{"id":"https://openalex.org/W4293248060","doi":"https://doi.org/10.1145/3539813.3545123","title":"Do Extractive Summarization Algorithms Amplify Lexical Bias in News Articles?","display_name":"Do Extractive Summarization Algorithms Amplify Lexical Bias in News Articles?","publication_year":2022,"publication_date":"2022-08-23","ids":{"openalex":"https://openalex.org/W4293248060","doi":"https://doi.org/10.1145/3539813.3545123"},"language":"en","primary_location":{"id":"doi:10.1145/3539813.3545123","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3539813.3545123","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 ACM SIGIR International Conference on Theory of Information Retrieval","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/A5071494217","display_name":"Rei Shimizu","orcid":"https://orcid.org/0000-0002-1036-3572"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Rei Shimizu","raw_affiliation_strings":["Waseda University, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Waseda University, Tokyo, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082125155","display_name":"Sumio Fujita","orcid":"https://orcid.org/0000-0002-1282-386X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sumio Fujita","raw_affiliation_strings":["Yahoo Japan Corporation, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Yahoo Japan Corporation, Tokyo, Japan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023595778","display_name":"Tetsuya Sakai","orcid":"https://orcid.org/0000-0002-6720-963X"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tetsuya Sakai","raw_affiliation_strings":["Waseda University, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Waseda University, Tokyo, Japan","institution_ids":["https://openalex.org/I150744194"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5071494217"],"corresponding_institution_ids":["https://openalex.org/I150744194"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.08561882,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"133","last_page":"137"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9993000030517578,"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/T10028","display_name":"Topic Modeling","score":0.9993000030517578,"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/T11147","display_name":"Misinformation and Its Impacts","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9980999827384949,"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/automatic-summarization","display_name":"Automatic summarization","score":0.8438029885292053},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.745806097984314},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.7241949439048767},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6851603984832764},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6422181725502014},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6205077171325684},{"id":"https://openalex.org/keywords/independence","display_name":"Independence (probability theory)","score":0.5519900321960449},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3744245171546936},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3299959897994995},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11519262194633484},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.10281679034233093}],"concepts":[{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.8438029885292053},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.745806097984314},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.7241949439048767},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6851603984832764},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6422181725502014},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6205077171325684},{"id":"https://openalex.org/C35651441","wikidata":"https://www.wikidata.org/wiki/Q625303","display_name":"Independence (probability theory)","level":2,"score":0.5519900321960449},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3744245171546936},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3299959897994995},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11519262194633484},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.10281679034233093},{"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:10.1145/3539813.3545123","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3539813.3545123","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 ACM SIGIR International Conference on Theory of Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5,"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":17,"referenced_works":["https://openalex.org/W2003885352","https://openalex.org/W2028009320","https://openalex.org/W2102636708","https://openalex.org/W2106404250","https://openalex.org/W2251738400","https://openalex.org/W2307381258","https://openalex.org/W2559655401","https://openalex.org/W2574535369","https://openalex.org/W2759820691","https://openalex.org/W2952138241","https://openalex.org/W2970600560","https://openalex.org/W3013198191","https://openalex.org/W3025132739","https://openalex.org/W3088965320","https://openalex.org/W3102589552","https://openalex.org/W3156597800","https://openalex.org/W3176193384"],"related_works":["https://openalex.org/W2366403280","https://openalex.org/W1495108544","https://openalex.org/W2091301346","https://openalex.org/W3148229873","https://openalex.org/W4389760904","https://openalex.org/W2150160875","https://openalex.org/W4242223894","https://openalex.org/W4306886878","https://openalex.org/W2973759123","https://openalex.org/W1517524280"],"abstract_inverted_index":{"Users":[0],"who":[1],"read":[2],"news":[3,18],"summaries":[4,23,33],"on":[5,144,184],"search":[6],"engine":[7],"result":[8],"pages":[9],"and":[10,42,101,173,246],"social":[11],"media":[12],"may":[13,65,238],"not":[14],"access":[15],"the":[16,22,31,35,38,68,98,112,120,136,145,156,163,166,176,185,192],"original":[17,39,99],"articles.":[19],"Hence,":[20],"if":[21,60],"are":[24,81],"automatically":[25],"generated,":[26],"it":[27,61],"is":[28,47,56,125,138,210],"vital":[29],"that":[30,64,119,122,174,220],"automatic":[32],"represent":[34],"contents":[36],"of":[37,134,165,175,266],"articles":[40],"accurately":[41],"fairly.":[43],"The":[44],"present":[45],"study":[46],"concerned":[48],"with":[49],"lexical":[50,89,214,226,244],"bias":[51,227],"in":[52,83],"sentences:":[53],"a":[54,72,123,201,206,263],"sentence":[55,124,137,167,177],"considered":[57],"lexically":[58,94,139,170,267],"biased":[59,95,140,171,268],"contains":[62],"expressions":[63],"strongly":[66],"influence":[67],"reader's":[69],"opinion":[70],"about":[71],"topic":[73],"either":[74],"positively":[75],"or":[76,141],"negatively.":[77],"More":[78],"specifically,":[79],"we":[80,109,147,187],"interested":[82],"whether":[84,135,200],"extractive":[85,129,153,208,222],"summarizers":[86,154,223],"can":[87,224],"amplify":[88,225],"bias,":[90],"by":[91,127,205],"excessively":[92],"extracting":[93,235],"sentences":[96,172,237],"from":[97],"article":[100],"thus":[102],"misrepresent":[103],"it.":[104],"To":[105],"address":[106],"this":[107],"question,":[108],"first":[110],"introduce":[111],"Bias":[113,157],"Independence":[114,158],"Principle":[115],"(BIP),":[116],"which":[117,161],"says":[118],"probability":[121],"selected":[126],"an":[128,149],"summarizer":[130,209],"should":[131],"be":[132,240],"independent":[133],"not.":[142],"Based":[143],"BIP,":[146],"propose":[148],"evaluation":[150],"measure":[151,190],"for":[152,169,179,212,234,242],"called":[155,191],"Criterion":[159],"(BIC),":[160],"compares":[162],"distribution":[164],"scores":[168,178,250,257],"non-biased":[180],"sentences.":[181],"Moreover,":[182],"based":[183],"BIC,":[186],"define":[188],"another":[189],"Summary":[193],"Feature":[194],"Permutation":[195],"Importance":[196],"(SFPI)":[197],"to":[198,228,260],"examine":[199],"particular":[202],"feature":[203],"used":[204],"feature-based":[207],"responsible":[211,241],"amplifying":[213,243],"bias.":[215],"Our":[216],"experimental":[217],"results":[218],"suggest":[219],"a)~Different":[221],"different":[229],"degrees;":[230],"b)~The":[231],"features":[232],"useful":[233],"informative":[236],"also":[239,258],"bias;":[245],"c)~as":[247],"mean":[248,255],"ROUGE":[249],"increase":[251,261],"(implying":[252,262],"higher":[253,264],"informativeness),":[254],"BIC":[256],"tend":[259],"concentration":[265],"sentences).":[269]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}