{"id":"https://openalex.org/W2008781077","doi":"https://doi.org/10.1145/1013367.1013426","title":"Web page classification without the web page","display_name":"Web page classification without the web page","publication_year":2004,"publication_date":"2004-01-01","ids":{"openalex":"https://openalex.org/W2008781077","doi":"https://doi.org/10.1145/1013367.1013426","mag":"2008781077"},"language":"en","primary_location":{"id":"doi:10.1145/1013367.1013426","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1013367.1013426","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th international World Wide Web conference on Alternate track papers &amp; posters  - WWW Alt. '04","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/A5066305082","display_name":"Min\u2010Yen Kan","orcid":"https://orcid.org/0000-0001-8507-3716"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Min-Yen Kan","raw_affiliation_strings":["National University of Singapore, Singapore","Nat. Univ. of Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"Nat. Univ. of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5066305082"],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":13.4141,"has_fulltext":false,"cited_by_count":79,"citation_normalized_percentile":{"value":0.9825373,"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":"262","last_page":"262"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9983000159263611,"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":0.9983000159263611,"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":0.9976999759674072,"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":0.9915000200271606,"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":0.8082994818687439},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.7559617161750793},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6733777523040771},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.629762589931488},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6135226488113403},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.5958278775215149},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5924786925315857},{"id":"https://openalex.org/keywords/web-resource","display_name":"Web resource","score":0.49170857667922974},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.436906635761261},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1483645737171173}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8082994818687439},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.7559617161750793},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6733777523040771},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.629762589931488},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6135226488113403},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.5958278775215149},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5924786925315857},{"id":"https://openalex.org/C65603577","wikidata":"https://www.wikidata.org/wiki/Q3427877","display_name":"Web resource","level":2,"score":0.49170857667922974},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.436906635761261},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1483645737171173},{"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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1013367.1013426","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1013367.1013426","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th international World Wide Web conference on Alternate track papers &amp; posters  - WWW Alt. '04","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"display_name":"Partnerships for the goals","id":"https://metadata.un.org/sdg/17"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W1510372738","https://openalex.org/W2067223933","https://openalex.org/W2293546693"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2592441986","https://openalex.org/W2051135816","https://openalex.org/W4244960141","https://openalex.org/W2017955920","https://openalex.org/W1963973829","https://openalex.org/W2113987729","https://openalex.org/W1827945352","https://openalex.org/W3213612967","https://openalex.org/W2884859571"],"abstract_inverted_index":{"Uniform":[0],"resource":[1,10],"locators":[2],"(URLs),":[3],"which":[4,54],"mark":[5],"the":[6,12,23,26,31,56,59],"address":[7],"of":[8,25,33,42,58],"a":[9,39],"on":[11],"World":[13],"Wide":[14],"Web,":[15],"are":[16],"often":[17],"human-readable":[18],"and":[19,45],"can":[20],"hint":[21],"at":[22],"category":[24],"resource.":[27],"This":[28],"paper":[29],"explores":[30],"use":[32],"URLs":[34],"for":[35],"webpage":[36],"categorization":[37],"via":[38],"two-phase":[40],"pipeline":[41],"word":[43],"segmentation/expansion":[44],"classification.":[46],"We":[47],"quantify":[48],"its":[49],"performance":[50],"against":[51],"document-based":[52],"methods,":[53],"require":[55],"retrieval":[57],"source":[60],"document.":[61]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":8},{"year":2012,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
