{"id":"https://openalex.org/W2078514547","doi":"https://doi.org/10.1145/1233341.1233359","title":"Enhancing clustering blog documents by utilizing author/reader comments","display_name":"Enhancing clustering blog documents by utilizing author/reader comments","publication_year":2007,"publication_date":"2007-03-23","ids":{"openalex":"https://openalex.org/W2078514547","doi":"https://doi.org/10.1145/1233341.1233359","mag":"2078514547"},"language":"en","primary_location":{"id":"doi:10.1145/1233341.1233359","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1233341.1233359","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 45th annual southeast regional 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/A5100423730","display_name":"Beibei Li","orcid":"https://orcid.org/0000-0002-0485-1975"},"institutions":[{"id":"https://openalex.org/I143302722","display_name":"University of Kentucky","ror":"https://ror.org/02k3smh20","country_code":"US","type":"education","lineage":["https://openalex.org/I143302722"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Beibei Li","raw_affiliation_strings":["University of Kentucky, Lexington, KY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Kentucky, Lexington, KY","institution_ids":["https://openalex.org/I143302722"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006617934","display_name":"Shuting Xu","orcid":"https://orcid.org/0000-0003-2572-5123"},"institutions":[{"id":"https://openalex.org/I11786554","display_name":"Virginia State University","ror":"https://ror.org/04esvpn06","country_code":"US","type":"education","lineage":["https://openalex.org/I11786554"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shuting Xu","raw_affiliation_strings":["Virginia State University, Petersburg, VA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Virginia State University, Petersburg, VA","institution_ids":["https://openalex.org/I11786554"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044019139","display_name":"Jun Zhang","orcid":"https://orcid.org/0000-0002-2189-7801"},"institutions":[{"id":"https://openalex.org/I143302722","display_name":"University of Kentucky","ror":"https://ror.org/02k3smh20","country_code":"US","type":"education","lineage":["https://openalex.org/I143302722"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jun Zhang","raw_affiliation_strings":["University of Kentucky, Lexington, KY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Kentucky, Lexington, KY","institution_ids":["https://openalex.org/I143302722"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.2826,"has_fulltext":false,"cited_by_count":51,"citation_normalized_percentile":{"value":0.96467519,"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":"94","last_page":"99"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10064","display_name":"Complex Network Analysis Techniques","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10064","display_name":"Complex Network Analysis Techniques","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9980000257492065,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9969000220298767,"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/cluster-analysis","display_name":"Cluster analysis","score":0.7919245958328247},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7910829782485962},{"id":"https://openalex.org/keywords/upload","display_name":"Upload","score":0.771318793296814},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6755541563034058},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5859361886978149},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.568345844745636},{"id":"https://openalex.org/keywords/hits-algorithm","display_name":"HITS algorithm","score":0.5455446243286133},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.545229434967041},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.5059699416160583},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4233455955982208},{"id":"https://openalex.org/keywords/web-search-engine","display_name":"Web search engine","score":0.19583532214164734},{"id":"https://openalex.org/keywords/web-navigation","display_name":"Web navigation","score":0.19096964597702026},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.16245374083518982}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7919245958328247},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7910829782485962},{"id":"https://openalex.org/C71901391","wikidata":"https://www.wikidata.org/wiki/Q7126699","display_name":"Upload","level":2,"score":0.771318793296814},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6755541563034058},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5859361886978149},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.568345844745636},{"id":"https://openalex.org/C195409031","wikidata":"https://www.wikidata.org/wiki/Q1031957","display_name":"HITS algorithm","level":5,"score":0.5455446243286133},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.545229434967041},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.5059699416160583},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4233455955982208},{"id":"https://openalex.org/C521815418","wikidata":"https://www.wikidata.org/wiki/Q4182287","display_name":"Web search engine","level":4,"score":0.19583532214164734},{"id":"https://openalex.org/C61096286","wikidata":"https://www.wikidata.org/wiki/Q7978592","display_name":"Web navigation","level":3,"score":0.19096964597702026},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.16245374083518982},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1233341.1233359","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1233341.1233359","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 45th annual southeast regional conference","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.556.220","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.556.220","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://pages.stern.nyu.edu/~bli/beibei1.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.66.7530","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.66.7530","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.uky.edu/~jzhang/pub/MINING/beibei1.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.6399999856948853,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W204086241","https://openalex.org/W365972403","https://openalex.org/W1790954942","https://openalex.org/W1871828683","https://openalex.org/W1956559956","https://openalex.org/W1994190630","https://openalex.org/W2079196839","https://openalex.org/W2100958137","https://openalex.org/W2127218421","https://openalex.org/W2147152072","https://openalex.org/W2150739536","https://openalex.org/W2155461849","https://openalex.org/W2156589869","https://openalex.org/W3139328003","https://openalex.org/W3194436879","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2110379974","https://openalex.org/W1795405792","https://openalex.org/W2019737068","https://openalex.org/W2899601636","https://openalex.org/W1881353113","https://openalex.org/W2187771236","https://openalex.org/W4254379378","https://openalex.org/W2387616437","https://openalex.org/W3015674157","https://openalex.org/W4206655101"],"abstract_inverted_index":{"Blogs":[0],"are":[1,30,148],"a":[2,9,20,84,92,97,118],"new":[3,22],"form":[4],"of":[5,51,69,144],"internet":[6],"phenomenon":[7],"and":[8,36,49,95,109],"vast":[10],"everincreasing":[11],"information":[12,18],"resource.":[13],"Mining":[14],"blog":[15,53,59,71,80,89,124,146,153],"files":[16,29,35,147],"for":[17],"is":[19],"very":[21,149],"research":[23],"direction":[24],"in":[25,55,78,151],"data":[26],"mining.":[27],"Blog":[28],"different":[31,102],"from":[32,58,91],"standard":[33],"web":[34],"may":[37,73],"need":[38],"specialized":[39],"mining":[40],"strategies.":[41],"We":[42,82],"propose":[43],"to":[44,105,122],"include":[45],"the":[46,52,66,70,106,123,127,141,145],"title,":[47,107],"body,":[48,108],"comments":[50,68,125,143],"pages":[54,72,90],"clustering":[56,79,99,132],"datasets":[57],"documents.":[60,81],"In":[61],"particular,":[62],"we":[63],"argue":[64],"that":[65,116,140],"author/reader":[67,142],"have":[74],"more":[75],"discriminating":[76,152],"effect":[77],"constructed":[83],"word-page":[85],"matrix":[86],"by":[87],"downloading":[88],"well-known":[93],"website":[94],"experimented":[96],"k-means":[98,128],"algorithm":[100,129],"with":[101],"weights":[103],"assigned":[104],"comment":[110],"parts.":[111],"Our":[112],"experimental":[113,135],"results":[114,136],"show":[115],"assigning":[117],"larger":[119],"weight":[120],"value":[121],"helps":[126],"produce":[130],"better":[131],"solutions.":[133],"The":[134],"confirm":[137],"our":[138],"hypothesis":[139],"useful":[150],"files.":[154]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":6}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}