{"id":"https://openalex.org/W2133549050","doi":"https://doi.org/10.1145/1526709.1526905","title":"Towards language-independent web genre detection","display_name":"Towards language-independent web genre detection","publication_year":2009,"publication_date":"2009-04-20","ids":{"openalex":"https://openalex.org/W2133549050","doi":"https://doi.org/10.1145/1526709.1526905","mag":"2133549050"},"language":"en","primary_location":{"id":"doi:10.1145/1526709.1526905","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1526709.1526905","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th international conference on World wide web","raw_type":"proceedings-article"},"type":"conference-paper","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/A5010197678","display_name":"Philipp Scholl","orcid":"https://orcid.org/0000-0001-6941-0161"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Philipp Scholl","raw_affiliation_strings":["Technische Universit\u00e4t Darmstadt, Darmstadt, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Universit\u00e4t Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111874045","display_name":"Renato Dom\u00ednguez Garc\u00eda","orcid":null},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Renato Dom\u00ednguez Garc\u00eda","raw_affiliation_strings":["Technische Universit\u00e4t Darmstadt, Darmstadt, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Universit\u00e4t Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108098419","display_name":"Doreen B\u00f6hnstedt","orcid":null},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Doreen B\u00f6hnstedt","raw_affiliation_strings":["Technische Universit\u00e4t Darmstadt, Darmstadt, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Universit\u00e4t Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009893898","display_name":"Christoph Rensing","orcid":"https://orcid.org/0000-0002-1287-216X"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christoph Rensing","raw_affiliation_strings":["Technische Universit\u00e4t Darmstadt, Darmstadt, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Universit\u00e4t Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004933128","display_name":"Ralf Steinmetz","orcid":"https://orcid.org/0000-0002-6839-9359"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ralf Steinmetz","raw_affiliation_strings":["Technische Universit\u00e4t Darmstadt, Darmstadt, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Universit\u00e4t Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I31512782"],"apc_list":null,"apc_paid":null,"fwci":0.4874,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.62722565,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1157","last_page":"1158"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12380","display_name":"Authorship Attribution and Profiling","score":0.973800003528595,"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":0.973800003528595,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9455999732017517,"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/T13629","display_name":"Text Readability and Simplification","score":0.9412000179290771,"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":0.8297507762908936},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6652313470840454},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6228135824203491},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.6128164529800415},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5931368470191956},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5440276861190796},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.46188706159591675},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4330673813819885},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.425489604473114},{"id":"https://openalex.org/keywords/web-modeling","display_name":"Web modeling","score":0.4181554913520813},{"id":"https://openalex.org/keywords/web-2.0","display_name":"Web 2.0","score":0.41150251030921936},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2526625096797943}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8297507762908936},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6652313470840454},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6228135824203491},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.6128164529800415},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5931368470191956},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5440276861190796},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.46188706159591675},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4330673813819885},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.425489604473114},{"id":"https://openalex.org/C130436687","wikidata":"https://www.wikidata.org/wiki/Q7978591","display_name":"Web modeling","level":3,"score":0.4181554913520813},{"id":"https://openalex.org/C136699151","wikidata":"https://www.wikidata.org/wiki/Q131164","display_name":"Web 2.0","level":3,"score":0.41150251030921936},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2526625096797943},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1526709.1526905","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1526709.1526905","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th international conference on World wide web","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7900000214576721,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W140890161","https://openalex.org/W2102247866","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2137912379","https://openalex.org/W2120222276","https://openalex.org/W143181582","https://openalex.org/W3025289787","https://openalex.org/W2404573736","https://openalex.org/W2167278502","https://openalex.org/W2036104219","https://openalex.org/W2389737178","https://openalex.org/W1986474863","https://openalex.org/W980488187"],"abstract_inverted_index":{"The":[0],"term":[1],"web":[2,10,28,47,90],"genre":[3],"denotes":[4],"the":[5,15,27,42,46,66],"type":[6],"of":[7,17,38,45,65,88],"a":[8,36,62,78,83],"given":[9],"resource,":[11],"in":[12,53],"contrast":[13,54],"to":[14,55,76],"topic":[16],"its":[18],"content.":[19,68],"In":[20],"this":[21],"research,":[22],"we":[23],"focus":[24],"on":[25,61],"recognizing":[26],"genres":[29],"blog,":[30],"wiki":[31],"and":[32,51],"forum.":[33],"We":[34],"present":[35],"set":[37],"features":[39],"that":[40,72],"exploit":[41],"hierarchical":[43],"structure":[44],"page's":[48,67],"HTML":[49],"mark-up":[50],"thus,":[52],"related":[56],"approaches,":[57],"do":[58],"not":[59],"depend":[60],"linguistic":[63],"analysis":[64],"Our":[69],"results":[70],"show":[71],"it":[73],"is":[74],"possible":[75],"achieve":[77],"very":[79],"good":[80],"accuracy":[81],"for":[82],"fully":[84],"language":[85],"independent":[86],"detection":[87],"structured":[89],"genres.":[91]},"counts_by_year":[{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
