{"id":"https://openalex.org/W1983531058","doi":"https://doi.org/10.1145/1998076.1998099","title":"On identifying academic homepages for digital libraries","display_name":"On identifying academic homepages for digital libraries","publication_year":2011,"publication_date":"2011-06-13","ids":{"openalex":"https://openalex.org/W1983531058","doi":"https://doi.org/10.1145/1998076.1998099","mag":"1983531058"},"language":"en","primary_location":{"id":"doi:10.1145/1998076.1998099","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1998076.1998099","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th annual international ACM/IEEE joint conference on Digital libraries","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/A5076157833","display_name":"Sujatha Das Gollapalli","orcid":"https://orcid.org/0000-0002-4567-8937"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sujatha Das Gollapalli","raw_affiliation_strings":["Penn State University, University Park, PA, USA",", Penn State University, University Park, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Penn State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":", Penn State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001294898","display_name":"C. Lee Giles","orcid":"https://orcid.org/0000-0002-1931-585X"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"C. Lee Giles","raw_affiliation_strings":["Penn State University, University Park, PA, USA",", Penn State University, University Park, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Penn State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":", Penn State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009542542","display_name":"Prasenjit Mitra","orcid":"https://orcid.org/0000-0002-7530-9497"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Prasenjit Mitra","raw_affiliation_strings":["Penn State University, University Park, PA, USA",", Penn State University, University Park, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Penn State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":", Penn State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089085275","display_name":"Cornelia Caragea","orcid":"https://orcid.org/0000-0002-5664-2163"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cornelia Caragea","raw_affiliation_strings":["Penn State University, University Park, PA, USA",", Penn State University, University Park, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Penn State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":", Penn State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I130769515"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"123","last_page":"132"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9890999794006348,"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":0.9890999794006348,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9883999824523926,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.958899974822998,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7929868698120117},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.6044231057167053},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5666956305503845},{"id":"https://openalex.org/keywords/digital-library","display_name":"Digital library","score":0.544497013092041},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5005083084106445},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.493264377117157}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7929868698120117},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.6044231057167053},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5666956305503845},{"id":"https://openalex.org/C513874922","wikidata":"https://www.wikidata.org/wiki/Q212805","display_name":"Digital library","level":3,"score":0.544497013092041},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5005083084106445},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.493264377117157},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C164913051","wikidata":"https://www.wikidata.org/wiki/Q482","display_name":"Poetry","level":2,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1998076.1998099","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1998076.1998099","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th annual international ACM/IEEE joint conference on Digital libraries","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.6200000047683716}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W96971711","https://openalex.org/W1490467549","https://openalex.org/W1498257742","https://openalex.org/W1501667924","https://openalex.org/W1605217017","https://openalex.org/W1691915759","https://openalex.org/W1880262756","https://openalex.org/W1993703890","https://openalex.org/W1998284155","https://openalex.org/W2001082470","https://openalex.org/W2018022579","https://openalex.org/W2020278455","https://openalex.org/W2022322548","https://openalex.org/W2023094000","https://openalex.org/W2030895949","https://openalex.org/W2059586463","https://openalex.org/W2061265416","https://openalex.org/W2067802667","https://openalex.org/W2068082565","https://openalex.org/W2104973501","https://openalex.org/W2110591510","https://openalex.org/W2117861756","https://openalex.org/W2121702856","https://openalex.org/W2128941908","https://openalex.org/W2130054784","https://openalex.org/W2130831177","https://openalex.org/W2132870739","https://openalex.org/W2133990480","https://openalex.org/W2138224681","https://openalex.org/W2140479099","https://openalex.org/W2142510125","https://openalex.org/W2147164982","https://openalex.org/W2150595037","https://openalex.org/W2152862885","https://openalex.org/W2153635508","https://openalex.org/W2154707336","https://openalex.org/W2156037541","https://openalex.org/W2164889641","https://openalex.org/W2166463728","https://openalex.org/W2247055361","https://openalex.org/W2262954636","https://openalex.org/W2626786574","https://openalex.org/W3120421331","https://openalex.org/W6603989278","https://openalex.org/W6639619044","https://openalex.org/W6665870229","https://openalex.org/W6676781583","https://openalex.org/W6681574511"],"related_works":["https://openalex.org/W1488511360","https://openalex.org/W1781894645","https://openalex.org/W2894902932","https://openalex.org/W569715723","https://openalex.org/W188332989","https://openalex.org/W2982387199","https://openalex.org/W2000745862","https://openalex.org/W2120930843","https://openalex.org/W42013907","https://openalex.org/W2042734105"],"abstract_inverted_index":{"Academic":[0],"homepages":[1,43,56,95],"are":[2,44,179],"rich":[3],"sources":[4],"of":[5,100,114,124,139,163,195,206],"information":[6,15,63,168],"on":[7,24,46,210,219],"scientific":[8],"research":[9,22,166,193],"and":[10,18,57,60,133,165],"researchers.":[11],"Most":[12],"researchers":[13,68,197],"provide":[14],"about":[16,67],"themselves":[17],"links":[19],"to":[20,36,85,181,187,192],"their":[21,25,70],"publications":[23],"homepages.":[26,201],"In":[27],"this":[28],"study,":[29],"we":[30,51,77,158],"address":[31],"the":[32,47,74,101,112,122,161,196,204,212],"following":[33],"questions":[34],"related":[35],"academic":[37,42,55,94,171,200],"homepages:":[38],"(1)":[39],"How":[40],"many":[41],"there":[45],"web?":[48],"(2)":[49],"Can":[50],"accurately":[52],"discriminate":[53],"between":[54],"other":[58],"webpages?":[59],"(3)":[61],"What":[62],"can":[64],"be":[65],"extracted":[66],"from":[69,169,176],"homepages?":[71],"For":[72],"addressing":[73],"first":[75],"question,":[76],"use":[78,123],"mark-recapture":[79],"techniques":[80,148],"commonly":[81],"employed":[82],"in":[83,199],"biometrics":[84],"estimate":[86],"animal":[87],"population":[88],"sizes.":[89],"Our":[90],"results":[91],"indicate":[92],"that":[93,135],"comprise":[96],"a":[97,136,183],"small":[98,137],"fraction":[99],"Web":[102],"making":[103],"automatic":[104],"methods":[105,209],"for":[106,117,127,131],"discriminating":[107],"them":[108,218],"crucial.":[109],"We":[110,120,202],"study":[111],"performance":[113],"content-based":[115,129],"features":[116,130,141,144],"classifying":[118],"webpages.":[119],"propose":[121],"topic":[125,177],"models":[126,178],"identifying":[128],"classification":[132],"show":[134,203],"set":[138],"LDA-based":[140],"out-perform":[142],"term":[143,152],"selected":[145],"using":[146],"traditional":[147],"such":[149],"as":[150],"aggregate":[151],"frequencies":[153],"or":[154],"mutual":[155],"information.":[156],"Finally,":[157],"deal":[159],"with":[160],"extraction":[162],"name":[164],"interests":[167,194],"an":[170],"homepage.":[172],"Term-topic":[173],"associations":[174],"obtained":[175],"used":[180],"design":[182],"novel,":[184],"unsupervised":[185],"technique":[186],"identify":[188],"short":[189],"segments":[190],"corresponding":[191],"specified":[198],"efficacy":[205],"our":[207],"proposed":[208],"all":[211],"three":[213],"tasks":[214],"by":[215],"experimentally":[216],"evaluating":[217],"multiple":[220],"publicly-available":[221],"datasets.":[222]},"counts_by_year":[{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}