{"id":"https://openalex.org/W2251787445","doi":"https://doi.org/10.3115/v1/w14-3706","title":"Semi-supervised Graph-based Genre Classification for Web Pages","display_name":"Semi-supervised Graph-based Genre Classification for Web Pages","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W2251787445","doi":"https://doi.org/10.3115/v1/w14-3706","mag":"2251787445"},"language":"en","primary_location":{"id":"doi:10.3115/v1/w14-3706","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-3706","pdf_url":"https://aclanthology.org/W14-3706.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of TextGraphs-9: the workshop on Graph-based Methods for Natural Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/W14-3706.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026242952","display_name":"Noushin Rezapour Asheghi","orcid":null},"institutions":[{"id":"https://openalex.org/I130828816","display_name":"University of Leeds","ror":"https://ror.org/024mrxd33","country_code":"GB","type":"education","lineage":["https://openalex.org/I130828816"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Noushin Rezapour Asheghi","raw_affiliation_strings":["University of Leeds"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Leeds","institution_ids":["https://openalex.org/I130828816"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082971401","display_name":"Katja Markert","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136150","display_name":"L3S Research Center","ror":"https://ror.org/039t4wk02","country_code":"DE","type":"facility","lineage":["https://openalex.org/I114112103","https://openalex.org/I4210136150","https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Katja Markert","raw_affiliation_strings":["L3S Research Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"L3S Research Center","institution_ids":["https://openalex.org/I4210136150"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072701587","display_name":"Serge Sharoff","orcid":"https://orcid.org/0000-0002-4877-0210"},"institutions":[{"id":"https://openalex.org/I130828816","display_name":"University of Leeds","ror":"https://ror.org/024mrxd33","country_code":"GB","type":"education","lineage":["https://openalex.org/I130828816"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Serge Sharoff","raw_affiliation_strings":["University of Leeds"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Leeds","institution_ids":["https://openalex.org/I130828816"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6916,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.88416796,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"39","last_page":"47"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12380","display_name":"Authorship Attribution and Profiling","score":0.9997000098228455,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.9997000098228455,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9995999932289124,"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/T10028","display_name":"Topic Modeling","score":0.9990000128746033,"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/computer-science","display_name":"Computer science","score":0.7980653643608093},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7466985583305359},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6331577897071838},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5538090467453003},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5498587489128113},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5469465851783752},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.502896249294281},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.41315943002700806},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.40584999322891235},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3370369076728821},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.17264005541801453},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09043991565704346},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.06945383548736572}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7980653643608093},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7466985583305359},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6331577897071838},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5538090467453003},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5498587489128113},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5469465851783752},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.502896249294281},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.41315943002700806},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.40584999322891235},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3370369076728821},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.17264005541801453},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09043991565704346},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.06945383548736572},{"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3115/v1/w14-3706","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-3706","pdf_url":"https://aclanthology.org/W14-3706.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of TextGraphs-9: the workshop on Graph-based Methods for Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.3115/v1/w14-3706","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-3706","pdf_url":"https://aclanthology.org/W14-3706.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of TextGraphs-9: the workshop on Graph-based Methods for Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.7300000190734863,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2251787445.pdf"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W1585385982","https://openalex.org/W1607545660","https://openalex.org/W1975879668","https://openalex.org/W1978181142","https://openalex.org/W1996430422","https://openalex.org/W2019416425","https://openalex.org/W2027582570","https://openalex.org/W2038201841","https://openalex.org/W2045455073","https://openalex.org/W2059586463","https://openalex.org/W2061130579","https://openalex.org/W2066259047","https://openalex.org/W2071238250","https://openalex.org/W2076008912","https://openalex.org/W2097606805","https://openalex.org/W2111603694","https://openalex.org/W2137253512","https://openalex.org/W2140676672","https://openalex.org/W2143516773","https://openalex.org/W2146888100","https://openalex.org/W2153547334","https://openalex.org/W2153959628","https://openalex.org/W2167044614","https://openalex.org/W2185268784","https://openalex.org/W2252247958","https://openalex.org/W2407873558","https://openalex.org/W2626786574","https://openalex.org/W2949696181"],"related_works":["https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W4205463238","https://openalex.org/W2761785940","https://openalex.org/W1482209366","https://openalex.org/W2110523656","https://openalex.org/W2521627374","https://openalex.org/W2981954115"],"abstract_inverted_index":{"Until":[0],"now,":[1],"it":[2,125],"is":[3,103],"still":[4],"unclear":[5],"which":[6,36,102],"set":[7,25,80],"of":[8,26,33,81,86,97],"features":[9,35,52,69],"produces":[10],"the":[11,19,23,40,44,84,89,95,119],"best":[12],"result":[13],"in":[14,22,64,107],"automatic":[15],"genre":[16,65,108,121,129],"classification":[17,66,122],"on":[18],"web.":[20],"Therefore,":[21],"first":[24],"experiments,":[27,82],"we":[28,93],"compared":[29,67],"a":[30,78,98,104],"wide":[31],"range":[32],"contentbased":[34],"are":[37],"extracted":[38],"from":[39,88,133],"data":[41],"appearing":[42],"within":[43],"web":[45,91],"pages.":[46],"The":[47,110],"results":[48,111],"show":[49,112],"that":[50,113,127],"lexical":[51],"such":[53,70],"as":[54,71],"word":[55],"unigrams":[56],"and":[57,74],"character":[58],"n-grams":[59,73],"have":[60],"more":[61,132],"discriminative":[62],"power":[63],"to":[68],"part-of-speech":[72],"text":[75],"statistics.":[76],"In":[77],"second":[79],"with":[83],"aim":[85],"learning":[87],"neighbouring":[90],"pages,":[92],"investigated":[94],"performance":[96],"semi-supervised":[99,115],"graphbased":[100],"model,":[101],"novel":[105],"technique":[106],"classification.":[109],"our":[114],"min-cut":[116],"algorithm":[117],"improves":[118],"overall":[120],"accuracy.":[123],"However,":[124],"seems":[126],"some":[128],"classes":[130],"benefit":[131],"this":[134],"graph-based":[135],"model":[136],"than":[137],"others.":[138]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}