{"id":"https://openalex.org/W2162788093","doi":"https://doi.org/10.1145/1390749.1390759","title":"On profiling blogs with representative entries","display_name":"On profiling blogs with representative entries","publication_year":2008,"publication_date":"2008-07-24","ids":{"openalex":"https://openalex.org/W2162788093","doi":"https://doi.org/10.1145/1390749.1390759","mag":"2162788093"},"language":"en","primary_location":{"id":"doi:10.1145/1390749.1390759","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1390749.1390759","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the second workshop on Analytics for noisy unstructured text data","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://ink.library.smu.edu.sg/cgi/viewcontent.cgi?article=3405&context=sis_research","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060548099","display_name":"Jinfeng Zhuang","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Jinfeng Zhuang","raw_affiliation_strings":["Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074834854","display_name":"Steven C. H. Hoi","orcid":"https://orcid.org/0000-0002-4584-3453"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Steven C. H. Hoi","raw_affiliation_strings":["Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100618738","display_name":"Aixin Sun","orcid":"https://orcid.org/0000-0003-0764-4258"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Aixin Sun","raw_affiliation_strings":["Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5060548099"],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":null,"apc_paid":null,"fwci":1.7496,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.90281832,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"55","last_page":"62"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9993000030517578,"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"}},"topics":[{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9993000030517578,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9991999864578247,"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/T11644","display_name":"Spam and Phishing Detection","score":0.9922000169754028,"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":0.7933678030967712},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.6989962458610535},{"id":"https://openalex.org/keywords/blogosphere","display_name":"Blogosphere","score":0.6102761030197144},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5924264192581177},{"id":"https://openalex.org/keywords/representativeness-heuristic","display_name":"Representativeness heuristic","score":0.51514732837677},{"id":"https://openalex.org/keywords/profiling","display_name":"Profiling (computer programming)","score":0.5032886862754822},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.48063722252845764},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4388800859451294},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.30642855167388916},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2982807457447052},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.25437113642692566}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7933678030967712},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.6989962458610535},{"id":"https://openalex.org/C2779661781","wikidata":"https://www.wikidata.org/wiki/Q374132","display_name":"Blogosphere","level":3,"score":0.6102761030197144},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5924264192581177},{"id":"https://openalex.org/C37381756","wikidata":"https://www.wikidata.org/wiki/Q20203288","display_name":"Representativeness heuristic","level":2,"score":0.51514732837677},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.5032886862754822},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.48063722252845764},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4388800859451294},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30642855167388916},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2982807457447052},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.25437113642692566},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1390749.1390759","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1390749.1390759","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the second workshop on Analytics for noisy unstructured text data","raw_type":"proceedings-article"},{"id":"pmh:oai:ink.library.smu.edu.sg:sis_research-3405","is_oa":true,"landing_page_url":"https://ink.library.smu.edu.sg/cgi/viewcontent.cgi?article=3405&context=sis_research","pdf_url":null,"source":{"id":"https://openalex.org/S4377196871","display_name":"Institutional Knowledge (InK) - Institutional Knowledge at Singapore Management University (Singapore Management University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79891267","host_organization_name":"Singapore Management University","host_organization_lineage":["https://openalex.org/I79891267"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://dx.doi.org/10.1145/1390749.1390759","raw_type":"Conference Proceeding Article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.330.3340","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.330.3340","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cais.ntu.edu.sg/~zjfeng/publications/AND08.pdf","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:ink.library.smu.edu.sg:sis_research-3405","is_oa":true,"landing_page_url":"https://ink.library.smu.edu.sg/cgi/viewcontent.cgi?article=3405&context=sis_research","pdf_url":null,"source":{"id":"https://openalex.org/S4377196871","display_name":"Institutional Knowledge (InK) - Institutional Knowledge at Singapore Management University (Singapore Management University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79891267","host_organization_name":"Singapore Management University","host_organization_lineage":["https://openalex.org/I79891267"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://dx.doi.org/10.1145/1390749.1390759","raw_type":"Conference Proceeding Article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6696749214","display_name":null,"funder_award_id":"RG67/07","funder_id":"https://openalex.org/F4320320751","funder_display_name":"Ministry of Education - Singapore"},{"id":"https://openalex.org/G947405056","display_name":null,"funder_award_id":"062 101 0031","funder_id":"https://openalex.org/F4320320696","funder_display_name":"Agency for Science, Technology and Research"}],"funders":[{"id":"https://openalex.org/F4320320696","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09"},{"id":"https://openalex.org/F4320320751","display_name":"Ministry of Education - Singapore","ror":"https://ror.org/01kcva023"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W172410088","https://openalex.org/W1535599202","https://openalex.org/W1982452440","https://openalex.org/W1993202648","https://openalex.org/W2078579128","https://openalex.org/W2082609669","https://openalex.org/W2083305840","https://openalex.org/W2093717447","https://openalex.org/W2103235295","https://openalex.org/W2104848109","https://openalex.org/W2106848050","https://openalex.org/W2108745803","https://openalex.org/W2110119381","https://openalex.org/W2116441169","https://openalex.org/W2118020653","https://openalex.org/W2123623606","https://openalex.org/W2133462743","https://openalex.org/W2134086158","https://openalex.org/W2148603752","https://openalex.org/W2148633389","https://openalex.org/W2150739536","https://openalex.org/W2154318594","https://openalex.org/W2164976357","https://openalex.org/W2296319761","https://openalex.org/W2912934387","https://openalex.org/W3138773240","https://openalex.org/W6679653975","https://openalex.org/W6683033130","https://openalex.org/W7071374342"],"related_works":["https://openalex.org/W2170860410","https://openalex.org/W2992958761","https://openalex.org/W3162250950","https://openalex.org/W2406269149","https://openalex.org/W2183591868","https://openalex.org/W4394774866","https://openalex.org/W38658537","https://openalex.org/W4312070466","https://openalex.org/W3209989275","https://openalex.org/W77221376"],"abstract_inverted_index":{"With":[0,82],"an":[1,31,154],"explosive":[2],"growth":[3],"of":[4,40,57,65,85,98,119,183,211],"blogs,":[5],"information":[6],"seeking":[7],"in":[8,113],"blogosphere":[9],"becomes":[10],"more":[11,13],"and":[12,44,47,110,132],"challenging.":[14],"One":[15],"example":[16],"task":[17,36],"is":[18,75,80,146,162],"to":[19,209],"find":[20],"the":[21,71,83,117,121,150,167],"most":[22,67,122],"relevant":[23],"topical":[24],"blogs":[25,41,91],"against":[26],"a":[27,35,54,59,63,76,138,181],"given":[28],"query":[29],"or":[30,95],"existing":[32],"blog.":[33],"Such":[34],"requires":[37],"concise":[38],"representation":[39],"for":[42,205],"effective":[43],"efficient":[45,142],"searching":[46],"matching.":[48],"In":[49],"this":[50],"paper,":[51],"we":[52,125,165],"investigate":[53],"new":[55],"problem":[56],"profiling":[58],"blog":[60,175,207],"by":[61,172,198],"choosing":[62],"set":[64,84],"m":[66,74],"representative":[68,87,123,203],"entries":[69,99,204],"from":[70,158],"blog,":[72,105],"where":[73],"predefined":[77],"number":[78,182],"that":[79,191,210],"application-dependent.":[81],"selected":[86],"entries,":[88,124],"applications":[89],"on":[90,135,180],"avoid":[92],"handling":[93],"hundreds":[94],"even":[96],"thousands":[97],"(or":[100],"posts)":[101],"associated":[102],"with":[103],"each":[104,206],"which":[106],"are":[107],"updated":[108],"frequently":[109],"often":[111],"noisy":[112],"nature.":[114],"To":[115,148],"guide":[116],"process":[118],"selecting":[120],"propose":[126],"three":[127],"principles,":[128,137],"i.e.,":[129],"anomaly,":[130],"representativeness,":[131],"diversity.":[133],"Based":[134],"these":[136],"greedy":[139],"yet":[140],"very":[141],"entry":[143,151,169],"selection":[144,152,170],"algorithm":[145],"proposed.":[147],"evaluate":[149,166],"algorithms,":[153],"extrinsic":[155],"evaluation":[156],"methodology":[157],"document":[159],"summarization":[160],"research":[161],"adapted.":[163],"Specifically,":[164],"proposed":[168],"algorithms":[171],"examining":[173],"their":[174],"classification":[176,185,193],"accuracies.":[177],"By":[178],"evaluating":[179],"different":[184],"methods,":[186],"our":[187],"empirical":[188],"results":[189],"showed":[190],"comparable":[192],"accuracy":[194],"could":[195],"be":[196],"achieved":[197],"using":[199],"fewer":[200],"than":[201],"20":[202],"compared":[208],"engaging":[212],"all":[213],"entries.":[214]},"counts_by_year":[{"year":2017,"cited_by_count":3},{"year":2015,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}