{"id":"https://openalex.org/W2121354841","doi":"https://doi.org/10.1145/1099554.1099583","title":"Focused crawling for both topical relevance and quality of medical information","display_name":"Focused crawling for both topical relevance and quality of medical information","publication_year":2005,"publication_date":"2005-10-31","ids":{"openalex":"https://openalex.org/W2121354841","doi":"https://doi.org/10.1145/1099554.1099583","mag":"2121354841"},"language":"en","primary_location":{"id":"doi:10.1145/1099554.1099583","doi":"https://doi.org/10.1145/1099554.1099583","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1099554.1099583","pdf_url":null,"source":{"id":"https://openalex.org/S4393918199","display_name":"ACM International Conference on Information and Knowledge Management (CIKM)","issn_l":"2155-0751","issn":["2155-0751"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th ACM international conference on Information and knowledge management","raw_type":"proceedings-article"},"volume":null,"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/A5013107135","display_name":"Thanh Tin Tang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Thanh Tin Tang","raw_affiliation_strings":["ANU, Canberra, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ANU, Canberra, Australia","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032211209","display_name":"David Hawking","orcid":"https://orcid.org/0000-0002-3704-5398","observed_orcids":["https://orcid.org/0000-0002-3704-5398"]},"institutions":[{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"government","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]},{"id":"https://openalex.org/I4210128581","display_name":"Information and Communication Technologies Centre","ror":"https://ror.org/034x2fx50","country_code":"AU","type":"facility","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4210128581","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"David Hawking","raw_affiliation_strings":["CSIRO ICT Centre, Canberra, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CSIRO ICT Centre, Canberra, Australia","institution_ids":["https://openalex.org/I1292875679","https://openalex.org/I4210128581"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055132321","display_name":"Nick Craswell","orcid":"https://orcid.org/0000-0002-9351-8137","observed_orcids":["https://orcid.org/0000-0002-9351-8137"]},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Nick Craswell","raw_affiliation_strings":["Microsoft Research, Cambridge, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Cambridge, UK","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109156857","display_name":"Kathy M. Griffiths","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Kathy Griffiths","raw_affiliation_strings":["ANU, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ANU, Australia","institution_ids":["https://openalex.org/I118347636"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.2225,"has_fulltext":false,"cited_by_count":40,"citation_normalized_percentile":{"value":0.88598237,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"147","last_page":"154"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9872999787330627,"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":0.9872999787330627,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.012299999594688416,"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/T10737","display_name":"Health Literacy and Information Accessibility","score":0.0003000000142492354,"subfield":{"id":"https://openalex.org/subfields/3600","display_name":"General Health Professions"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/focused-crawling","display_name":"focused crawling","score":0.9639999866485596},{"id":"https://openalex.org/keywords/health-information-quality","display_name":"health information quality","score":0.6790000200271606},{"id":"https://openalex.org/keywords/depression","display_name":"depression","score":0.41100001335144043},{"id":"https://openalex.org/keywords/health-information-retrieval","display_name":"medical information retrieval","score":0.7089999914169312},{"id":"https://openalex.org/keywords/anchor-text","display_name":"anchor text","score":0.6930000185966492},{"id":"https://openalex.org/keywords/post-filtering","display_name":"post-filtering","score":0.6150000095367432},{"id":"https://openalex.org/keywords/network-traffic-reduction","display_name":"network traffic reduction","score":0.656000018119812}],"concepts":[{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.9369944334030151},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7388667464256287},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.7197819352149963},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.6916232705116272},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.6393528580665588},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6140041947364807},{"id":"https://openalex.org/C73340581","wikidata":"https://www.wikidata.org/wiki/Q5463958","display_name":"Focused crawler","level":5,"score":0.5214720964431763},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5048666596412659},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.40431681275367737},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.36115020513534546},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.1084173321723938},{"id":"https://openalex.org/C61096286","wikidata":"https://www.wikidata.org/wiki/Q7978592","display_name":"Web navigation","level":3,"score":0.08691975474357605},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.08601915836334229},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/1099554.1099583","doi":"https://doi.org/10.1145/1099554.1099583","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1099554.1099583","pdf_url":null,"source":{"id":"https://openalex.org/S4393918199","display_name":"ACM International Conference on Information and Knowledge Management (CIKM)","issn_l":"2155-0751","issn":["2155-0751"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th ACM international conference on Information and knowledge management","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.473.9186","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.473.9186","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://cs.anu.edu.au/people/Tim.Tang/Documents/cikm05.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.86.7992","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.86.7992","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://research.microsoft.com/users/nickcr/pubs/tang_cikm05.pdf","raw_type":"text"},{"id":"pmh:oai:openresearch-repository.anu.edu.au:1885/83541","doi":null,"is_oa":false,"landing_page_url":"http://hdl.handle.net/1885/83541","pdf_url":null,"source":{"id":"https://openalex.org/S4306402539","display_name":"ANU Open Research (Australian National University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I118347636","host_organization_name":"Australian National University","host_organization_lineage":["https://openalex.org/I118347636"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of ACM Conference on Information and Knowledge Management (CIKM 2005)","raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/3","display_name":"Good health and well-being","score":0.504800021648407}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W173995639","https://openalex.org/W187984960","https://openalex.org/W1482214997","https://openalex.org/W1489992655","https://openalex.org/W1497353506","https://openalex.org/W1504694836","https://openalex.org/W1556034692","https://openalex.org/W1633338417","https://openalex.org/W1990058660","https://openalex.org/W2001832505","https://openalex.org/W2006119904","https://openalex.org/W2014134732","https://openalex.org/W2014980529","https://openalex.org/W2029341294","https://openalex.org/W2039522453","https://openalex.org/W2043909051","https://openalex.org/W2048071039","https://openalex.org/W2065096648","https://openalex.org/W2066309116","https://openalex.org/W2066395238","https://openalex.org/W2066636486","https://openalex.org/W2066702198","https://openalex.org/W2123109647","https://openalex.org/W2123504579","https://openalex.org/W2124673015","https://openalex.org/W2125055259","https://openalex.org/W2141195236","https://openalex.org/W2155520985","https://openalex.org/W2156093156","https://openalex.org/W2396291300","https://openalex.org/W4245350944","https://openalex.org/W6628905179"],"related_works":["https://openalex.org/W7096174953","https://openalex.org/W2274096661","https://openalex.org/W187984960","https://openalex.org/W2331924699","https://openalex.org/W1556034692","https://openalex.org/W2141195236","https://openalex.org/W2011303552","https://openalex.org/W1989111359","https://openalex.org/W2069952484","https://openalex.org/W2236554525"],"abstract_inverted_index":{"Subject-specific":[0],"search":[1,38],"facilities":[2],"on":[3,90],"health":[4,33,64],"sites":[5],"are":[6],"usually":[7],"built":[8,57],"using":[9,107,150,160],"manual":[10],"inclusion":[11],"and":[12,21,44,54,116,119,141,154,170],"exclusion":[13],"rules.":[14],"These":[15],"can":[16,45,86],"be":[17,41,46,87,219],"expensive":[18],"to":[19,71,122,208],"maintain":[20],"often":[22],"provide":[23],"incomplete":[24],"coverage":[25,53],"of":[26,51,66,83,102,112,126,138,196,216,231],"Web":[27],"resources.":[28],"On":[29],"the":[30,62,81,95,103,124,136,171,194,209,229],"other":[31],"hand,":[32],"information":[34],"obtained":[35,159],"through":[36],"whole-of-Web":[37],"may":[39],"not":[40],"scientifically":[42],"based":[43,89],"potentially":[47],"harmful.To":[48],"address":[49],"problems":[50],"cost,":[52],"quality,":[55],"we":[56],"a":[58,108,166,182,223],"focused":[59,168,173,187,211],"crawler":[60,131,146,169,174,188],"for":[61],"mental":[63],"topic":[65],"depression,":[67],"which":[68],"was":[69,133,189],"able":[70],"selectively":[72],"fetch":[73],"higher":[74],"quality":[75,96,101,125,157,172,186,198,205,215],"relevant":[76,179],"information.":[77],"We":[78,98],"found":[79],"that":[80,214],"relevance":[82,140,152,167,210],"unfetched":[84],"pages":[85,180],"predicted":[88],"link":[91,139],"anchor":[92],"context,":[93],"but":[94],"cannot.":[97],"therefore":[99],"estimated":[100],"entire":[104],"linking":[105],"page,":[106],"learned":[109],"IR-style":[110],"query":[111],"weighted":[113],"single":[114],"words":[115],"word":[117],"pairs,":[118],"used":[120],"this":[121],"predict":[123],"its":[127],"links.":[128],"The":[129,185],"overall":[130],"priority":[132],"determined":[134],"by":[135,221],"product":[137],"source":[142],"quality.We":[143],"evaluated":[144],"our":[145],"against":[147],"baseline":[148],"crawls":[149],"both":[151],"judgments":[153],"objective":[155],"site":[156],"scores":[158],"an":[161],"evidence-based":[162],"rating":[163],"scale.":[164],"Both":[165],"retrieved":[175],"twice":[176],"as":[177,181],"many":[178],"breadth-first":[183,226],"control.":[184],"quite":[190],"effective":[191],"in":[192],"reducing":[193],"amount":[195],"low":[197],"material":[199],"fetched":[200],"while":[201],"crawling":[202],"more":[203],"high":[204],"content,":[206],"relative":[207],"crawler.Analysis":[212],"suggests":[213],"content":[217],"might":[218],"improved":[220],"post-filtering":[222],"very":[224],"big":[225],"crawl,":[227],"at":[228],"cost":[230],"substantially":[232],"increased":[233],"network":[234],"traffic.":[235]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}
