{"id":"https://openalex.org/W2145049651","doi":"https://doi.org/10.1145/1526709.1526798","title":"Extracting key terms from noisy and multitheme documents","display_name":"Extracting key terms from noisy and multitheme documents","publication_year":2009,"publication_date":"2009-04-20","ids":{"openalex":"https://openalex.org/W2145049651","doi":"https://doi.org/10.1145/1526709.1526798","mag":"2145049651"},"language":"en","primary_location":{"id":"doi:10.1145/1526709.1526798","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1526709.1526798","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":"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/A5031395328","display_name":"Maria Grineva","orcid":null},"institutions":[{"id":"https://openalex.org/I4210140184","display_name":"Institute of Social and Economic Studies of Population","ror":"https://ror.org/03cdkd641","country_code":"RU","type":"facility","lineage":["https://openalex.org/I1313323035","https://openalex.org/I4210140184"]}],"countries":["RU"],"is_corresponding":true,"raw_author_name":"Maria Grineva","raw_affiliation_strings":["ISP RAS, Moscow, Russian Fed"],"affiliations":[{"raw_affiliation_string":"ISP RAS, Moscow, Russian Fed","institution_ids":["https://openalex.org/I4210140184"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108451635","display_name":"Maxim Grinev","orcid":null},"institutions":[{"id":"https://openalex.org/I4210140184","display_name":"Institute of Social and Economic Studies of Population","ror":"https://ror.org/03cdkd641","country_code":"RU","type":"facility","lineage":["https://openalex.org/I1313323035","https://openalex.org/I4210140184"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Maxim Grinev","raw_affiliation_strings":["ISP RAS, Moscow, Russian Fed"],"affiliations":[{"raw_affiliation_string":"ISP RAS, Moscow, Russian Fed","institution_ids":["https://openalex.org/I4210140184"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031099526","display_name":"Dmitry Lizorkin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210140184","display_name":"Institute of Social and Economic Studies of Population","ror":"https://ror.org/03cdkd641","country_code":"RU","type":"facility","lineage":["https://openalex.org/I1313323035","https://openalex.org/I4210140184"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Dmitry Lizorkin","raw_affiliation_strings":["ISP RAS, Moscow, Russian Fed"],"affiliations":[{"raw_affiliation_string":"ISP RAS, Moscow, Russian Fed","institution_ids":["https://openalex.org/I4210140184"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5031395328"],"corresponding_institution_ids":["https://openalex.org/I4210140184"],"apc_list":null,"apc_paid":null,"fwci":21.1739,"has_fulltext":false,"cited_by_count":267,"citation_normalized_percentile":{"value":0.99505723,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"661","last_page":"670"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9991000294685364,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9991000294685364,"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/T10064","display_name":"Complex Network Analysis Techniques","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9934999942779541,"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":0.7115452289581299},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.7106122374534607},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4232051968574524},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.41812556982040405},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3788910508155823},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.07969045639038086}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7115452289581299},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.7106122374534607},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4232051968574524},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.41812556982040405},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3788910508155823},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.07969045639038086}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1526709.1526798","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1526709.1526798","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":[{"score":0.5600000023841858,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W158057341","https://openalex.org/W177984263","https://openalex.org/W950821216","https://openalex.org/W1525595230","https://openalex.org/W1574901103","https://openalex.org/W1580825123","https://openalex.org/W1586197708","https://openalex.org/W1832927598","https://openalex.org/W1907578970","https://openalex.org/W1960027552","https://openalex.org/W1971224531","https://openalex.org/W1978394996","https://openalex.org/W1991862576","https://openalex.org/W2027800842","https://openalex.org/W2047940964","https://openalex.org/W2062021443","https://openalex.org/W2066636486","https://openalex.org/W2088209891","https://openalex.org/W2095293504","https://openalex.org/W2120779048","https://openalex.org/W2128809169","https://openalex.org/W2131357087","https://openalex.org/W2138621811","https://openalex.org/W2153702741","https://openalex.org/W2156577800","https://openalex.org/W3151019514","https://openalex.org/W6607321472","https://openalex.org/W6683098028","https://openalex.org/W7015831105"],"related_works":["https://openalex.org/W2357241418","https://openalex.org/W2329452785","https://openalex.org/W2356380379","https://openalex.org/W2789919619","https://openalex.org/W2086064646","https://openalex.org/W2119135658","https://openalex.org/W2363925233","https://openalex.org/W2115485936","https://openalex.org/W2293457016","https://openalex.org/W3022131925"],"abstract_inverted_index":{"We":[0,29,71,87],"present":[1],"a":[2,19,89],"novel":[3],"method":[4],"for":[5],"key":[6,97],"term":[7],"extraction":[8],"from":[9,117],"text":[10],"documents.":[11],"In":[12],"our":[13],"method,":[14],"document":[15,47],"is":[16],"modeled":[17],"as":[18],"graph":[20,73,80],"of":[21,26,35,45,85],"semantic":[22,109],"relationships":[23],"between":[24,111],"terms":[25,39,60,98,106],"that":[27,95],"document.":[28],"exploit":[30,114],"the":[31,36,38,42,46,79],"following":[32],"remarkable":[33],"feature":[34],"graph:":[37],"related":[40],"to":[41,49,77,92],"main":[43],"topics":[44],"tend":[48],"bunch":[50],"up":[51],"into":[52,62,81],"densely":[53],"interconnected":[54,64],"subgraphs":[55],"or":[56,66],"communities,":[57,65],"while":[58],"non-important":[59],"fall":[61],"weakly":[63],"even":[67],"become":[68],"isolated":[69],"vertices.":[70],"apply":[72],"community":[74],"detection":[75],"techniques":[76],"partition":[78],"thematically":[82],"cohesive":[83],"groups":[84,94,100],"terms.":[86,103],"introduce":[88],"criterion":[90],"function":[91],"select":[93],"contain":[96],"discarding":[99],"with":[101],"unimportant":[102],"To":[104],"weight":[105],"and":[107],"determine":[108],"relatedness":[110],"them":[112],"we":[113],"information":[115],"extracted":[116],"Wikipedia.":[118]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":19},{"year":2020,"cited_by_count":19},{"year":2019,"cited_by_count":30},{"year":2018,"cited_by_count":18},{"year":2017,"cited_by_count":24},{"year":2016,"cited_by_count":19},{"year":2015,"cited_by_count":22},{"year":2014,"cited_by_count":19},{"year":2013,"cited_by_count":19},{"year":2012,"cited_by_count":14}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}