{"id":"https://openalex.org/W2554990436","doi":"https://doi.org/10.5220/0006077403840391","title":"Gender Clustering of Blog Posts using Distinguishable Features","display_name":"Gender Clustering of Blog Posts using Distinguishable Features","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2554990436","doi":"https://doi.org/10.5220/0006077403840391","mag":"2554990436"},"language":"en","primary_location":{"id":"doi:10.5220/0006077403840391","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0006077403840391","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 8th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.5220/0006077403840391","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058308382","display_name":"Yaakov HaCohen\u2010Kerner","orcid":"https://orcid.org/0000-0002-4834-1272"},"institutions":[{"id":"https://openalex.org/I192238737","display_name":"Jerusalem College of Technology","ror":"https://ror.org/002kenh51","country_code":"IL","type":"education","lineage":["https://openalex.org/I192238737"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"Yaakov HaCohen-Kerner","raw_affiliation_strings":["Jerusalem College of Technology (Machon Lev), Israel"],"affiliations":[{"raw_affiliation_string":"Jerusalem College of Technology (Machon Lev), Israel","institution_ids":["https://openalex.org/I192238737"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022774232","display_name":"Yarden Tzach","orcid":null},"institutions":[{"id":"https://openalex.org/I192238737","display_name":"Jerusalem College of Technology","ror":"https://ror.org/002kenh51","country_code":"IL","type":"education","lineage":["https://openalex.org/I192238737"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Yarden Tzach","raw_affiliation_strings":["Jerusalem College of Technology (Machon Lev), Israel"],"affiliations":[{"raw_affiliation_string":"Jerusalem College of Technology (Machon Lev), Israel","institution_ids":["https://openalex.org/I192238737"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017572687","display_name":"Ori Asis","orcid":null},"institutions":[{"id":"https://openalex.org/I192238737","display_name":"Jerusalem College of Technology","ror":"https://ror.org/002kenh51","country_code":"IL","type":"education","lineage":["https://openalex.org/I192238737"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Ori Asis","raw_affiliation_strings":["Jerusalem College of Technology (Machon Lev), Israel"],"affiliations":[{"raw_affiliation_string":"Jerusalem College of Technology (Machon Lev), Israel","institution_ids":["https://openalex.org/I192238737"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5058308382"],"corresponding_institution_ids":["https://openalex.org/I192238737"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.165312,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"384","last_page":"391"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9553999900817871,"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":0.9553999900817871,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9430000185966492,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.9041000008583069,"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/cluster-analysis","display_name":"Cluster analysis","score":0.8149728775024414},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6983969211578369},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6298070549964905},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6280902028083801},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.54230797290802},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5101435780525208},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4367522597312927},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09130102396011353}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8149728775024414},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6983969211578369},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6298070549964905},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6280902028083801},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.54230797290802},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5101435780525208},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4367522597312927},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09130102396011353},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5220/0006077403840391","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0006077403840391","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 8th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.5220/0006077403840391","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0006077403840391","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 8th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6299999952316284,"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":0,"referenced_works":[],"related_works":["https://openalex.org/W2804364458","https://openalex.org/W4298130764","https://openalex.org/W2132641928","https://openalex.org/W4310225030","https://openalex.org/W2090259340","https://openalex.org/W2083665254","https://openalex.org/W2393816671","https://openalex.org/W2158836806","https://openalex.org/W1926736923","https://openalex.org/W4386159726"],"abstract_inverted_index":{"The":[0,70],"aim":[1],"of":[2,14,58,90,97,102,131],"this":[3,112,118],"research":[4],"is":[5,33,119],"to":[6,10,75,94,123],"find":[7],"out":[8],"how":[9],"perform":[11],"effective":[12],"clustering":[13,101,130],"unlabeled":[15,104,133],"personal":[16],"blog":[17,26,30,105,125],"posts\r\n\r\nwritten":[18],"in":[19],"English":[20],"by":[21,127],"gender.":[22],"Given":[23],"a":[24,29,82,142],"gender-labeled":[25],"corpus":[27,31,40,134],"and":[28,46,62,67],"that":[32,53,89,138],"not":[34],"gender-labeled,\r\n\r\nwe":[35],"extracted":[36,140],"from":[37,141],"the":[38,55,59,77,103,108,120],"labeled":[39],"distinguishable":[41,60,136],"unigrams":[42],"for":[43,99],"both":[44],"males":[45],"females.":[47],"Then,\r\n\r\nwe":[48],"defined":[49],"two":[50,115],"general":[51],"features":[52,137],"represent":[54],"relative":[56],"frequencies":[57],"males\u00e2\u0080\u0099\r\n\r\nunigrams":[61],"females\u00e2\u0080\u0099":[63,68],"unigrams,":[64],"(males\u00e2\u0080\u0099":[65],"frequency":[66,79],"frequency).":[69],"best":[71],"distinguishable\r\n\r\nfeature":[72],"was":[73],"found":[74],"be":[76],"males\u00e2\u0080\u0099":[78],"feature":[80,92],"with":[81],"ratio":[83],"factor":[84],"at":[85],"least":[86],"1.4":[87],"times":[88],"females.\r\n\r\nThis":[91],"leads":[93],"accuracy":[95],"rate":[96],"83.7%":[98],"gender":[100],"corpus.":[106],"To":[107],"best\r\n\r\nof":[109],"our":[110],"knowledge,":[111],"study":[113,122],"presents":[114],"novelties:":[116],"(1)":[117],"first":[121],"cluster":[124],"posts":[126],"gender,\r\n\r\nand":[128],"(2)":[129],"an":[132],"using":[135],"were":[139],"labeled\r\n\r\ncorpus.":[143]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}