{"id":"https://openalex.org/W4412673544","doi":"https://doi.org/10.1145/3731120.3744597","title":"Neural Prioritisation for Web Crawling","display_name":"Neural Prioritisation for Web Crawling","publication_year":2025,"publication_date":"2025-07-18","ids":{"openalex":"https://openalex.org/W4412673544","doi":"https://doi.org/10.1145/3731120.3744597"},"language":"en","primary_location":{"id":"doi:10.1145/3731120.3744597","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3731120.3744597","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 International ACM SIGIR Conference on Innovative Concepts and Theories in Information Retrieval (ICTIR)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://eprints.gla.ac.uk/view/author/60888.html>","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5115460553","display_name":"Francesca Pezzuti","orcid":null},"institutions":[{"id":"https://openalex.org/I108290504","display_name":"University of Pisa","ror":"https://ror.org/03ad39j10","country_code":"IT","type":"education","lineage":["https://openalex.org/I108290504"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Francesca Pezzuti","raw_affiliation_strings":["University of Pisa, Pisa, Italy"],"affiliations":[{"raw_affiliation_string":"University of Pisa, Pisa, Italy","institution_ids":["https://openalex.org/I108290504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014199889","display_name":"Sean MacAvaney","orcid":"https://orcid.org/0000-0002-8914-2659"},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sean MacAvaney","raw_affiliation_strings":["University of Glasgow, Glasgow, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Glasgow, Glasgow, United Kingdom","institution_ids":["https://openalex.org/I7882870"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018894843","display_name":"Nicola Tonellotto","orcid":"https://orcid.org/0000-0002-7427-1001"},"institutions":[{"id":"https://openalex.org/I108290504","display_name":"University of Pisa","ror":"https://ror.org/03ad39j10","country_code":"IT","type":"education","lineage":["https://openalex.org/I108290504"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Nicola Tonellotto","raw_affiliation_strings":["University of Pisa, Pisa, Italy"],"affiliations":[{"raw_affiliation_string":"University of Pisa, Pisa, Italy","institution_ids":["https://openalex.org/I108290504"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5115460553"],"corresponding_institution_ids":["https://openalex.org/I108290504"],"apc_list":null,"apc_paid":null,"fwci":3.0778,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.92226862,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"307","last_page":"314"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9811999797821045,"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/T11644","display_name":"Spam and Phishing Detection","score":0.9370999932289124,"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/crawling","display_name":"Crawling","score":0.8838729858398438},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6984397172927856},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.44830551743507385},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.08761289715766907}],"concepts":[{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.8838729858398438},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6984397172927856},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.44830551743507385},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.08761289715766907},{"id":"https://openalex.org/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3731120.3744597","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3731120.3744597","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 International ACM SIGIR Conference on Innovative Concepts and Theories in Information Retrieval (ICTIR)","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.gla.ac.uk:359292","is_oa":true,"landing_page_url":"https://eprints.gla.ac.uk/view/author/60888.html>","pdf_url":null,"source":{"id":"https://openalex.org/S4210235606","display_name":"ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam)","issn_l":"2622-8912","issn":["2622-8912","2622-8920"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"},{"id":"pmh:oai:arXiv.org:2506.16146","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.16146","pdf_url":"https://arxiv.org/pdf/2506.16146","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:arpi.unipi.it:11568/1343923","is_oa":false,"landing_page_url":"https://hdl.handle.net/11568/1343923","pdf_url":null,"source":{"id":"https://openalex.org/S4377196265","display_name":"CINECA IRIS Institutial research information system (University of Pisa)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I108290504","host_organization_name":"University of Pisa","host_organization_lineage":["https://openalex.org/I108290504"],"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":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:eprints.gla.ac.uk:359292","is_oa":true,"landing_page_url":"https://eprints.gla.ac.uk/view/author/60888.html>","pdf_url":null,"source":{"id":"https://openalex.org/S4210235606","display_name":"ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam)","issn_l":"2622-8912","issn":["2622-8912","2622-8920"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2020622295","display_name":null,"funder_award_id":"Big Data","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G5082371171","display_name":null,"funder_award_id":"GA 101070014","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G7504899342","display_name":null,"funder_award_id":"101070014","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320317295","display_name":"Dipartimenti di Eccellenza","ror":null},{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W81688156","https://openalex.org/W1489992655","https://openalex.org/W1548349843","https://openalex.org/W1562513652","https://openalex.org/W2001832505","https://openalex.org/W2007687650","https://openalex.org/W2029341294","https://openalex.org/W2044743392","https://openalex.org/W2102942431","https://openalex.org/W2103545802","https://openalex.org/W2108280221","https://openalex.org/W2116224704","https://openalex.org/W2127536142","https://openalex.org/W2151007976","https://openalex.org/W2162502927","https://openalex.org/W2162630660","https://openalex.org/W2165612380","https://openalex.org/W2172189174","https://openalex.org/W2293888960","https://openalex.org/W2949213912","https://openalex.org/W3155638432","https://openalex.org/W4284691825","https://openalex.org/W4284705591","https://openalex.org/W4327810025","https://openalex.org/W4391998301","https://openalex.org/W4400528444","https://openalex.org/W4401065928","https://openalex.org/W4401933721","https://openalex.org/W6657826343","https://openalex.org/W6675604878","https://openalex.org/W6675676085","https://openalex.org/W6677666047","https://openalex.org/W6703381501","https://openalex.org/W6850554703"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4393220254","https://openalex.org/W4321258516","https://openalex.org/W2159872134","https://openalex.org/W4299833833","https://openalex.org/W2795447506","https://openalex.org/W2963942219","https://openalex.org/W2152505903"],"abstract_inverted_index":{"Given":[0],"the":[1,5,100,106,122,134,139,157,163,187,208,236,253],"vast":[2],"scale":[3],"of":[4,62,102,141,160,190,242],"Web,":[6],"crawling":[7,76,103,123,135,173,176,233],"prioritisation":[8,96],"techniques":[9,36],"based":[10,194],"on":[11,156,195,204,231,244],"link":[12,16],"graph":[13],"traversal,":[14],"popularity,":[15],"analysis,":[17],"and":[18,45,66,104,148,162,183,223,234],"textual":[19],"content":[20,143],"are":[21,28,37,49],"frequently":[22],"applied":[23],"to":[24,31,54,73,98,132,171,238,248],"surface":[25],"documents":[26],"that":[27,75,144],"most":[29],"likely":[30],"be":[32,78],"valuable.":[33],"While":[34,215],"existing":[35,172],"effective":[38],"for":[39,150],"keyword-based":[40,52],"search,":[41],"both":[42],"retrieval":[43],"methods":[44],"user":[46],"search":[47,152,184,202],"behaviours":[48],"shifting":[50],"from":[51,207],"matching":[53,65],"natural":[55,113,257],"language":[56,114,258],"semantic":[57,64,86,94,118,129,246],"matching.":[58],"The":[59],"remarkable":[60],"success":[61],"applying":[63],"quality":[67,130],"signals":[68],"during":[69,186],"ranking":[70],"leads":[71],"us":[72],"hypothesize":[74],"could":[77],"improved":[79],"by":[80],"prioritizing":[81],"Web":[82,211,232],"pages":[83],"with":[84,109,138,252],"high":[85],"quality.":[87],"To":[88],"investigate":[89],"this,":[90],"we":[91],"propose":[92,220],"a":[93,221,228,239],"quality-driven":[95],"technique":[97],"enhance":[99],"effectiveness":[101,185],"align":[105,250],"crawler":[107],"behaviour":[108],"recent":[110,127],"shift":[111,255],"towards":[112],"search.":[115,259],"We":[116],"embed":[117],"understanding":[119],"directly":[120],"into":[121],"process":[124],"--":[125,137],"leveraging":[126,245],"neural":[128,175,198],"estimators":[131],"prioritise":[133],"frontier":[136],"goal":[140],"surfacing":[142],"is":[145],"semantically":[146],"rich":[147],"valuable":[149],"modern":[151],"needs.":[153],"Our":[154],"experiments":[155],"English":[158],"subset":[159],"ClueWeb22-B":[161],"Researchy":[164],"Questions":[165],"query":[166,213],"set":[167],"show":[168],"that,":[169],"compared":[170],"techniques,":[174],"policies":[177,199],"significantly":[178],"improve":[179],"harvest":[180],"rate,":[181],"maxNDCG,":[182],"early":[188],"stages":[189],"crawling.":[191],"Meanwhile,":[192],"crawlers":[193,251],"our":[196],"proposed":[197],"maintain":[200],"comparable":[201],"performance":[203],"keyword":[205],"queries":[206],"MS":[209],"MARCO":[210],"Search":[212],"set.":[214],"this":[216],"work":[217],"does":[218],"not":[219],"definitive":[222],"complete":[224],"solution,":[225],"it":[226],"presents":[227],"forward-looking":[229],"perspective":[230],"opens":[235],"door":[237],"new":[240],"line":[241],"research":[243],"analysis":[247],"effectively":[249],"ongoing":[254],"toward":[256]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}