{"id":"https://openalex.org/W4242974827","doi":"https://doi.org/10.1002/asi.20341","title":"Finding nuggets in documents: A machine learning approach","display_name":"Finding nuggets in documents: A machine learning approach","publication_year":2006,"publication_date":"2006-02-17","ids":{"openalex":"https://openalex.org/W4242974827","doi":"https://doi.org/10.1002/asi.20341"},"language":"en","primary_location":{"id":"doi:10.1002/asi.20341","is_oa":true,"landing_page_url":"https://doi.org/10.1002/asi.20341","pdf_url":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/asi.20341","source":{"id":"https://openalex.org/S80113298","display_name":"Journal of the American Society for Information Science and Technology","issn_l":"1532-2882","issn":["1532-2882","1532-2890"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of the American Society for Information Science and Technology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/asi.20341","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101636289","display_name":"Yifang Wu","orcid":"https://orcid.org/0000-0002-9731-3155"},"institutions":[{"id":"https://openalex.org/I118118575","display_name":"New Jersey Institute of Technology","ror":"https://ror.org/05e74xb87","country_code":"US","type":"education","lineage":["https://openalex.org/I118118575"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yi\u2010fang Brook Wu","raw_affiliation_strings":["Information Systems Department, New Jersey Institute of Technology, Newark, NJ 07102"],"affiliations":[{"raw_affiliation_string":"Information Systems Department, New Jersey Institute of Technology, Newark, NJ 07102","institution_ids":["https://openalex.org/I118118575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048436051","display_name":"Quanzhi Li","orcid":"https://orcid.org/0000-0002-4605-4237"},"institutions":[{"id":"https://openalex.org/I118118575","display_name":"New Jersey Institute of Technology","ror":"https://ror.org/05e74xb87","country_code":"US","type":"education","lineage":["https://openalex.org/I118118575"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Quanzhi Li","raw_affiliation_strings":["Information Systems Department, New Jersey Institute of Technology, Newark, NJ 07102"],"affiliations":[{"raw_affiliation_string":"Information Systems Department, New Jersey Institute of Technology, Newark, NJ 07102","institution_ids":["https://openalex.org/I118118575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111387168","display_name":"Razvan Stefan Bot","orcid":null},"institutions":[{"id":"https://openalex.org/I118118575","display_name":"New Jersey Institute of Technology","ror":"https://ror.org/05e74xb87","country_code":"US","type":"education","lineage":["https://openalex.org/I118118575"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Razvan Stefan Bot","raw_affiliation_strings":["Information Systems Department, New Jersey Institute of Technology, Newark, NJ 07102"],"affiliations":[{"raw_affiliation_string":"Information Systems Department, New Jersey Institute of Technology, Newark, NJ 07102","institution_ids":["https://openalex.org/I118118575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100638657","display_name":"Xin Chen","orcid":"https://orcid.org/0000-0002-0747-1361"},"institutions":[{"id":"https://openalex.org/I118118575","display_name":"New Jersey Institute of Technology","ror":"https://ror.org/05e74xb87","country_code":"US","type":"education","lineage":["https://openalex.org/I118118575"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xin Chen","raw_affiliation_strings":["Information Systems Department, New Jersey Institute of Technology, Newark, NJ 07102"],"affiliations":[{"raw_affiliation_string":"Information Systems Department, New Jersey Institute of Technology, Newark, NJ 07102","institution_ids":["https://openalex.org/I118118575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101636289"],"corresponding_institution_ids":["https://openalex.org/I118118575"],"apc_list":null,"apc_paid":null,"fwci":0.9304,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.8341748,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"57","issue":"6","first_page":"740","last_page":"752"},"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.9219574928283691},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.7465168833732605},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7259186506271362},{"id":"https://openalex.org/keywords/personalization","display_name":"Personalization","score":0.5239738821983337},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.5078526139259338},{"id":"https://openalex.org/keywords/thesaurus","display_name":"Thesaurus","score":0.5004715919494629},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.47341519594192505},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.471508651971817},{"id":"https://openalex.org/keywords/automatic-indexing","display_name":"Automatic indexing","score":0.4573208689689636},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.4498072862625122},{"id":"https://openalex.org/keywords/glossary","display_name":"Glossary","score":0.44779208302497864},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.4431416988372803},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.4146284759044647},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3460503816604614},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33413904905319214},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.29362380504608154}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9219574928283691},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.7465168833732605},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7259186506271362},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.5239738821983337},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.5078526139259338},{"id":"https://openalex.org/C2778698081","wikidata":"https://www.wikidata.org/wiki/Q179797","display_name":"Thesaurus","level":2,"score":0.5004715919494629},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.47341519594192505},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.471508651971817},{"id":"https://openalex.org/C2778330532","wikidata":"https://www.wikidata.org/wiki/Q4826577","display_name":"Automatic indexing","level":3,"score":0.4573208689689636},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.4498072862625122},{"id":"https://openalex.org/C2780031656","wikidata":"https://www.wikidata.org/wiki/Q859161","display_name":"Glossary","level":2,"score":0.44779208302497864},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.4431416988372803},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.4146284759044647},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3460503816604614},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33413904905319214},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29362380504608154},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1002/asi.20341","is_oa":true,"landing_page_url":"https://doi.org/10.1002/asi.20341","pdf_url":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/asi.20341","source":{"id":"https://openalex.org/S80113298","display_name":"Journal of the American Society for Information Science and Technology","issn_l":"1532-2882","issn":["1532-2882","1532-2890"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of the American Society for Information Science and Technology","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.512.5664","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.512.5664","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://web.njit.edu/~wu/research/Software/KIP/Papers/KIP_JASIST.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.1002/asi.20341","is_oa":true,"landing_page_url":"https://doi.org/10.1002/asi.20341","pdf_url":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/asi.20341","source":{"id":"https://openalex.org/S80113298","display_name":"Journal of the American Society for Information Science and Technology","issn_l":"1532-2882","issn":["1532-2882","1532-2890"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of the American Society for Information Science and Technology","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5299999713897705,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4242974827.pdf"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W110802701","https://openalex.org/W1580678109","https://openalex.org/W1975432235","https://openalex.org/W2034721576","https://openalex.org/W2049119796","https://openalex.org/W2060772621","https://openalex.org/W2069634543","https://openalex.org/W2069778239","https://openalex.org/W2071940869","https://openalex.org/W2085129404","https://openalex.org/W2089589285","https://openalex.org/W2093098531","https://openalex.org/W2099111195","https://openalex.org/W2145766604","https://openalex.org/W2153804780","https://openalex.org/W2153927559","https://openalex.org/W2163490678","https://openalex.org/W2524597696","https://openalex.org/W2912676594","https://openalex.org/W3144372880","https://openalex.org/W4235505822","https://openalex.org/W4238183243"],"related_works":["https://openalex.org/W2082470383","https://openalex.org/W2018548390","https://openalex.org/W2500077666","https://openalex.org/W2009051249","https://openalex.org/W2033237568","https://openalex.org/W2040347855","https://openalex.org/W1526322729","https://openalex.org/W2146030189","https://openalex.org/W266409346","https://openalex.org/W3080996507"],"abstract_inverted_index":{"Abstract":[0],"Document":[1],"keyphrases":[2,57,70,83,97,156],"provide":[3],"a":[4,8,15,51,89,123,141,168],"concise":[5],"summary":[6],"of":[7,37,54,103,116,176],"document's":[9],"content,":[10],"offering":[11],"semantic":[12],"metadata":[13],"summarizing":[14],"document.":[16],"They":[17],"can":[18,146],"be":[19],"used":[20],"in":[21],"many":[22],"applications":[23],"related":[24],"to":[25,67,71,76,80,107,110,157,193],"knowledge":[26],"management":[27],"and":[28,46,61,65,127,194],"text":[29,34],"mining,":[30],"such":[31],"as":[32],"automatic":[33],"summarization,":[35],"development":[36],"search":[38],"engines,":[39],"document":[40,42,96],"clustering,":[41],"classification,":[43],"thesaurus":[44],"construction,":[45],"browsing":[47],"interfaces.":[48],"Because":[49],"only":[50],"small":[52],"portion":[53],"documents":[55],"have":[56],"assigned":[58],"by":[59,98,151],"authors,":[60],"it":[62,73],"is":[63,74,140,186,199],"time\u2010consuming":[64],"costly":[66],"manually":[68],"assign":[69,108],"documents,":[72],"necessary":[75],"develop":[77],"an":[78],"algorithm":[79,118],"automatically":[81,152],"generate":[82],"for":[84,173],"documents.":[85],"This":[86],"paper":[87],"describes":[88],"Keyphrase":[90],"Identification":[91],"Program":[92],"(KIP),":[93],"which":[94],"extracts":[95],"using":[99],"prior":[100],"positive":[101],"samples":[102],"human":[104],"identified":[105,155],"phrases":[106],"weights":[109],"the":[111,128,134,148,158,165,174,189,196],"candidate":[112,124,138],"keyphrases.":[113],"The":[114,120,179],"logic":[115],"our":[117],"is:":[119],"more":[121,129,135],"keywords":[122,132],"keyphrase":[125],"contains":[126],"significant":[130],"these":[131],"are,":[133],"likely":[136],"this":[137],"phrase":[139],"keyphrase.":[142],"KIP's":[143,160,184],"learning":[144,197],"function":[145,198],"enrich":[147],"glossary":[149,169],"database":[150,170],"adding":[153],"new":[154],"database.":[159],"personalization":[161],"feature":[162],"will":[163],"let":[164],"user":[166],"build":[167],"specifically":[171],"suitable":[172],"area":[175],"his/her":[177],"interest.":[178],"evaluation":[180],"results":[181],"show":[182],"that":[183,195],"performance":[185],"better":[187],"than":[188],"systems":[190],"we":[191],"compared":[192],"effective.":[200]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
