{"id":"https://openalex.org/W2108937378","doi":"https://doi.org/10.1145/1401890.1401976","title":"Building semantic kernels for text classification using wikipedia","display_name":"Building semantic kernels for text classification using wikipedia","publication_year":2008,"publication_date":"2008-08-24","ids":{"openalex":"https://openalex.org/W2108937378","doi":"https://doi.org/10.1145/1401890.1401976","mag":"2108937378"},"language":"en","primary_location":{"id":"doi:10.1145/1401890.1401976","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1401890.1401976","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining","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/A5100383507","display_name":"Pu Wang","orcid":"https://orcid.org/0000-0001-8144-9755"},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Pu Wang","raw_affiliation_strings":["George Mason University, Fairfax, USA","George Mason University, Fairfax, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"George Mason University, Fairfax, USA","institution_ids":["https://openalex.org/I162714631"]},{"raw_affiliation_string":"George Mason University, Fairfax, USA#TAB#","institution_ids":["https://openalex.org/I162714631"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090148962","display_name":"Carlotta Domeniconi","orcid":"https://orcid.org/0000-0003-2140-9596"},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Carlotta Domeniconi","raw_affiliation_strings":["George Mason University, Fairfax, USA","George Mason University, Fairfax, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"George Mason University, Fairfax, USA","institution_ids":["https://openalex.org/I162714631"]},{"raw_affiliation_string":"George Mason University, Fairfax, USA#TAB#","institution_ids":["https://openalex.org/I162714631"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100383507"],"corresponding_institution_ids":["https://openalex.org/I162714631"],"apc_list":null,"apc_paid":null,"fwci":28.1562,"has_fulltext":false,"cited_by_count":205,"citation_normalized_percentile":{"value":0.99634818,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"713","last_page":"721"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","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"}},"topics":[{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9923999905586243,"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":0.989799976348877,"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":0.8212522268295288},{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.6175218820571899},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6052069664001465},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6048004031181335},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5884199142456055},{"id":"https://openalex.org/keywords/bag-of-words-model","display_name":"Bag-of-words model","score":0.5649851560592651},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5528518557548523},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5418413877487183},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.4628296196460724},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.4377378225326538},{"id":"https://openalex.org/keywords/document-classification","display_name":"Document classification","score":0.425689160823822},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4170769453048706},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4115193784236908}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8212522268295288},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.6175218820571899},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6052069664001465},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6048004031181335},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5884199142456055},{"id":"https://openalex.org/C13672336","wikidata":"https://www.wikidata.org/wiki/Q3460803","display_name":"Bag-of-words model","level":2,"score":0.5649851560592651},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5528518557548523},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5418413877487183},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.4628296196460724},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.4377378225326538},{"id":"https://openalex.org/C2780479914","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Document classification","level":2,"score":0.425689160823822},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4170769453048706},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4115193784236908},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"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/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1401890.1401976","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1401890.1401976","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7699999809265137,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W103965747","https://openalex.org/W130742730","https://openalex.org/W140312209","https://openalex.org/W1493526108","https://openalex.org/W1510073064","https://openalex.org/W1548663377","https://openalex.org/W1563088657","https://openalex.org/W1573149547","https://openalex.org/W1578881253","https://openalex.org/W1974406477","https://openalex.org/W1979015808","https://openalex.org/W2045117606","https://openalex.org/W2071664212","https://openalex.org/W2100335205","https://openalex.org/W2115023510","https://openalex.org/W2130913205","https://openalex.org/W2138861205","https://openalex.org/W2149684865","https://openalex.org/W2153635508","https://openalex.org/W2166706824","https://openalex.org/W2269043412","https://openalex.org/W2435251607","https://openalex.org/W2997501009","https://openalex.org/W3120421331","https://openalex.org/W3160981298","https://openalex.org/W4256361765","https://openalex.org/W6605363618"],"related_works":["https://openalex.org/W4286432911","https://openalex.org/W2970435854","https://openalex.org/W2945947799","https://openalex.org/W3175524270","https://openalex.org/W2289741972","https://openalex.org/W2580878117","https://openalex.org/W4296501933","https://openalex.org/W3043161732","https://openalex.org/W4251594503","https://openalex.org/W3036348210"],"abstract_inverted_index":{"Document":[0],"classification":[1,86,134],"presents":[2],"difficult":[3],"challenges":[4],"due":[5],"to":[6,17,71,80,114,138,143],"the":[7,10,18,22,47,51,56,82,93,96,116,139],"sparsity":[8],"and":[9,16,60,75,142],"high":[11],"dimensionality":[12],"of":[13,21,34,46,85,95,118],"text":[14],"data,":[15],"complex":[19],"semantics":[20],"natural":[23],"language.":[24],"The":[25],"traditional":[26],"document":[27],"representation":[28,64,117],"is":[29,41,69,111],"a":[30,44,107],"word-based":[31],"vector":[32],"(Bag":[33],"Words,":[35],"or":[36],"BOW),":[37],"where":[38],"each":[39],"dimension":[40],"associated":[42],"with":[43,123,136],"term":[45],"dictionary":[48],"containing":[49],"all":[50],"words":[52],"that":[53,128],"appear":[54],"in":[55,78],"corpus.":[57],"Although":[58],"simple":[59],"commonly":[61],"used,":[62],"this":[63,89],"has":[65],"several":[66],"limitations.":[67],"It":[68],"essential":[70],"embed":[72],"semantic":[73,108],"information":[74],"conceptual":[76],"patterns":[77],"order":[79],"enhance":[81],"prediction":[83],"capabilities":[84],"algorithms.":[87],"In":[88],"paper,":[90],"we":[91],"overcome":[92],"shortages":[94],"BOW":[97,140],"approach":[98,130],"by":[99],"embedding":[100],"background":[101],"knowledge":[102],"derived":[103],"from":[104],"Wikipedia":[105],"into":[106],"kernel,":[109],"which":[110],"then":[112],"used":[113],"enrich":[115],"documents.":[119],"Our":[120],"empirical":[121],"evaluation":[122],"real":[124],"data":[125],"sets":[126],"demonstrates":[127],"our":[129],"successfully":[131],"achieves":[132],"improved":[133],"accuracy":[135],"respect":[137],"technique,":[141],"other":[144],"recently":[145],"developed":[146],"methods.":[147]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":14},{"year":2017,"cited_by_count":14},{"year":2016,"cited_by_count":13},{"year":2015,"cited_by_count":19},{"year":2014,"cited_by_count":16},{"year":2013,"cited_by_count":23},{"year":2012,"cited_by_count":34}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}