{"id":"https://openalex.org/W2059586463","doi":"https://doi.org/10.1145/1459352.1459357","title":"Web page classification","display_name":"Web page classification","publication_year":2009,"publication_date":"2009-02-01","ids":{"openalex":"https://openalex.org/W2059586463","doi":"https://doi.org/10.1145/1459352.1459357","mag":"2059586463"},"language":"en","primary_location":{"id":"doi:10.1145/1459352.1459357","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1459352.1459357","pdf_url":null,"source":{"id":"https://openalex.org/S157921468","display_name":"ACM Computing Surveys","issn_l":"0360-0300","issn":["0360-0300","1557-7341"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Computing Surveys","raw_type":"journal-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/A5024068814","display_name":"Xiaoguang Qi","orcid":"https://orcid.org/0000-0002-3465-9482"},"institutions":[{"id":"https://openalex.org/I186143895","display_name":"Lehigh University","ror":"https://ror.org/012afjb06","country_code":"US","type":"education","lineage":["https://openalex.org/I186143895"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaoguang Qi","raw_affiliation_strings":["Lehigh University, Bethlehem, PA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lehigh University, Bethlehem, PA","institution_ids":["https://openalex.org/I186143895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042328810","display_name":"Brian D. Davison","orcid":"https://orcid.org/0000-0002-9326-3648"},"institutions":[{"id":"https://openalex.org/I186143895","display_name":"Lehigh University","ror":"https://ror.org/012afjb06","country_code":"US","type":"education","lineage":["https://openalex.org/I186143895"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brian D. Davison","raw_affiliation_strings":["Lehigh University, Bethlehem, PA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lehigh University, Bethlehem, PA","institution_ids":["https://openalex.org/I186143895"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I186143895"],"apc_list":null,"apc_paid":null,"fwci":154.6726,"has_fulltext":false,"cited_by_count":432,"citation_normalized_percentile":{"value":0.99960411,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"41","issue":"2","first_page":"1","last_page":"31"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9975000023841858,"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":0.9890999794006348,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.883045494556427},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.7296616435050964},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.6988784074783325},{"id":"https://openalex.org/keywords/static-web-page","display_name":"Static web page","score":0.6495449542999268},{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.5993385910987854},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5897151827812195},{"id":"https://openalex.org/keywords/web-navigation","display_name":"Web navigation","score":0.5170708298683167},{"id":"https://openalex.org/keywords/hypertext","display_name":"Hypertext","score":0.5150780081748962},{"id":"https://openalex.org/keywords/data-web","display_name":"Data Web","score":0.4994387626647949},{"id":"https://openalex.org/keywords/web-development","display_name":"Web development","score":0.4698913097381592},{"id":"https://openalex.org/keywords/web-mining","display_name":"Web mining","score":0.4695863127708435},{"id":"https://openalex.org/keywords/web-standards","display_name":"Web standards","score":0.4585113525390625},{"id":"https://openalex.org/keywords/web-modeling","display_name":"Web modeling","score":0.4500851035118103}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.883045494556427},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.7296616435050964},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.6988784074783325},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.6495449542999268},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.5993385910987854},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5897151827812195},{"id":"https://openalex.org/C61096286","wikidata":"https://www.wikidata.org/wiki/Q7978592","display_name":"Web navigation","level":3,"score":0.5170708298683167},{"id":"https://openalex.org/C162215914","wikidata":"https://www.wikidata.org/wiki/Q93241","display_name":"Hypertext","level":2,"score":0.5150780081748962},{"id":"https://openalex.org/C162005631","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Data Web","level":3,"score":0.4994387626647949},{"id":"https://openalex.org/C79373723","wikidata":"https://www.wikidata.org/wiki/Q386275","display_name":"Web development","level":3,"score":0.4698913097381592},{"id":"https://openalex.org/C197046077","wikidata":"https://www.wikidata.org/wiki/Q785337","display_name":"Web mining","level":3,"score":0.4695863127708435},{"id":"https://openalex.org/C182321512","wikidata":"https://www.wikidata.org/wiki/Q1153289","display_name":"Web standards","level":3,"score":0.4585113525390625},{"id":"https://openalex.org/C130436687","wikidata":"https://www.wikidata.org/wiki/Q7978591","display_name":"Web modeling","level":3,"score":0.4500851035118103},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1459352.1459357","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1459352.1459357","pdf_url":null,"source":{"id":"https://openalex.org/S157921468","display_name":"ACM Computing Surveys","issn_l":"0360-0300","issn":["0360-0300","1557-7341"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Computing Surveys","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.800000011920929,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G6284682955","display_name":null,"funder_award_id":"IIS-0328825","funder_id":"https://openalex.org/F4320337389","funder_display_name":"Division of Information and Intelligent Systems"}],"funders":[{"id":"https://openalex.org/F4320337389","display_name":"Division of Information and Intelligent Systems","ror":"https://ror.org/053a2cp42"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":180,"referenced_works":["https://openalex.org/W4627272","https://openalex.org/W23905605","https://openalex.org/W28412257","https://openalex.org/W40914139","https://openalex.org/W46587594","https://openalex.org/W103965747","https://openalex.org/W140890161","https://openalex.org/W157719725","https://openalex.org/W163587274","https://openalex.org/W1482260847","https://openalex.org/W1489992655","https://openalex.org/W1491658408","https://openalex.org/W1503141391","https://openalex.org/W1506845741","https://openalex.org/W1511546282","https://openalex.org/W1532285064","https://openalex.org/W1541840304","https://openalex.org/W1549874165","https://openalex.org/W1554796723","https://openalex.org/W1558302528","https://openalex.org/W1563243329","https://openalex.org/W1571603666","https://openalex.org/W1575736368","https://openalex.org/W1587718046","https://openalex.org/W1595222087","https://openalex.org/W1596622341","https://openalex.org/W1600036847","https://openalex.org/W1612003148","https://openalex.org/W1676820704","https://openalex.org/W1711700449","https://openalex.org/W1815110991","https://openalex.org/W1854214752","https://openalex.org/W1908728294","https://openalex.org/W1956559956","https://openalex.org/W1966982551","https://openalex.org/W1967160701","https://openalex.org/W1972645849","https://openalex.org/W1976502741","https://openalex.org/W1977733111","https://openalex.org/W1979584682","https://openalex.org/W1979622972","https://openalex.org/W1979974203","https://openalex.org/W1989993068","https://openalex.org/W1994589572","https://openalex.org/W1997749914","https://openalex.org/W1997943123","https://openalex.org/W1998196377","https://openalex.org/W2000145992","https://openalex.org/W2000900876","https://openalex.org/W2003471189","https://openalex.org/W2004194926","https://openalex.org/W2007278710","https://openalex.org/W2007395264","https://openalex.org/W2008781077","https://openalex.org/W2011265791","https://openalex.org/W2011442902","https://openalex.org/W2012516036","https://openalex.org/W2013316690","https://openalex.org/W2014134732","https://openalex.org/W2017102965","https://openalex.org/W2022177107","https://openalex.org/W2023607075","https://openalex.org/W2023991263","https://openalex.org/W2025047573","https://openalex.org/W2025117268","https://openalex.org/W2029296527","https://openalex.org/W2032304665","https://openalex.org/W2033747448","https://openalex.org/W2035411645","https://openalex.org/W2036100275","https://openalex.org/W2041179002","https://openalex.org/W2043353538","https://openalex.org/W2043747172","https://openalex.org/W2047053749","https://openalex.org/W2047221353","https://openalex.org/W2048679005","https://openalex.org/W2050028965","https://openalex.org/W2050559027","https://openalex.org/W2054804336","https://openalex.org/W2055354597","https://openalex.org/W2063862666","https://openalex.org/W2065168033","https://openalex.org/W2067223933","https://openalex.org/W2070920590","https://openalex.org/W2071415686","https://openalex.org/W2073448073","https://openalex.org/W2076008912","https://openalex.org/W2077122984","https://openalex.org/W2077167900","https://openalex.org/W2086004682","https://openalex.org/W2092231883","https://openalex.org/W2092689128","https://openalex.org/W2092906664","https://openalex.org/W2094400120","https://openalex.org/W2096018540","https://openalex.org/W2097720891","https://openalex.org/W2098034778","https://openalex.org/W2098045186","https://openalex.org/W2098876286","https://openalex.org/W2100335205","https://openalex.org/W2101005742","https://openalex.org/W2101538110","https://openalex.org/W2105102731","https://openalex.org/W2105324886","https://openalex.org/W2107269684","https://openalex.org/W2107743791","https://openalex.org/W2108346334","https://openalex.org/W2108671511","https://openalex.org/W2109438061","https://openalex.org/W2110224739","https://openalex.org/W2111689752","https://openalex.org/W2112335400","https://openalex.org/W2113043986","https://openalex.org/W2117225622","https://openalex.org/W2118020653","https://openalex.org/W2118603198","https://openalex.org/W2118889948","https://openalex.org/W2121290184","https://openalex.org/W2121672615","https://openalex.org/W2121715962","https://openalex.org/W2123827533","https://openalex.org/W2124168655","https://openalex.org/W2124868070","https://openalex.org/W2125098710","https://openalex.org/W2125398996","https://openalex.org/W2126795521","https://openalex.org/W2130196635","https://openalex.org/W2132329793","https://openalex.org/W2134131174","https://openalex.org/W2137253512","https://openalex.org/W2140809065","https://openalex.org/W2143331230","https://openalex.org/W2147152072","https://openalex.org/W2148572968","https://openalex.org/W2152814537","https://openalex.org/W2153390303","https://openalex.org/W2153914519","https://openalex.org/W2156772624","https://openalex.org/W2158140178","https://openalex.org/W2158324310","https://openalex.org/W2159082584","https://openalex.org/W2160368903","https://openalex.org/W2162438644","https://openalex.org/W2166601255","https://openalex.org/W2167044614","https://openalex.org/W2167403283","https://openalex.org/W2167894050","https://openalex.org/W2168540192","https://openalex.org/W2169270715","https://openalex.org/W2170344111","https://openalex.org/W2170602716","https://openalex.org/W2182824764","https://openalex.org/W2189067371","https://openalex.org/W2395980234","https://openalex.org/W2398854657","https://openalex.org/W2408674741","https://openalex.org/W2426031434","https://openalex.org/W2435251607","https://openalex.org/W2487087946","https://openalex.org/W2503170438","https://openalex.org/W2503755628","https://openalex.org/W2561675875","https://openalex.org/W2608239929","https://openalex.org/W2612346562","https://openalex.org/W2912753362","https://openalex.org/W2978329087","https://openalex.org/W2999060954","https://openalex.org/W3017143921","https://openalex.org/W3165850736","https://openalex.org/W4212774754","https://openalex.org/W4233135949","https://openalex.org/W4249653116","https://openalex.org/W4285719527","https://openalex.org/W6601924087","https://openalex.org/W6636808696","https://openalex.org/W6640862754","https://openalex.org/W6649554654","https://openalex.org/W6712710312","https://openalex.org/W6738852829","https://openalex.org/W6980646113"],"related_works":["https://openalex.org/W2015727217","https://openalex.org/W163338125","https://openalex.org/W2415191659","https://openalex.org/W2744329849","https://openalex.org/W2567626003","https://openalex.org/W2563863560","https://openalex.org/W4224286275","https://openalex.org/W2472862012","https://openalex.org/W3139873369","https://openalex.org/W2520851676"],"abstract_inverted_index":{"Classification":[0],"of":[1,25,45,67,84],"Web":[2,11,17,26,32,60],"page":[3,33,61],"content":[4,27],"is":[5],"essential":[6],"to":[7,31,37],"many":[8],"tasks":[9],"in":[10,59],"information":[12,85],"retrieval":[13],"such":[14],"as":[15,35],"maintaining":[16],"directories":[18],"and":[19,71,76],"focused":[20],"crawling.":[21],"The":[22],"uncontrolled":[23],"nature":[24,44],"presents":[28],"additional":[29],"challenges":[30],"classification":[34],"compared":[36],"traditional":[38],"text":[39],"classification,":[40,62],"but":[41],"the":[42,53,65,78,82],"interconnected":[43],"hypertext":[46],"also":[47],"provides":[48],"features":[49,70],"that":[50],"can":[51],"assist":[52],"process.":[54],"As":[55],"we":[56,63],"review":[57],"work":[58],"note":[64],"importance":[66],"these":[68],"Web-specific":[69],"algorithms,":[72],"describe":[73],"state-of-the-art":[74],"practices,":[75],"track":[77],"underlying":[79],"assumptions":[80],"behind":[81],"use":[83],"from":[86],"neighboring":[87],"pages.":[88]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":28},{"year":2020,"cited_by_count":20},{"year":2019,"cited_by_count":22},{"year":2018,"cited_by_count":15},{"year":2017,"cited_by_count":22},{"year":2016,"cited_by_count":23},{"year":2015,"cited_by_count":41},{"year":2014,"cited_by_count":53},{"year":2013,"cited_by_count":39},{"year":2012,"cited_by_count":47}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}