{"id":"https://openalex.org/W2767606706","doi":"https://doi.org/10.7910/dvn/xrr0hm","title":"Replication Data for: Text Preprocessing For Unsupervised Learning: Why It Matters, When It Misleads, And What To Do About It","display_name":"Replication Data for: Text Preprocessing For Unsupervised Learning: Why It Matters, When It Misleads, And What To Do About It","publication_year":2017,"publication_date":"2017-09-27","ids":{"openalex":"https://openalex.org/W2767606706","doi":"https://doi.org/10.7910/dvn/xrr0hm","mag":"2767606706"},"language":"en","primary_location":{"id":"doi:10.7910/dvn/xrr0hm","doi":"https://doi.org/10.7910/dvn/xrr0hm","is_oa":true,"landing_page_url":"https://doi.org/10.7910/dvn/xrr0hm","pdf_url":null,"source":{"id":"https://openalex.org/S4377196806","display_name":"Harvard Dataverse","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I136199984","host_organization_name":"Harvard University","host_organization_lineage":["https://openalex.org/I136199984"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"volume":null,"type":"dataset","is_traditional":false,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.7910/dvn/xrr0hm","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111212127","display_name":"Matthew Spirling Denny","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Denny, Matthew","raw_affiliation_strings":["Penn State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Penn State University","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"last","author":{"id":null,"display_name":"Spirling, Arthur","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Spirling, Arthur","raw_affiliation_strings":["New York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5111212127"],"corresponding_institution_ids":["https://openalex.org/I130769515"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"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/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":0.0003000000142492354,"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":0.00019999999494757503,"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/text-preprocessing","display_name":"text preprocessing","score":1.0},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"unsupervised learning","score":0.968999981880188},{"id":"https://openalex.org/keywords/text-representation","display_name":"text representation","score":0.36399999260902405},{"id":"https://openalex.org/keywords/document-clustering","display_name":"document clustering","score":0.37599998712539673}],"concepts":[{"id":"https://openalex.org/C12590798","wikidata":"https://www.wikidata.org/wiki/Q3933199","display_name":"Replication (statistics)","level":2,"score":0.8248189687728882},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6010187864303589},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5783314108848572},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4133342504501343},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3413427770137787},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.193587064743042},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18898829817771912}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.7910/dvn/xrr0hm","doi":"https://doi.org/10.7910/dvn/xrr0hm","is_oa":true,"landing_page_url":"https://doi.org/10.7910/dvn/xrr0hm","pdf_url":null,"source":{"id":"https://openalex.org/S4377196806","display_name":"Harvard Dataverse","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I136199984","host_organization_name":"Harvard University","host_organization_lineage":["https://openalex.org/I136199984"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"}],"best_oa_location":{"id":"doi:10.7910/dvn/xrr0hm","doi":"https://doi.org/10.7910/dvn/xrr0hm","is_oa":true,"landing_page_url":"https://doi.org/10.7910/dvn/xrr0hm","pdf_url":null,"source":{"id":"https://openalex.org/S4377196806","display_name":"Harvard Dataverse","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I136199984","host_organization_name":"Harvard University","host_organization_lineage":["https://openalex.org/I136199984"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3125733373","https://openalex.org/W2531372442","https://openalex.org/W4398693689","https://openalex.org/W6921221301","https://openalex.org/W60680076","https://openalex.org/W4408033692","https://openalex.org/W7024876674","https://openalex.org/W2765124601","https://openalex.org/W7093300720","https://openalex.org/W4293163956"],"abstract_inverted_index":{"Data":[0],"and":[1],"code":[2],"to":[3],"replicate":[4],"findings":[5],"in":[6,25],"\"Text":[7],"Preprocessing":[8],"For":[9],"Unsupervised":[10],"Learning:":[11],"Why":[12],"It":[13,16],"Matters,":[14],"When":[15],"Misleads,":[17],"And":[18],"What":[19],"To":[20],"Do":[21],"About":[22],"It,\"":[23],"forthcoming":[24],"Political":[26],"Analysis.":[27]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2017-11-17T00:00:00"}