{"id":"https://openalex.org/W2804344463","doi":"https://doi.org/10.1109/tkde.2018.2840127","title":"Comments Mining With TF-IDF: The Inherent Bias and Its Removal","display_name":"Comments Mining With TF-IDF: The Inherent Bias and Its Removal","publication_year":2018,"publication_date":"2018-05-24","ids":{"openalex":"https://openalex.org/W2804344463","doi":"https://doi.org/10.1109/tkde.2018.2840127","mag":"2804344463"},"language":"en","primary_location":{"id":"doi:10.1109/tkde.2018.2840127","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2018.2840127","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-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/A5070441489","display_name":"Inbal Yahav","orcid":"https://orcid.org/0000-0002-1513-017X"},"institutions":[{"id":"https://openalex.org/I13955877","display_name":"Bar-Ilan University","ror":"https://ror.org/03kgsv495","country_code":"IL","type":"education","lineage":["https://openalex.org/I13955877"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Inbal Yahav","raw_affiliation_strings":["Graduate School of Business Administration, Bar Ilan University, Ramat Gan, Israel"],"raw_orcid":"https://orcid.org/0000-0002-1513-017X","affiliations":[{"raw_affiliation_string":"Graduate School of Business Administration, Bar Ilan University, Ramat Gan, Israel","institution_ids":["https://openalex.org/I13955877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041060862","display_name":"Onn Shehory","orcid":"https://orcid.org/0000-0001-9594-7819"},"institutions":[{"id":"https://openalex.org/I13955877","display_name":"Bar-Ilan University","ror":"https://ror.org/03kgsv495","country_code":"IL","type":"education","lineage":["https://openalex.org/I13955877"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Onn Shehory","raw_affiliation_strings":["Graduate School of Business Administration, Bar Ilan University, Ramat Gan, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Business Administration, Bar Ilan University, Ramat Gan, Israel","institution_ids":["https://openalex.org/I13955877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047203435","display_name":"David G. Schwartz","orcid":"https://orcid.org/0000-0002-2125-2069"},"institutions":[{"id":"https://openalex.org/I13955877","display_name":"Bar-Ilan University","ror":"https://ror.org/03kgsv495","country_code":"IL","type":"education","lineage":["https://openalex.org/I13955877"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"David Schwartz","raw_affiliation_strings":["Graduate School of Business Administration, Bar Ilan University, Ramat Gan, Israel"],"raw_orcid":"https://orcid.org/0000-0002-2125-2069","affiliations":[{"raw_affiliation_string":"Graduate School of Business Administration, Bar Ilan University, Ramat Gan, Israel","institution_ids":["https://openalex.org/I13955877"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I13955877"],"apc_list":null,"apc_paid":null,"fwci":8.7704,"has_fulltext":false,"cited_by_count":102,"citation_normalized_percentile":{"value":0.98120504,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"31","issue":"3","first_page":"437","last_page":"450"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9998999834060669,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9998999834060669,"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":0.9994999766349792,"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":0.9984999895095825,"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/sentiment-analysis","display_name":"Sentiment analysis","score":0.7791082262992859},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7622379660606384},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.5510896444320679},{"id":"https://openalex.org/keywords/offset","display_name":"Offset (computer science)","score":0.5457387566566467},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.5022134780883789},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.46957823634147644},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.44838547706604004},{"id":"https://openalex.org/keywords/text-mining","display_name":"Text mining","score":0.4463132619857788},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.43659693002700806},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4144143760204315},{"id":"https://openalex.org/keywords/tf\u2013idf","display_name":"tf\u2013idf","score":0.413045197725296},{"id":"https://openalex.org/keywords/entertainment","display_name":"Entertainment","score":0.4110450744628906},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4077260196208954},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39397528767585754},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.1755700707435608}],"concepts":[{"id":"https://openalex.org/C66402592","wikidata":"https://www.wikidata.org/wiki/Q2271421","display_name":"Sentiment analysis","level":2,"score":0.7791082262992859},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7622379660606384},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.5510896444320679},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.5457387566566467},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.5022134780883789},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.46957823634147644},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.44838547706604004},{"id":"https://openalex.org/C71472368","wikidata":"https://www.wikidata.org/wiki/Q676880","display_name":"Text mining","level":2,"score":0.4463132619857788},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.43659693002700806},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4144143760204315},{"id":"https://openalex.org/C81758059","wikidata":"https://www.wikidata.org/wiki/Q796584","display_name":"tf\u2013idf","level":3,"score":0.413045197725296},{"id":"https://openalex.org/C512170562","wikidata":"https://www.wikidata.org/wiki/Q173799","display_name":"Entertainment","level":2,"score":0.4110450744628906},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4077260196208954},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39397528767585754},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.1755700707435608},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tkde.2018.2840127","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2018.2840127","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1995883027","display_name":null,"funder_award_id":"3-9770","funder_id":"https://openalex.org/F4320323706","funder_display_name":"Ministry of Science and Technology, Israel"}],"funders":[{"id":"https://openalex.org/F4320323706","display_name":"Ministry of Science and Technology, Israel","ror":"https://ror.org/02heb2n75"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":86,"referenced_works":["https://openalex.org/W34956765","https://openalex.org/W66373487","https://openalex.org/W111251943","https://openalex.org/W137217113","https://openalex.org/W1513088263","https://openalex.org/W1541367332","https://openalex.org/W1565251461","https://openalex.org/W1571050549","https://openalex.org/W1754818811","https://openalex.org/W1935626982","https://openalex.org/W1970191301","https://openalex.org/W1978394996","https://openalex.org/W1983314966","https://openalex.org/W1985710361","https://openalex.org/W1985749074","https://openalex.org/W1990845847","https://openalex.org/W1995049667","https://openalex.org/W1999054530","https://openalex.org/W2020345959","https://openalex.org/W2021570179","https://openalex.org/W2024932032","https://openalex.org/W2035259174","https://openalex.org/W2039120654","https://openalex.org/W2048392812","https://openalex.org/W2063596712","https://openalex.org/W2067569849","https://openalex.org/W2071546224","https://openalex.org/W2075006521","https://openalex.org/W2075046382","https://openalex.org/W2079621256","https://openalex.org/W2089065004","https://openalex.org/W2097726431","https://openalex.org/W2100431644","https://openalex.org/W2100979733","https://openalex.org/W2107641306","https://openalex.org/W2109634664","https://openalex.org/W2115023510","https://openalex.org/W2117261786","https://openalex.org/W2119671065","https://openalex.org/W2121871834","https://openalex.org/W2122160290","https://openalex.org/W2126948581","https://openalex.org/W2130313487","https://openalex.org/W2135731857","https://openalex.org/W2141975087","https://openalex.org/W2148506018","https://openalex.org/W2159981908","https://openalex.org/W2165044314","https://openalex.org/W2166706824","https://openalex.org/W2168501109","https://openalex.org/W2170340032","https://openalex.org/W2171284435","https://openalex.org/W2182516908","https://openalex.org/W2233216052","https://openalex.org/W2249760312","https://openalex.org/W2321087410","https://openalex.org/W2332078328","https://openalex.org/W2404527150","https://openalex.org/W2405154930","https://openalex.org/W2498862114","https://openalex.org/W2602930571","https://openalex.org/W2758863782","https://openalex.org/W2794351147","https://openalex.org/W2797066131","https://openalex.org/W2951936974","https://openalex.org/W3104500099","https://openalex.org/W3121452939","https://openalex.org/W3121961986","https://openalex.org/W3122125470","https://openalex.org/W4205184193","https://openalex.org/W4233790810","https://openalex.org/W4243501507","https://openalex.org/W4250860020","https://openalex.org/W4312789226","https://openalex.org/W6604557708","https://openalex.org/W6605553331","https://openalex.org/W6637780042","https://openalex.org/W6668217731","https://openalex.org/W6676621845","https://openalex.org/W6677885705","https://openalex.org/W6678682705","https://openalex.org/W6680340802","https://openalex.org/W6683251412","https://openalex.org/W6683602473","https://openalex.org/W6684364469","https://openalex.org/W6713764426"],"related_works":["https://openalex.org/W2382433580","https://openalex.org/W2100326285","https://openalex.org/W2369751049","https://openalex.org/W2198237484","https://openalex.org/W2381981226","https://openalex.org/W4296339319","https://openalex.org/W2041122820","https://openalex.org/W2548633793","https://openalex.org/W4312472170","https://openalex.org/W3107962899"],"abstract_inverted_index":{"Text":[0],"mining":[1,40],"have":[2],"gained":[3],"great":[4],"momentum":[5],"in":[6,35,46,62,75,108,127,132,145],"recent":[7],"years,":[8],"with":[9,21,53,59,182,183],"user-generated":[10],"content":[11,118],"becoming":[12],"widely":[13],"available.":[14],"One":[15],"key":[16],"use":[17,85],"is":[18,41,51,67,83,122],"comment":[19,39],"mining,":[20],"much":[22],"attention":[23],"being":[24],"given":[25],"to":[26,84,90,103,154,165],"sentiment":[27],"analysis":[28,148],"and":[29,111,151,180,198],"opinion":[30],"mining.":[31],"An":[32],"essential":[33],"step":[34,45],"the":[36,63,70,73,76,86,97,104,133,174,178],"process":[37],"of":[38,72,78,106,176],"text":[42],"pre-processing;":[43],"a":[44,54,137,146],"which":[47],"each":[48],"linguistic":[49],"term":[50,74],"assigned":[52],"weight":[55],"that":[56,117,167],"commonly":[57],"increases":[58],"its":[60],"appearance":[61],"studied":[64],"text,":[65],"yet":[66],"offset":[68],"by":[69,100],"frequency":[71],"domain":[77],"interest.":[79],"A":[80],"common":[81],"practice":[82],"well-known":[87],"tf-idf":[88,166],"formula":[89],"compute":[91],"these":[92],"weights.":[93],"This":[94],"paper":[95],"reveals":[96],"bias":[98,142,179],"introduced":[99],"between-participants'":[101],"discourse":[102,121],"study":[105],"comments":[107],"social":[109],"media,":[110],"proposes":[112],"an":[113,155,163],"adjustment.":[114],"We":[115,161,172],"find":[116],"extracted":[119],"from":[120],"often":[123],"highly":[124],"correlated,":[125],"resulting":[126],"dependency":[128],"structures":[129],"between":[130],"observations":[131],"study,":[134],"thus":[135],"introducing":[136],"statistical":[138],"bias.":[139,171],"Ignoring":[140],"this":[141,170],"can":[143,152],"manifest":[144],"non-robust":[147],"at":[149,159],"best":[150],"lead":[153],"entirely":[156],"wrong":[157],"conclusion":[158],"worst.":[160],"propose":[162],"adjustment":[164],"accounts":[168],"for":[169],"illustrate":[173],"effects":[175],"both":[177],"correction":[181],"seven":[184],"Facebook":[185],"fan":[186],"pages":[187],"data,":[188],"covering":[189],"different":[190],"domains,":[191],"including":[192],"news,":[193],"finance,":[194],"politics,":[195],"sport,":[196],"shopping,":[197],"entertainment.":[199]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":18},{"year":2021,"cited_by_count":17},{"year":2020,"cited_by_count":20},{"year":2019,"cited_by_count":10}],"updated_date":"2026-07-17T09:13:05.818461","created_date":"2025-10-10T00:00:00"}