{"id":"https://openalex.org/W2104040045","doi":"https://doi.org/10.1109/icdim.2008.4746816","title":"Extracting community structure features for hypertext classification","display_name":"Extracting community structure features for hypertext classification","publication_year":2008,"publication_date":"2008-11-01","ids":{"openalex":"https://openalex.org/W2104040045","doi":"https://doi.org/10.1109/icdim.2008.4746816","mag":"2104040045"},"language":"en","primary_location":{"id":"doi:10.1109/icdim.2008.4746816","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdim.2008.4746816","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 Third International Conference on Digital Information Management","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/A5015784640","display_name":"Dell Zhang","orcid":"https://orcid.org/0000-0002-8774-3725"},"institutions":[{"id":"https://openalex.org/I98259816","display_name":"Birkbeck, University of London","ror":"https://ror.org/02mb95055","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I98259816"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Dell Zhang","raw_affiliation_strings":["SCSIS Birkbeck, University of London, London, UK"],"affiliations":[{"raw_affiliation_string":"SCSIS Birkbeck, University of London, London, UK","institution_ids":["https://openalex.org/I98259816"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109101754","display_name":"Robert Mao","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4210109507","display_name":"Microsoft (Ireland)","ror":"https://ror.org/017fqk185","country_code":"IE","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210109507"]}],"countries":["IE","US"],"is_corresponding":false,"raw_author_name":"Robert Mao","raw_affiliation_strings":["EPDC5/2352, South County Business Park, Microsoft Corporation, Dublin, Ireland","Microsoft Corp., Leopardstown"],"affiliations":[{"raw_affiliation_string":"EPDC5/2352, South County Business Park, Microsoft Corporation, Dublin, Ireland","institution_ids":["https://openalex.org/I4210109507"]},{"raw_affiliation_string":"Microsoft Corp., Leopardstown","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5015784640"],"corresponding_institution_ids":["https://openalex.org/I98259816"],"apc_list":null,"apc_paid":null,"fwci":1.7598,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.87895158,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"436","last_page":"441"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9986000061035156,"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"}},"topics":[{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9986000061035156,"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":0.9861999750137329,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.98580002784729,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/hypertext","display_name":"Hypertext","score":0.8924683332443237},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8284006118774414},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6196960210800171},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5673596858978271},{"id":"https://openalex.org/keywords/modularity","display_name":"Modularity (biology)","score":0.5028743147850037},{"id":"https://openalex.org/keywords/document-classification","display_name":"Document classification","score":0.48783615231513977},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.39605334401130676},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3738820552825928},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35155996680259705}],"concepts":[{"id":"https://openalex.org/C162215914","wikidata":"https://www.wikidata.org/wiki/Q93241","display_name":"Hypertext","level":2,"score":0.8924683332443237},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8284006118774414},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6196960210800171},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5673596858978271},{"id":"https://openalex.org/C2779478453","wikidata":"https://www.wikidata.org/wiki/Q6889748","display_name":"Modularity (biology)","level":2,"score":0.5028743147850037},{"id":"https://openalex.org/C2780479914","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Document classification","level":2,"score":0.48783615231513977},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.39605334401130676},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3738820552825928},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35155996680259705},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icdim.2008.4746816","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdim.2008.4746816","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 Third International Conference on Digital Information Management","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.144.487","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.144.487","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.dcs.bbk.ac.uk/~dell/publications/dellzhang_icdim2008c.pdf","raw_type":"text"},{"id":"pmh:oai:eprints.bbk.ac.uk.oai2:7080","is_oa":false,"landing_page_url":"https://eprints.bbk.ac.uk/id/eprint/7080/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400466","display_name":"BIROn (Birkbeck, University of London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98259816","host_organization_name":"Birkbeck, University of London","host_organization_lineage":["https://openalex.org/I98259816"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Book Section"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5400000214576721}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W99849907","https://openalex.org/W1540550673","https://openalex.org/W1578099820","https://openalex.org/W1979584682","https://openalex.org/W2015953751","https://openalex.org/W2076008912","https://openalex.org/W2097308346","https://openalex.org/W2108346334","https://openalex.org/W2118020653","https://openalex.org/W2148606196","https://openalex.org/W2152814537","https://openalex.org/W2165922980","https://openalex.org/W6676036752"],"related_works":["https://openalex.org/W1536970214","https://openalex.org/W1565135491","https://openalex.org/W1815780662","https://openalex.org/W2897383060","https://openalex.org/W3126015170","https://openalex.org/W2378211422","https://openalex.org/W2264492131","https://openalex.org/W1791756088","https://openalex.org/W2050926388","https://openalex.org/W4230687177"],"abstract_inverted_index":{"Standard":[0],"text":[1],"classification":[2,38,77,134],"techniques":[3],"assume":[4],"that":[5,88,127],"all":[6],"documents":[7,16,41,53],"are":[8,21],"independent":[9],"and":[10,61,114],"identically":[11],"distributed":[12],"(i.i.d.).":[13],"However,":[14],"hypertext":[15,40,52],"such":[17,30,67],"as":[18,32,57],"web":[19],"pages":[20],"interconnected":[22,51],"with":[23,138],"links.":[24],"How":[25],"to":[26,35,132],"take":[27],"advantage":[28],"of":[29,39,50,66,78,120],"links":[31],"extra":[33],"evidences":[34],"enhance":[36],"automatic":[37],"is":[42,100],"a":[43,48,58,68,83],"non-trivial":[44],"problem.":[45],"We":[46],"think":[47],"collection":[49],"can":[54,89],"be":[55],"considered":[56],"complex":[59],"network,":[60],"the":[62,75,96,128,139],"underlying":[63],"community":[64,92],"structure":[65,93],"document":[69,97,103,112,115],"network":[70,98],"contains":[71],"valuable":[72],"clues":[73],"about":[74],"right":[76],"documents.":[79],"This":[80],"paper":[81],"introduces":[82],"new":[84],"technique,":[85],"Modularity":[86],"Eigenmap,":[87],"effectively":[90],"extract":[91],"features":[94],"from":[95,102],"which":[99],"induced":[101],"link":[104,116],"information":[105],"only":[106],"or":[107],"constructed":[108],"by":[109],"combining":[110],"both":[111],"content":[113],"information.":[117],"A":[118],"number":[119],"experiments":[121],"on":[122],"real-world":[123],"benchmark":[124],"datasets":[125],"show":[126],"proposed":[129],"approach":[130],"leads":[131],"excellent":[133],"performance":[135],"in":[136],"comparison":[137],"state-of-the-art":[140],"methods.":[141]},"counts_by_year":[],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}