{"id":"https://openalex.org/W2095096163","doi":"https://doi.org/10.1145/1980422.1980450","title":"Dirichlet distribution with centroid model (DDCM) based summarization technique for web document classification","display_name":"Dirichlet distribution with centroid model (DDCM) based summarization technique for web document classification","publication_year":2011,"publication_date":"2011-03-25","ids":{"openalex":"https://openalex.org/W2095096163","doi":"https://doi.org/10.1145/1980422.1980450","mag":"2095096163"},"language":"en","primary_location":{"id":"doi:10.1145/1980422.1980450","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1980422.1980450","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Fourth Annual ACM Bangalore Conference","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/A5080236075","display_name":"Setu Kumar Chaturvedi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210162153","display_name":"Madhya Pradesh Council of Science and Technology","ror":"https://ror.org/04xtbyj71","country_code":"IN","type":"government","lineage":["https://openalex.org/I4210162153"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Setu K. Chaturvedi","raw_affiliation_strings":["Technocrats Institute of Technology, Bhopal, MP, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technocrats Institute of Technology, Bhopal, MP, India","institution_ids":["https://openalex.org/I4210162153"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068367743","display_name":"Dhirendra Kumar Swami","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"D. K. Swami","raw_affiliation_strings":["VNS Institute of Technology, Bhopal, MP, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VNS Institute of Technology, Bhopal, MP, India","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032953437","display_name":"Gulab Singh","orcid":"https://orcid.org/0000-0002-7774-5997"},"institutions":[{"id":"https://openalex.org/I4210162153","display_name":"Madhya Pradesh Council of Science and Technology","ror":"https://ror.org/04xtbyj71","country_code":"IN","type":"government","lineage":["https://openalex.org/I4210162153"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Gulab Singh","raw_affiliation_strings":["Technocrats Institute of Technology, Bhopal, MP, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technocrats Institute of Technology, Bhopal, MP, India","institution_ids":["https://openalex.org/I4210162153"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2941,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.84245188,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9995999932289124,"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":0.9995999932289124,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9966999888420105,"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":0.9944999814033508,"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/automatic-summarization","display_name":"Automatic summarization","score":0.935819149017334},{"id":"https://openalex.org/keywords/centroid","display_name":"Centroid","score":0.8054683208465576},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7576837539672852},{"id":"https://openalex.org/keywords/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.64096599817276},{"id":"https://openalex.org/keywords/multi-document-summarization","display_name":"Multi-document summarization","score":0.6352338790893555},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5700148344039917},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5431912541389465},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5421953201293945},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5032963156700134},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4846492409706116},{"id":"https://openalex.org/keywords/document-classification","display_name":"Document classification","score":0.4668259024620056},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4341813027858734},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.369268000125885},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3420944809913635},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.07260715961456299}],"concepts":[{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.935819149017334},{"id":"https://openalex.org/C146599234","wikidata":"https://www.wikidata.org/wiki/Q511093","display_name":"Centroid","level":2,"score":0.8054683208465576},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7576837539672852},{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.64096599817276},{"id":"https://openalex.org/C134714966","wikidata":"https://www.wikidata.org/wiki/Q6934448","display_name":"Multi-document summarization","level":3,"score":0.6352338790893555},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5700148344039917},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5431912541389465},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5421953201293945},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5032963156700134},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4846492409706116},{"id":"https://openalex.org/C2780479914","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Document classification","level":2,"score":0.4668259024620056},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4341813027858734},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.369268000125885},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3420944809913635},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.07260715961456299},{"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:10.1145/1980422.1980450","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1980422.1980450","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Fourth Annual ACM Bangalore Conference","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1880262756","https://openalex.org/W2065964044","https://openalex.org/W2103339462","https://openalex.org/W2118020653","https://openalex.org/W2121715962","https://openalex.org/W2137005794","https://openalex.org/W2150286230","https://openalex.org/W2150977471","https://openalex.org/W6639619044"],"related_works":["https://openalex.org/W2888805565","https://openalex.org/W4312773271","https://openalex.org/W2743191757","https://openalex.org/W2703484599","https://openalex.org/W4297311563","https://openalex.org/W2008991527","https://openalex.org/W1995796873","https://openalex.org/W2008338582","https://openalex.org/W2594674086","https://openalex.org/W2018409826"],"abstract_inverted_index":{"Web":[0],"document":[1,136,170],"summarization":[2,29,167,181,195],"deals":[3],"with":[4,43,175],"computing":[5],"a":[6,9,20],"summary":[7,77],"for":[8,168],"set":[10],"of":[11,27,75,107,152,160,180],"related":[12],"articles":[13],"such":[14],"that":[15,32,119,145,191],"they":[16],"give":[17],"the":[18,24,28,33,37,41,44,69,73,76,89,104,117,131,135,143],"user":[19],"general":[21],"view":[22],"about":[23],"events.":[25,65],"One":[26],"objectives":[30],"is":[31,100,155],"sentences":[34,50,74,111,118],"should":[35],"cover":[36],"different":[38,62,132],"events":[39],"in":[40,47,122,134],"documents":[42,60],"information":[45,71],"covered":[46],"as":[48,51,112,205],"few":[49],"possible.":[52],"Dirichlet":[53],"Distribution":[54],"Model":[55,140],"can":[56,115],"break":[57],"down":[58],"these":[59,148],"into":[61],"sentence":[63,133],"or":[64],"However":[66],"to":[67,79,82,102,156,207],"reduce":[68],"common":[70],"content":[72],"need":[78],"be":[80],"orthogonal":[81,86,105,121],"each":[83],"other":[84],"since":[85],"vectors":[87,108],"have":[88],"lowest":[90],"possible":[91],"similarity":[92],"and":[93,109,137,183,202],"correlation":[94],"between":[95],"them.":[96],"Centroid":[97,139,177],"Value":[98],"Decomposition":[99],"used":[101],"get":[103,116,130],"representations":[106],"representing":[110],"vectors,":[113],"we":[114,129,141],"are":[120],"our":[123,192],"proposed":[124,193],"DDCM.":[125],"Thus":[126],"using":[127,138],"DDM":[128],"find":[142,157],"words":[144],"best":[146,166],"represent":[147],"sentences.":[149],"The":[150],"goal":[151],"this":[153],"paper":[154],"minimum":[158],"number":[159],"highly":[161],"qualitative":[162],"features":[163],"by":[164],"generating":[165],"web":[169],"classification.":[171,211],"We":[172],"conducted":[173],"experiments":[174],"various":[176],"based":[178,196,210],"numbers":[179],"approaches":[182],"obtain":[184],"effective":[185],"classification":[186,197],"results.":[187],"Experimental":[188],"results":[189],"show":[190],"DDCM":[194],"approach":[198],"achieved":[199],"more":[200],"accurate":[201],"improved":[203],"result":[204],"compared":[206],"full":[208],"text":[209]},"counts_by_year":[{"year":2013,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}