{"id":"https://openalex.org/W3204737101","doi":"https://doi.org/10.21248/jlcl.35.2022.226","title":"Small Data Problems in Political Research: A Critical Replication Study","display_name":"Small Data Problems in Political Research: A Critical Replication Study","publication_year":2022,"publication_date":"2022-07-01","ids":{"openalex":"https://openalex.org/W3204737101","doi":"https://doi.org/10.21248/jlcl.35.2022.226","mag":"3204737101"},"language":"en","primary_location":{"id":"doi:10.21248/jlcl.35.2022.226","doi":"https://doi.org/10.21248/jlcl.35.2022.226","is_oa":true,"landing_page_url":"https://doi.org/10.21248/jlcl.35.2022.226","pdf_url":"https://jlcl.org/article/download/226/224","source":{"id":"https://openalex.org/S4393913653","display_name":"LDV-Forum/Journal for language technology and computational linguistics","issn_l":"0175-1336","issn":["0175-1336","2190-6858"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["anvur-scientific","jufo-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal for Language Technology and Computational Linguistics","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://jlcl.org/article/download/226/224","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077770673","display_name":"H. de Vos","orcid":"https://orcid.org/0000-0002-0706-7027","observed_orcids":["https://orcid.org/0000-0002-0706-7027"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hugo De Vos","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-0706-7027","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5027124439","display_name":"Suzan Verberne","orcid":"https://orcid.org/0000-0002-9609-9505","observed_orcids":["https://orcid.org/0000-0002-9609-9505"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Suzan Verberne","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-9609-9505","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1309,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.84318592,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":93},"biblio":{"volume":"35","issue":"2","first_page":"1","last_page":"14"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13910","display_name":"Computational and Text Analysis Methods","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13910","display_name":"Computational and Text Analysis Methods","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.00039999998989515007,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.00019999999494757503,"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/small-data","display_name":"small data","score":0.6650000214576721},{"id":"https://openalex.org/keywords/text-classification","display_name":"text classification","score":0.8619999885559082},{"id":"https://openalex.org/keywords/organizational-reputation","display_name":"organizational reputation","score":0.7609999775886536},{"id":"https://openalex.org/keywords/tweets","display_name":"tweets","score":0.765999972820282},{"id":"https://openalex.org/keywords/machine-learning","display_name":"machine learning","score":0.6499999761581421},{"id":"https://openalex.org/keywords/data-sparsity","display_name":"data sparsity","score":0.7549999952316284},{"id":"https://openalex.org/keywords/text-preprocessing","display_name":"text preprocessing","score":0.722000002861023},{"id":"https://openalex.org/keywords/model-stability","display_name":"model stability","score":0.8019999861717224},{"id":"https://openalex.org/keywords/replication-study","display_name":"replication study","score":0.7459999918937683},{"id":"https://openalex.org/keywords/public-administration","display_name":"public administration","score":0.6650000214576721},{"id":"https://openalex.org/keywords/social-media","display_name":"social media","score":0.4569999873638153}],"concepts":[{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.8386596441268921},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6871975660324097},{"id":"https://openalex.org/C48798503","wikidata":"https://www.wikidata.org/wiki/Q877546","display_name":"Reputation","level":2,"score":0.648038387298584},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.620876669883728},{"id":"https://openalex.org/C12590798","wikidata":"https://www.wikidata.org/wiki/Q3933199","display_name":"Replication (statistics)","level":2,"score":0.5611403584480286},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.5377734899520874},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5286294221878052},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5142300128936768},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.47066983580589294},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44471266865730286},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43451637029647827},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.43345189094543457},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3803284466266632},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.372330904006958},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.15528199076652527},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11669576168060303},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.09002667665481567},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.08256736397743225},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":7,"locations":[{"id":"doi:10.21248/jlcl.35.2022.226","doi":"https://doi.org/10.21248/jlcl.35.2022.226","is_oa":true,"landing_page_url":"https://doi.org/10.21248/jlcl.35.2022.226","pdf_url":"https://jlcl.org/article/download/226/224","source":{"id":"https://openalex.org/S4393913653","display_name":"LDV-Forum/Journal for language technology and computational linguistics","issn_l":"0175-1336","issn":["0175-1336","2190-6858"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["anvur-scientific","jufo-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal for Language Technology and Computational Linguistics","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2109.12911","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2109.12911","pdf_url":"https://arxiv.org/pdf/2109.12911","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:alma.31UKB_LEU:9940749162102711","doi":null,"is_oa":true,"landing_page_url":"https://scholarlypublications.universiteitleiden.nl/handle/1887/3249376","pdf_url":"https://scholarlypublications.universiteitleiden.nl/download/1887/3249376/1?col=81522199450002711&col=81522199650002711","source":{"id":"https://openalex.org/S4306400850","display_name":"Leiden Repository (Leiden University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I121797337","host_organization_name":"Leiden University","host_organization_lineage":["https://openalex.org/I121797337"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"1st Workshop on computational linguistics for political text analysis (CPSS-2021)","raw_type":"http://purl.org/coar/resource_type/c_6501"},{"id":"pmh:oai:scholarlypublications.universiteitleiden.nl:item_3249376","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2109.12911","pdf_url":null,"source":{"id":"https://openalex.org/S4306400850","display_name":"Leiden Repository (Leiden University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I121797337","host_organization_name":"Leiden University","host_organization_lineage":["https://openalex.org/I121797337"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"1st Workshop on computational linguistics for political text analysis (CPSS-2021)","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:publikationen.ub.uni-frankfurt.de:83117","doi":null,"is_oa":true,"landing_page_url":"https://nbn-resolving.org/urn:nbn:de:hebis:30:3-831178","pdf_url":null,"source":{"id":"https://openalex.org/S4306400432","display_name":"Publication Server of Goethe University Frankfurt am Main (Goethe University Frankfurt)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I114090438","host_organization_name":"Goethe University Frankfurt","host_organization_lineage":["https://openalex.org/I114090438"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},{"id":"pmh:ul:oai:scholarlypublications.universiteitleiden.nl:item_3249376","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/1887/3249376","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"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":"1st Workshop on computational linguistics for political text analysis (CPSS-2021)","raw_type":"info:eu-repo/semantics/article"},{"id":"doi:10.48550/arxiv.2109.12911","doi":"https://doi.org/10.48550/arxiv.2109.12911","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2109.12911","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.21248/jlcl.35.2022.226","doi":"https://doi.org/10.21248/jlcl.35.2022.226","is_oa":true,"landing_page_url":"https://doi.org/10.21248/jlcl.35.2022.226","pdf_url":"https://jlcl.org/article/download/226/224","source":{"id":"https://openalex.org/S4393913653","display_name":"LDV-Forum/Journal for language technology and computational linguistics","issn_l":"0175-1336","issn":["0175-1336","2190-6858"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["anvur-scientific","jufo-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal for Language Technology and Computational Linguistics","raw_type":"journal-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3204737101.pdf","grobid_xml":"https://content.openalex.org/works/W3204737101.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W1517590677","https://openalex.org/W2095655043","https://openalex.org/W2103206127","https://openalex.org/W2250243742","https://openalex.org/W2295598076","https://openalex.org/W2338010732","https://openalex.org/W2342934368","https://openalex.org/W2759117937","https://openalex.org/W2803497048","https://openalex.org/W2806901780","https://openalex.org/W2895553377","https://openalex.org/W2896457183","https://openalex.org/W2900956204","https://openalex.org/W2916719435","https://openalex.org/W2963297649","https://openalex.org/W2999309192","https://openalex.org/W3102476541","https://openalex.org/W3139394221","https://openalex.org/W3140486758","https://openalex.org/W4401951602"],"related_works":["https://openalex.org/W4221054978","https://openalex.org/W4387166054","https://openalex.org/W7167755781","https://openalex.org/W7131358476","https://openalex.org/W3125733373","https://openalex.org/W7108071533","https://openalex.org/W2397760338","https://openalex.org/W6990261719","https://openalex.org/W2624972956","https://openalex.org/W7204881424"],"abstract_inverted_index":{"In":[0],"an":[1],"often-cited":[2],"2019":[3],"paper":[4,32,54],"on":[5,46,58,70,160],"the":[6,47,52,74,82,89,93,103,108,112,119,124,139,142,148,157,169],"use":[7,48],"of":[8,30,49,64,76,121,141,156,172],"machine":[9,50],"learning":[10],"in":[11,79,102,123,135],"political":[12],"research,":[13],"Anastasopoulos":[14],"&":[15],"Whitford":[16],"(A&W)":[17],"propose":[18],"a":[19,36,62,186],"text":[20],"classification":[21,94,171],"method":[22],"for":[23,40,190],"tweets":[24,175],"related":[25],"to":[26,34,38,81,96,100,114],"organizational":[27,173],"reputation.The":[28],"aim":[29],"their":[31],"was":[33],"provide":[35],"'guide":[37],"practice'":[39],"public":[41],"administration":[42],"scholars":[43],"and":[44,67,73,184,192],"practitioners":[45],"learning.In":[51],"current":[53],"we":[55,137,145,163],"follow":[56],"up":[57],"that":[59,87,147,165],"work":[60],"with":[61,118],"replication":[63],"A&W's":[65,166],"experiments":[66,134],"additional":[68,133],"analyses":[69],"model":[71,95],"stability":[72],"effects":[75],"preprocessing,":[77],"both":[78],"relation":[80],"small":[83,90,149],"data":[84,91,113,125,150,188],"size.We":[85],"show":[86,146],"(1)":[88],"causes":[92,111],"be":[97,115,182],"highly":[98],"sensitive":[99],"variations":[101],"random":[104],"train-test":[105],"split":[106],"(2)":[107],"applied":[109],"preprocessing":[110,143,158],"extremely":[116],"sparse,":[117],"majority":[120],"items":[122],"having":[126],"at":[127],"most":[128],"two":[129],"non-zero":[130],"lexical":[131],"features.With":[132],"which":[136],"vary":[138],"steps":[140],"pipeline,":[144],"size":[151],"keeps":[152],"causing":[153],"problems,":[154],"irrespective":[155],"choices.Based":[159],"our":[161],"findings,":[162],"argue":[164],"conclusions":[167],"regarding":[168],"automated":[170],"reputation":[174],"-either":[176],"substantive":[177],"or":[178],"methodological":[179],"-can":[180],"not":[181],"maintained":[183],"require":[185],"larger":[187],"set":[189],"training":[191],"more":[193],"careful":[194],"validation.":[195]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2021-10-11T00:00:00"}