{"id":"https://openalex.org/W3209177236","doi":"https://doi.org/10.5281/zenodo.4124410","title":"Portuguese Comparative Sentences: A Collection of Labeled Sentences on Twitter and Buscap\u00e9","display_name":"Portuguese Comparative Sentences: A Collection of Labeled Sentences on Twitter and Buscap\u00e9","publication_year":2020,"publication_date":"2020-10-29","ids":{"openalex":"https://openalex.org/W3209177236","doi":"https://doi.org/10.5281/zenodo.4124410","mag":"3209177236"},"language":"en","primary_location":{"id":"pmh:oai:zenodo.org:4124410","is_oa":true,"landing_page_url":"https://zenodo.org/record/4124410","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"","raw_type":"info:eu-repo/semantics/other"},"type":"dataset","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://zenodo.org/record/4124410","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072835017","display_name":"Daniel Kansaon","orcid":"https://orcid.org/0000-0001-5990-1629"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kansaon, Daniel","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-5990-1629","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054180602","display_name":"Michele A. Brand\u00e3o","orcid":"https://orcid.org/0000-0001-7808-9357"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Brand\u00e3o, Michele A.","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-7808-9357","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077142904","display_name":"J\u00falio C. S. Reis","orcid":"https://orcid.org/0000-0003-0563-0434"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Reis, Julio C. S.","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-0563-0434","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085247364","display_name":"Matheus Barbosa","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Matheus Barbosa","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000520670","display_name":"Breno Matos","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Breno Matos","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5085054435","display_name":"Fabr\u00ed\u00adcio Benevenuto","orcid":"https://orcid.org/0000-0001-6875-6259"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Benevenuto, Fabr\u00edcio","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-6875-6259","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13155","display_name":"Digital Communication and Language","score":0.5501000285148621,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T13155","display_name":"Digital Communication and Language","score":0.5501000285148621,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T12119","display_name":"Linguistics and Discourse Analysis","score":0.4984000027179718,"subfield":{"id":"https://openalex.org/subfields/1211","display_name":"Philosophy"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10557","display_name":"Social Media and Politics","score":0.45249998569488525,"subfield":{"id":"https://openalex.org/subfields/3315","display_name":"Communication"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/portuguese","display_name":"Portuguese","score":0.6924909353256226},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.6068322658538818},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5993752479553223},{"id":"https://openalex.org/keywords/brazilian-portuguese","display_name":"Brazilian Portuguese","score":0.43455618619918823},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.42708659172058105},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.423446387052536},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.12715908885002136}],"concepts":[{"id":"https://openalex.org/C35219183","wikidata":"https://www.wikidata.org/wiki/Q5146","display_name":"Portuguese","level":2,"score":0.6924909353256226},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.6068322658538818},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5993752479553223},{"id":"https://openalex.org/C2778880076","wikidata":"https://www.wikidata.org/wiki/Q750553","display_name":"Brazilian Portuguese","level":3,"score":0.43455618619918823},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.42708659172058105},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.423446387052536},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.12715908885002136}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:zenodo.org:4124410","is_oa":true,"landing_page_url":"https://zenodo.org/record/4124410","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"","raw_type":"info:eu-repo/semantics/other"},{"id":"doi:10.5281/zenodo.4124410","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.4124410","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"dataset"}],"best_oa_location":{"id":"pmh:oai:zenodo.org:4124410","is_oa":true,"landing_page_url":"https://zenodo.org/record/4124410","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"","raw_type":"info:eu-repo/semantics/other"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2789286307","https://openalex.org/W2899664355","https://openalex.org/W4319311403","https://openalex.org/W3204019825","https://openalex.org/W2306266016","https://openalex.org/W4254443907","https://openalex.org/W2886753397","https://openalex.org/W4377968335","https://openalex.org/W2544314260","https://openalex.org/W4387674232"],"abstract_inverted_index":{"More":[0],"and":[1,9,57,135,172,191,207,237,488,504,589],"more":[2,575,654],"customers":[3],"demand":[4],"online":[5],"reviews":[6,51],"of":[7,45,50,60,79,111,148,178,283,303,317,329,627,641,666],"products":[8,80],"comments":[10,289],"on":[11,54,205,228,271,502],"the":[12,30,42,87,159,165,219,229,272,274,306,341,345,354,362,370,385,393,402,422,428,505,529,534,551,556,562,567,580,593,603,607,625,630,648,659,667],"Web":[13,506],"to":[14,33,90,122,153,174,267,372,536,540,549,584],"make":[15,123,528],"decisions":[16],"about":[17],"buying":[18],"a":[19,35,46,71,124,146,155,170,238,262,281,405,416,432,597,611],"product":[20,269],"over":[21],"another.":[22],"In":[23,162,499],"this":[24,468,642],"context,":[25],"sentiment":[26],"analysis":[27,49],"techniques":[28],"constitute":[29],"traditional":[31],"way":[32],"summarize":[34],"user\u2019s":[36],"opinions":[37,66,93],"that":[38,117,211,600],"criticizes":[39],"or":[40,73],"highlights":[41],"positive":[43,56,72],"aspects":[44,59,78],"product.":[47],"Sentiment":[48],"usually":[52],"relies":[53],"extracting":[55],"negative":[58,74],"products,":[61],"neglecting":[62],"comparative":[63,92,102,133,141,156,181,366,594],"opinions.":[64],"Such":[65],"do":[67],"not":[68,426,635,662],"directly":[69],"express":[70,154,373],"view":[75],"but":[76],"contrast":[77],"from":[81,183,288,344],"different":[82,542],"competitors.":[83],"Here,":[84],"we":[85,197],"present":[86,217],"first":[88,350],"effort":[89],"study":[91],"in":[94,126,158,169,203,218,291,353,361,369,384,392,496,533,555,566,579,606,629],"Portuguese,":[95],"creating":[96,280,596],"two":[97,176,184],"new":[98,598,621],"Portuguese":[99,160,200,493],"datasets":[100,335],"with":[101,131,139,180,240,256,305,574],"sentences":[103,182,234,242,412,531,553],"marked":[104],"by":[105,279,297],"three":[106,112,249,298,586,590],"humans.":[107],"This":[108,293],"repository":[109],"consists":[110],"important":[113,185],"files:":[114],"(1)":[115,187],"lexicon":[116,144,166],"contains":[118],"words":[119,150,587,591,657],"frequently":[120,151],"used":[121,152,173,266,368,554],"comparison":[125],"Portuguese;":[127],"(2)":[128,192],"Twitter":[129,311],"dataset":[130,138,294,312,324,535],"labeled":[132,140,247,285,296,315,327,338],"sentences;":[134],"(3)":[136],"Buscap\u00e9":[137,323],"sentences.":[142,622],"The":[143,310,322,613,632],"is":[145,167,226,404,425,624],"set":[147,282],"176":[149],"opinion":[157],"language.":[161],"these":[163,337],"contexts,":[164],"aggregated":[168],"filter":[171],"build":[175],"sets":[177],"data":[179],"contexts:":[186],"Social":[188],"Network":[189],"Online;":[190],"Product":[193],"reviews.":[194],"For":[195,260,571],"Twitter,":[196],"collected":[198],"all":[199,209,233],"tweets":[201,210],"published":[202],"Brazil":[204],"2018/01/10":[206],"filtered":[208],"contained":[212],"at":[213],"least":[214],"one":[215,577],"keyword":[216,367,578],"lexicon,":[220],"obtaining":[221],"130,459":[222],"tweets.":[223],"Our":[224],"work":[225,539],"based":[227],"sentence":[230,342,371,397,417,573,599,615,651],"level.":[231],"Thus,":[232],"were":[235,413],"extracted":[236,343],"sample":[239],"2,053":[241,314],"was":[243,246,277,295],"created,":[244],"which":[245,318,330,399],"for":[248,638],"human":[250],"manuals,":[251],"reaching":[252,300],"an":[253,301],"83.2%":[254],"agreement":[255,302],"Fleiss'":[257],"Kappa":[258,308],"coefficient.":[259,309],"Buscap\u00e9,":[261],"Brazilian":[263,500],"website":[264],"(https://www.buscape.com.br/)":[265],"compare":[268],"prices":[270],"web,":[273],"same":[275],"methodology":[276],"conducted":[278],"2,754":[284,326],"sentences,":[286,316,328],"obtained":[287],"made":[290],"2013.":[292],"humans,":[299],"83.46%":[304],"Fleiss":[307],"has":[313,325],"918":[319],"are":[320,332,661],"comparative.":[321,333],"1,282":[331],"<strong>The":[334],"contain":[336,441],"properties:</strong>":[339],"<em>text</em>:":[340],"review":[346],"comment.":[347],"<em>entity_s1:":[348],"</em>the":[349,357,365,376,380,388,396],"entity":[351,359,424],"compared":[352,360,423],"sentence<em>.</em>":[355],"<em>entity_s2:":[356],"second":[358],"sentence.":[363,386,394],"<em>keyword:":[364],"comparison.":[374],"<em>preferred_entity:":[375],"preferred":[377],"entity.":[378],"<em>id_start:":[379],"keyword's":[381,389],"initial":[382],"position":[383,391],"<em>id_end:":[387],"final":[390,649],"<em>type:":[395],"label,":[398],"specifies":[400],"whether":[401],"phrase":[403],"comparison<em>.</em>":[406],"<strong>Additional":[407],"Information:</strong>":[408,526],"<em><strong>1":[409],"</strong>-":[410,420],"</em>The":[411,437],"separated":[414],"using":[415],"tokenizer.":[418],"<em><strong>2":[419],"</em>If":[421],"specified,":[427],"field":[429,609],"will":[430,601,616],"receive":[431,602],"value:":[433],"\"__\".":[434],"<em><strong>3</strong>":[435],"-":[436],"property":[438],"<em>\"type\"</em>":[439],"can":[440,652],"five":[442],"values,":[443],"they":[444],"are:":[445],"<em>0:":[446],"Non-comparative":[447],"(</em>N\u00e3o":[448,463],"Comparativa<em>)</em>.":[449],"<em>1:":[450],"Non-Equal-Gradable":[451,462],"(</em>Gradativa":[452],"com":[453],"Predile\u00e7\u00e3o<em>)</em>.":[454],"<em>2:":[455],"Equative</em>":[456],"<em>(</em>Equitativa<em>).</em>":[457],"<em>3:":[458],"Superlative":[459],"(</em>Superlativa<em>).</em>":[460],"<em>4:":[461],"Gradativa<em>).</em>":[464],"If":[465],"you":[466,547,559],"use":[467],"data,":[469],"please":[470],"cite":[471],"our":[472],"paper":[473,557,568],"as":[474,610,639,664],"follows:":[475],"<em>\"Daniel":[476],"Kansaon,":[477],"Michele":[478],"A.":[479],"Brand\u00e3o,":[480],"Julio":[481],"C.":[482],"S.":[483],"Reis,":[484],"Matheus":[485],"Barbosa,Breno":[486],"Matos,":[487],"Fabr\u00edcio":[489],"Benevenuto.":[490],"2020.":[491],"Mining":[492],"Comparative":[494],"Sentences":[495],"Online":[497],"Reviews.":[498],"Symposium":[501],"Multimedia":[503],"(WebMedia":[507],"\u201920),":[508],"November":[509],"30-December":[510],"4,":[511],"2020,":[512],"S\u00e3o":[513],"Lu\u00eds,":[514],"Brazil.":[515],"ACM,":[516],"New":[517],"York,":[518],"NY,":[519],"USA,":[520],"8":[521],"pages.":[522],"https://doi.org/10.1145/3428658.3431081\"</em>":[523],"--------------":[524],"<strong>Plus":[525],"We":[527],"raw":[530],"available":[532],"allow":[537],"future":[538],"test":[541],"pre-processing":[543,563],"steps.":[544],"Then,":[545],"if":[546],"want":[548],"obtain":[550],"exact":[552],"above,":[558],"must":[560],"reproduce":[561],"step":[564],"described":[565],"(<em>Figure":[569],"2</em>).":[570],"each":[572],"than":[576,655],"dataset:":[581],"You":[582],"need":[583],"extract":[585],"before":[588],"after":[592],"keyword,":[595],"existing":[604],"value":[605],"\u201c<em>type</em>\u201d":[608],"label;":[612],"original":[614],"be":[617,636],"divided":[618],"into":[619],"<em>n</em>":[620],"(<em>n</em>)":[623],"number":[626],"keywords":[628],"sentence;":[631],"stopwords":[633,660],"should":[634],"accounted":[637],"part":[640,665],"range":[643],"(<em>3":[644],"words</em>);":[645],"Note":[646],"that:":[647],"processed":[650],"have":[653],"six":[656],"because":[658],"counted":[663],"range.":[668]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
