{"id":"https://openalex.org/W6907806358","doi":"https://doi.org/10.25384/sage.21186778","title":"sj-docx-4-orm-10.1177_10944281221124947 - Supplemental material for Advancing Reproducibility and Accountability of Unsupervised Machine Learning in Text Mining: Importance of Transparency in Reporting Preprocessing and Algorithm Selection","display_name":"sj-docx-4-orm-10.1177_10944281221124947 - Supplemental material for Advancing Reproducibility and Accountability of Unsupervised Machine Learning in Text Mining: Importance of Transparency in Reporting Preprocessing and Algorithm Selection","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W6907806358","doi":"https://doi.org/10.25384/sage.21186778"},"language":"en","primary_location":{"id":"pmh:oai:figshare.com:article/21186778","doi":null,"is_oa":true,"landing_page_url":"https://figshare.com/articles/journal_contribution/sj-docx-4-orm-10_1177_10944281221124947_-_Supplemental_material_for_Advancing_Reproducibility_and_Accountability_of_Unsupervised_Machine_Learning_in_Text_Mining_Importance_of_Transparency_in_Reporting_Preprocessing_and_Algorithm_Selection/21186778","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"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":"","raw_type":"Text"},"volume":null,"type":"supplementary-materials","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://figshare.com/articles/journal_contribution/sj-docx-4-orm-10_1177_10944281221124947_-_Supplemental_material_for_Advancing_Reproducibility_and_Accountability_of_Unsupervised_Machine_Learning_in_Text_Mining_Importance_of_Transparency_in_Reporting_Preprocessing_and_Algorithm_Selection/21186778","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072098154","display_name":"Laura Valtonen","orcid":"https://orcid.org/0000-0003-4387-1239","observed_orcids":["https://orcid.org/0000-0003-4387-1239"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Valtonen, L.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"M\u00e4kinen, Saku J.","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"M\u00e4kinen, Saku J.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5014651029","display_name":"Johanna Kirjavainen","orcid":"https://orcid.org/0000-0003-3598-8701","observed_orcids":["https://orcid.org/0000-0003-3598-8701"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kirjavainen, Johanna","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":true,"primary_topic":{"id":"https://openalex.org/T13910","display_name":"Computational and Text Analysis Methods","score":0.9994999766349792,"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":0.9994999766349792,"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/T12880","display_name":"Qualitative Research Methods and Applications","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/3304","display_name":"Education"},"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":0.0,"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/reproducibility","display_name":"reproducibility","score":0.8410000205039978},{"id":"https://openalex.org/keywords/accountability","display_name":"accountability","score":0.6690000295639038},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"unsupervised learning","score":0.9890000224113464},{"id":"https://openalex.org/keywords/text-mining","display_name":"text mining","score":0.996999979019165},{"id":"https://openalex.org/keywords/transparency","display_name":"transparency","score":0.4779999852180481},{"id":"https://openalex.org/keywords/reporting-practices","display_name":"reporting practices","score":0.6660000085830688},{"id":"https://openalex.org/keywords/data-preprocessing","display_name":"data preprocessing","score":0.6159999966621399},{"id":"https://openalex.org/keywords/algorithm-selection","display_name":"algorithm selection","score":0.8899999856948853},{"id":"https://openalex.org/keywords/reporting-guidelines","display_name":"reporting guidelines","score":0.4320000112056732}],"concepts":[{"id":"https://openalex.org/C2780233690","wikidata":"https://www.wikidata.org/wiki/Q535347","display_name":"Transparency (behavior)","level":2,"score":0.8610000014305115},{"id":"https://openalex.org/C2776007630","wikidata":"https://www.wikidata.org/wiki/Q2798912","display_name":"Accountability","level":2,"score":0.7537000179290771},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.7488999962806702},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6807000041007996},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6561999917030334},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.64410001039505},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5734000205993652},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.49900001287460327},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.4790000021457672},{"id":"https://openalex.org/C9893847","wikidata":"https://www.wikidata.org/wiki/Q1425625","display_name":"Reproducibility","level":2,"score":0.40220001339912415},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.39070001244544983},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.31380000710487366}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:figshare.com:article/21186778","doi":null,"is_oa":true,"landing_page_url":"https://figshare.com/articles/journal_contribution/sj-docx-4-orm-10_1177_10944281221124947_-_Supplemental_material_for_Advancing_Reproducibility_and_Accountability_of_Unsupervised_Machine_Learning_in_Text_Mining_Importance_of_Transparency_in_Reporting_Preprocessing_and_Algorithm_Selection/21186778","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"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":"","raw_type":"Text"},{"id":"doi:10.25384/sage.21186778","doi":"https://doi.org/10.25384/sage.21186778","is_oa":true,"landing_page_url":"https://doi.org/10.25384/sage.21186778","pdf_url":null,"source":{"id":"https://openalex.org/S7407052682","display_name":"Sage Journals Data","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"},{"id":"doi:10.25384/sage.21186778.v1","doi":"https://doi.org/10.25384/sage.21186778.v1","is_oa":true,"landing_page_url":"https://doi.org/10.25384/sage.21186778.v1","pdf_url":null,"source":{"id":"https://openalex.org/S7407052682","display_name":"Sage Journals Data","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/21186778","doi":null,"is_oa":true,"landing_page_url":"https://figshare.com/articles/journal_contribution/sj-docx-4-orm-10_1177_10944281221124947_-_Supplemental_material_for_Advancing_Reproducibility_and_Accountability_of_Unsupervised_Machine_Learning_in_Text_Mining_Importance_of_Transparency_in_Reporting_Preprocessing_and_Algorithm_Selection/21186778","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"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":"","raw_type":"Text"},"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/W4296711326","https://openalex.org/W2767606706","https://openalex.org/W7214074447","https://openalex.org/W2531372442","https://openalex.org/W3109416014","https://openalex.org/W7172212186","https://openalex.org/W4205249749","https://openalex.org/W4400511359","https://openalex.org/W2765124601","https://openalex.org/W6996998382"],"abstract_inverted_index":{"Supplemental":[0],"material,":[1],"sj-docx-4-orm-10.1177_10944281221124947":[2],"for":[3],"Advancing":[4],"Reproducibility":[5],"and":[6,21,30],"Accountability":[7],"of":[8,16],"Unsupervised":[9],"Machine":[10],"Learning":[11],"in":[12,18,33],"Text":[13],"Mining:":[14],"Importance":[15],"Transparency":[17],"Reporting":[19],"Preprocessing":[20],"Algorithm":[22],"Selection":[23],"by":[24],"L.":[25],"Valtonen,":[26],"Saku":[27],"J.":[28],"M\u00e4kinen":[29],"Johanna":[31],"Kirjavainen":[32],"Organizational":[34],"Research":[35],"Methods":[36]},"counts_by_year":[],"updated_date":"2026-10-14T16:39:01.820549","created_date":"2025-10-10T00:00:00"}
