{"id":"https://openalex.org/W71104953","doi":"https://doi.org/10.1145/2488388.2488430","title":"Researcher homepage classification using unlabeled data","display_name":"Researcher homepage classification using unlabeled data","publication_year":2013,"publication_date":"2013-05-13","ids":{"openalex":"https://openalex.org/W71104953","doi":"https://doi.org/10.1145/2488388.2488430","mag":"71104953"},"language":"en","primary_location":{"id":"doi:10.1145/2488388.2488430","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2488388.2488430","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd international conference on World Wide Web","raw_type":"proceedings-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/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":true,"raw_author_name":"Sujatha Das Gollapalli","raw_affiliation_strings":["The Pennsylvania State University, State College, PA, USA"],"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University, State College, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089085275","display_name":"Cornelia Caragea","orcid":"https://orcid.org/0000-0002-5664-2163"},"institutions":[{"id":"https://openalex.org/I123534392","display_name":"University of North Texas","ror":"https://ror.org/00v97ad02","country_code":"US","type":"education","lineage":["https://openalex.org/I123534392"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cornelia Caragea","raw_affiliation_strings":["University of North Texas, Denton, TX, USA","University of North Texas, Denton, TX, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"University of North Texas, Denton, TX, USA","institution_ids":["https://openalex.org/I123534392"]},{"raw_affiliation_string":"University of North Texas, Denton, TX, USA#TAB#","institution_ids":["https://openalex.org/I123534392"]}]},{"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":["The Pennsylvania State University, State College, PA, USA"],"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University, State College, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"last","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":["The Pennsylvania State University, State College, PA, USA"],"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University, State College, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5076157833"],"corresponding_institution_ids":["https://openalex.org/I130769515"],"apc_list":null,"apc_paid":null,"fwci":12.1342,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.98150776,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"471","last_page":"482"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9919000267982483,"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/T11644","display_name":"Spam and Phishing Detection","score":0.9768999814987183,"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":0.931767463684082},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7545062899589539},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.657461941242218},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6482154130935669},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4926021695137024},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4854789078235626},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4532736837863922},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4364355504512787},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.339047372341156}],"concepts":[{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.931767463684082},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7545062899589539},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.657461941242218},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6482154130935669},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4926021695137024},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4854789078235626},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4532736837863922},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4364355504512787},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.339047372341156},{"id":"https://openalex.org/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2488388.2488430","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2488388.2488430","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd international conference on World Wide Web","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W87822204","https://openalex.org/W173995639","https://openalex.org/W202303397","https://openalex.org/W396027602","https://openalex.org/W1489992655","https://openalex.org/W1501667924","https://openalex.org/W1506806321","https://openalex.org/W1532325895","https://openalex.org/W1550206324","https://openalex.org/W1563088657","https://openalex.org/W1582583141","https://openalex.org/W1595222087","https://openalex.org/W1889038981","https://openalex.org/W1983531058","https://openalex.org/W2003471189","https://openalex.org/W2022322548","https://openalex.org/W2029341294","https://openalex.org/W2037603696","https://openalex.org/W2038721957","https://openalex.org/W2048679005","https://openalex.org/W2059586463","https://openalex.org/W2081580037","https://openalex.org/W2084745915","https://openalex.org/W2097083044","https://openalex.org/W2097089247","https://openalex.org/W2097580385","https://openalex.org/W2101210369","https://openalex.org/W2104660959","https://openalex.org/W2111700528","https://openalex.org/W2121702856","https://openalex.org/W2125327503","https://openalex.org/W2128614648","https://openalex.org/W2130062883","https://openalex.org/W2133348086","https://openalex.org/W2133990480","https://openalex.org/W2134491992","https://openalex.org/W2136504847","https://openalex.org/W2139578439","https://openalex.org/W2141416357","https://openalex.org/W2153635508","https://openalex.org/W2156772624","https://openalex.org/W2156909104","https://openalex.org/W2161920802","https://openalex.org/W2169899598","https://openalex.org/W2171629518","https://openalex.org/W2215421138","https://openalex.org/W2950359053","https://openalex.org/W3029645440","https://openalex.org/W4206037918","https://openalex.org/W4235505822","https://openalex.org/W4301909677","https://openalex.org/W6608351394","https://openalex.org/W6657826343","https://openalex.org/W6680140577","https://openalex.org/W6683581212","https://openalex.org/W6842097421","https://openalex.org/W6983226262"],"related_works":["https://openalex.org/W4385695127","https://openalex.org/W2981877337","https://openalex.org/W3203938600","https://openalex.org/W2169074127","https://openalex.org/W83146503","https://openalex.org/W2163707935","https://openalex.org/W202723009","https://openalex.org/W2145955964","https://openalex.org/W2188612292","https://openalex.org/W2165396616"],"abstract_inverted_index":{"A":[0],"classifier":[1,24],"that":[2,25],"determines":[3],"if":[4],"a":[5,10,16,23],"webpage":[6],"is":[7,26],"relevant":[8],"to":[9,28,35],"specified":[11],"set":[12],"of":[13,43,56],"topics":[14],"comprises":[15],"key":[17],"component":[18],"for":[19],"focused":[20],"crawling.":[21,59],"Can":[22],"tuned":[27],"perform":[29],"well":[30],"on":[31,46],"training":[32],"datasets":[33],"continue":[34],"filter":[36],"out":[37],"irrelevant":[38],"pages":[39],"in":[40,53],"the":[41,47,54],"face":[42],"changed":[44],"content":[45],"Web?":[48],"We":[49],"investigate":[50],"this":[51],"question":[52],"context":[55],"researcher":[57],"homepage":[58]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":8},{"year":2014,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}