki/Q3948731","display_name":"Web content","level":3,"score":0.2831000089645386},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.2791000008583069},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.27469998598098755},{"id":"https://openalex.org/C503923677","wikidata":"https://www.wikidata.org/wiki/Q2724244","display_name":"Social web","level":3,"score":0.2574000060558319}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2756406.2756925","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2756406.2756925","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th ACM/IEEE-CS Joint Conference on Digital Libraries","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1612.06202","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1612.06202","pdf_url":"https://arxiv.org/pdf/1612.06202","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1612.06202","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1612.06202","pdf_url":"https://arxiv.org/pdf/1612.06202","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1139929693","display_name":null,"funder_award_id":"GlycoRec","funder_id":"https://openalex.org/F4320321114","funder_display_name":"Bundesministerium f\u00fcr Bildung und Forschung"},{"id":"https://openalex.org/G5897118590","display_name":null,"funder_award_id":"339233","funder_id":"https://openalex.org/F4320334678","funder_display_name":"European Research Council"}],"funders":[{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"},{"id":"https://openalex.org/F4320334678","display_name":"European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W45685238","https://openalex.org/W1489992655","https://openalex.org/W1758813703","https://openalex.org/W1967788125","https://openalex.org/W1972601723","https://openalex.org/W1976216148","https://openalex.org/W1982029265","https://openalex.org/W1999544021","https://openalex.org/W2005579877","https://openalex.org/W2017224880","https://openalex.org/W2030559659","https://openalex.org/W2095648979","https://openalex.org/W2116224704","https://openalex.org/W2128915886","https://openalex.org/W2158601853","https://openalex.org/W2160853696","https://openalex.org/W2167378365","https://openalex.org/W2252096988","https://openalex.org/W2911388033","https://openalex.org/W6678701036"],"related_works":[],"abstract_inverted_index":{"Researchers":[0],"in":[1,104,118],"the":[2,21,25,76,80,124,133],"Digital":[3],"Humanities":[4],"and":[5,11,43,49,84,87,101,114,122],"journalists":[6],"need":[7],"to":[8],"monitor,":[9],"collect":[10],"analyze":[12],"fresh":[13,50,61,83,127],"online":[14],"content":[15,90,117,130],"regarding":[16],"current":[17],"events":[18],"such":[19],"as":[20],"Ebola":[22],"outbreak":[23],"or":[24],"Ukraine":[26],"crisis":[27],"on":[28],"demand.":[29],"However,":[30],"existing":[31],"focused":[32,69,108],"crawling":[33],"approaches":[34],"only":[35],"consider":[36],"topical":[37],"aspects":[38,42],"while":[39],"ignoring":[40],"temporal":[41],"therefore":[44],"cannot":[45],"achieve":[46],"thematically":[47],"coherent":[48],"Web":[51,86,89,100,113],"collections.":[52],"Especially":[53],"Social":[54,88,102,115,128],"Media":[55,103,116,129],"provide":[56],"a":[57,92,105,119],"rich":[58],"source":[59],"of":[60,78,82,94,99,126],"content,":[62],"which":[63],"is":[64],"not":[65],"used":[66],"by":[67],"state-of-the-art":[68],"crawlers.":[70],"In":[71],"this":[72],"paper":[73],"we":[74],"address":[75],"issues":[77],"enabling":[79],"collection":[81],"relevant":[85],"for":[91,131],"topic":[93],"interest":[95],"through":[96],"seamless":[97],"integration":[98],"novel":[106],"integrated":[107],"crawler.":[109,134],"The":[110],"crawler":[111],"collects":[112],"single":[120],"system":[121],"exploits":[123],"stream":[125],"guiding":[132]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":4}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2016-06-24T00:00:00"}
