{"id":"https://openalex.org/W2138954094","doi":"https://doi.org/10.1145/1097047.1097059","title":"Narrative text classification for automatic key phrase extraction in web document corpora","display_name":"Narrative text classification for automatic key phrase extraction in web document corpora","publication_year":2005,"publication_date":"2005-11-04","ids":{"openalex":"https://openalex.org/W2138954094","doi":"https://doi.org/10.1145/1097047.1097059","mag":"2138954094"},"language":"en","primary_location":{"id":"doi:10.1145/1097047.1097059","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1097047.1097059","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th annual ACM international workshop on Web information and data 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/A5100715816","display_name":"Yongzheng Zhang","orcid":"https://orcid.org/0009-0000-1077-3849"},"institutions":[{"id":"https://openalex.org/I129902397","display_name":"Dalhousie University","ror":"https://ror.org/01e6qks80","country_code":"CA","type":"education","lineage":["https://openalex.org/I129902397"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Yongzheng Zhang","raw_affiliation_strings":["Dalhousie University, Halifax, NS, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalhousie University, Halifax, NS, Canada","institution_ids":["https://openalex.org/I129902397"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008462534","display_name":"A. Nur Zincir\u2010Heywood","orcid":"https://orcid.org/0000-0003-2796-7265"},"institutions":[{"id":"https://openalex.org/I129902397","display_name":"Dalhousie University","ror":"https://ror.org/01e6qks80","country_code":"CA","type":"education","lineage":["https://openalex.org/I129902397"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Nur Zincir-Heywood","raw_affiliation_strings":["Dalhousie University, Halifax, NS, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalhousie University, Halifax, NS, Canada","institution_ids":["https://openalex.org/I129902397"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013989913","display_name":"Evangelos Milios","orcid":"https://orcid.org/0000-0001-5549-4675"},"institutions":[{"id":"https://openalex.org/I129902397","display_name":"Dalhousie University","ror":"https://ror.org/01e6qks80","country_code":"CA","type":"education","lineage":["https://openalex.org/I129902397"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Evangelos Milios","raw_affiliation_strings":["Dalhousie University, Halifax, NS, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalhousie University, Halifax, NS, Canada","institution_ids":["https://openalex.org/I129902397"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I129902397"],"apc_list":null,"apc_paid":null,"fwci":3.679,"has_fulltext":false,"cited_by_count":64,"citation_normalized_percentile":{"value":0.93329588,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"51","last_page":"58"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9835000038146973,"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/T10028","display_name":"Topic Modeling","score":0.957099974155426,"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":0.8151092529296875},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.7818738222122192},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6810391545295715},{"id":"https://openalex.org/keywords/plain-text","display_name":"Plain text","score":0.6215375065803528},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.6032755970954895},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5916821956634521},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.5859459042549133},{"id":"https://openalex.org/keywords/tf\u2013idf","display_name":"tf\u2013idf","score":0.5256208777427673},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5036117434501648},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.46591073274612427},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.4239785075187683},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.4219118654727936},{"id":"https://openalex.org/keywords/html-element","display_name":"HTML element","score":0.42008885741233826},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.41605618596076965},{"id":"https://openalex.org/keywords/keyword-extraction","display_name":"Keyword extraction","score":0.4110988676548004},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.39954760670661926},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3715318441390991},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.15514856576919556}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8151092529296875},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.7818738222122192},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6810391545295715},{"id":"https://openalex.org/C46503548","wikidata":"https://www.wikidata.org/wiki/Q1145976","display_name":"Plain text","level":3,"score":0.6215375065803528},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6032755970954895},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5916821956634521},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.5859459042549133},{"id":"https://openalex.org/C81758059","wikidata":"https://www.wikidata.org/wiki/Q796584","display_name":"tf\u2013idf","level":3,"score":0.5256208777427673},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5036117434501648},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.46591073274612427},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.4239785075187683},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.4219118654727936},{"id":"https://openalex.org/C81639021","wikidata":"https://www.wikidata.org/wiki/Q179551","display_name":"HTML element","level":3,"score":0.42008885741233826},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.41605618596076965},{"id":"https://openalex.org/C2780288562","wikidata":"https://www.wikidata.org/wiki/Q25053353","display_name":"Keyword extraction","level":2,"score":0.4110988676548004},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.39954760670661926},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3715318441390991},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.15514856576919556},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C148730421","wikidata":"https://www.wikidata.org/wiki/Q141090","display_name":"Encryption","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1097047.1097059","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1097047.1097059","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th annual ACM international workshop on Web information and data management","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.84.8798","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.84.8798","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://nike.psu.edu/widm05/p/p51-zhang.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5400000214576721,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W152176684","https://openalex.org/W1486865875","https://openalex.org/W1487148382","https://openalex.org/W1494273468","https://openalex.org/W1574901103","https://openalex.org/W1828830618","https://openalex.org/W1997841190","https://openalex.org/W2026642282","https://openalex.org/W2038670074","https://openalex.org/W2049107599","https://openalex.org/W2060772621","https://openalex.org/W2067879405","https://openalex.org/W2081687495","https://openalex.org/W2103759455","https://openalex.org/W2107828735","https://openalex.org/W2120474184","https://openalex.org/W2126032162","https://openalex.org/W2131345120","https://openalex.org/W2138621811","https://openalex.org/W2145766604","https://openalex.org/W2170758876","https://openalex.org/W6606141769","https://openalex.org/W6628983414","https://openalex.org/W6638437678","https://openalex.org/W6660343642"],"related_works":["https://openalex.org/W1997256148","https://openalex.org/W3186733304","https://openalex.org/W2343335642","https://openalex.org/W2795900462","https://openalex.org/W2069275471","https://openalex.org/W2251767200","https://openalex.org/W2384924398","https://openalex.org/W3083038004","https://openalex.org/W2997891576","https://openalex.org/W2035503345"],"abstract_inverted_index":{"Automatic":[0],"key":[1,24,73,91,134,165],"phrase":[2,74,166],"extraction":[3,75,167],"is":[4,47,161],"a":[5,118],"useful":[6],"tool":[7],"in":[8,53,68,76,117,168],"many":[9],"text":[10,28,66,97,103,140,151,159],"related":[11],"applications":[12],"such":[13,29],"as":[14,30],"clustering":[15],"and":[16,44,51,86,98,127],"summarization.":[17],"State-of-the-art":[18],"methods":[19,36],"are":[20,109,142],"aimed":[21],"towards":[22],"extracting":[23],"phrases":[25,92,135],"from":[26,93,99,137,148],"traditional":[27],"technical":[31],"papers.":[32],"Application":[33],"of":[34,48,64,71,104,124,152],"these":[35],"on":[37],"Web":[38,77,105,153,169],"documents,":[39],"which":[40],"often":[41],"contain":[42],"diverse":[43],"heterogeneous":[45],"contents,":[46],"particular":[49],"interest":[50],"challenge":[52],"the":[54,62,69,95,101,113,138],"information":[55],"age.":[56],"In":[57],"this":[58],"work,":[59],"we":[60],"investigate":[61],"significance":[63],"narrative":[65,102,139,158],"classification":[67,160],"task":[70],"automatic":[72],"document":[78,170],"corpora.":[79,171],"We":[80],"benchmark":[81],"three":[82],"methods,":[83],"TFIDF,":[84],"KEA,":[85],"Keyterm,":[87],"used":[88,110],"to":[89,111],"extract":[90],"all":[94,149],"plain":[96,150],"only":[100,141],"pages.":[106,154],"ANOVA":[107],"tests":[108],"analyze":[112],"ranking":[114],"data":[115],"collected":[116],"user":[119],"study":[120],"using":[121],"quantitative":[122],"measures":[123],"acceptable":[125],"percentage":[126],"quality":[128],"value.":[129],"The":[130],"evaluation":[131],"shows":[132],"that":[133,157],"extracted":[136],"significantly":[143],"better":[144],"than":[145],"those":[146],"obtained":[147],"This":[155],"demonstrates":[156],"indispensable":[162],"for":[163],"effective":[164]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":7},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":9}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}