{"id":"https://openalex.org/W4304755972","doi":"https://doi.org/10.1145/3562007.3562028","title":"Batch Active Learning for Text Classification and Sentiment Analysis","display_name":"Batch Active Learning for Text Classification and Sentiment Analysis","publication_year":2022,"publication_date":"2022-08-26","ids":{"openalex":"https://openalex.org/W4304755972","doi":"https://doi.org/10.1145/3562007.3562028"},"language":"en","primary_location":{"id":"doi:10.1145/3562007.3562028","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3562007.3562028","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 3rd International Conference on Control, Robotics and Intelligent System","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/A5004038926","display_name":"Marko Sahan","orcid":null},"institutions":[{"id":"https://openalex.org/I44504214","display_name":"Czech Technical University in Prague","ror":"https://ror.org/03kqpb082","country_code":"CZ","type":"education","lineage":["https://openalex.org/I44504214"]},{"id":"https://openalex.org/I151321946","display_name":"Center for Economic Research and Graduate Education \u2013 Economics Institute","ror":"https://ror.org/0362ttz08","country_code":"CZ","type":"education","lineage":["https://openalex.org/I151321946"]}],"countries":["CZ"],"is_corresponding":true,"raw_author_name":"Marko Sahan","raw_affiliation_strings":["Dept. of Computer Science, FEE, CTU in Prague, Czech Republic"],"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science, FEE, CTU in Prague, Czech Republic","institution_ids":["https://openalex.org/I151321946","https://openalex.org/I44504214"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037930366","display_name":"V\u00e1clav \u0160m\u00eddl","orcid":"https://orcid.org/0000-0003-3027-6174"},"institutions":[{"id":"https://openalex.org/I151321946","display_name":"Center for Economic Research and Graduate Education \u2013 Economics Institute","ror":"https://ror.org/0362ttz08","country_code":"CZ","type":"education","lineage":["https://openalex.org/I151321946"]},{"id":"https://openalex.org/I44504214","display_name":"Czech Technical University in Prague","ror":"https://ror.org/03kqpb082","country_code":"CZ","type":"education","lineage":["https://openalex.org/I44504214"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Vaclav Smidl","raw_affiliation_strings":["Dept. of Computer Science, FEE, CTU in Prague, Czech Republic"],"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science, FEE, CTU in Prague, Czech Republic","institution_ids":["https://openalex.org/I151321946","https://openalex.org/I44504214"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088745846","display_name":"Radek Ma\u0159\u00edk","orcid":"https://orcid.org/0000-0003-2000-6541"},"institutions":[{"id":"https://openalex.org/I44504214","display_name":"Czech Technical University in Prague","ror":"https://ror.org/03kqpb082","country_code":"CZ","type":"education","lineage":["https://openalex.org/I44504214"]},{"id":"https://openalex.org/I151321946","display_name":"Center for Economic Research and Graduate Education \u2013 Economics Institute","ror":"https://ror.org/0362ttz08","country_code":"CZ","type":"education","lineage":["https://openalex.org/I151321946"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Radek Marik","raw_affiliation_strings":["Dept. of Telecommunication Engineering, FEE, CTU in Prague, Czech Republic"],"affiliations":[{"raw_affiliation_string":"Dept. of Telecommunication Engineering, FEE, CTU in Prague, Czech Republic","institution_ids":["https://openalex.org/I151321946","https://openalex.org/I44504214"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5004038926"],"corresponding_institution_ids":["https://openalex.org/I151321946","https://openalex.org/I44504214"],"apc_list":null,"apc_paid":null,"fwci":0.6628,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.74319482,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"111","last_page":"116"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9994000196456909,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9994000196456909,"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":0.9987999796867371,"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":0.9980999827384949,"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/computer-science","display_name":"Computer science","score":0.8169864416122437},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6511217355728149},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.632846474647522},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5700592994689941},{"id":"https://openalex.org/keywords/active-learning","display_name":"Active learning (machine learning)","score":0.5352647304534912},{"id":"https://openalex.org/keywords/batch-processing","display_name":"Batch processing","score":0.4938889145851135},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.48208552598953247},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.42298638820648193},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.41434401273727417},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3691529631614685},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09849315881729126}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8169864416122437},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6511217355728149},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.632846474647522},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5700592994689941},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.5352647304534912},{"id":"https://openalex.org/C172658912","wikidata":"https://www.wikidata.org/wiki/Q661613","display_name":"Batch processing","level":2,"score":0.4938889145851135},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.48208552598953247},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.42298638820648193},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.41434401273727417},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3691529631614685},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09849315881729126},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3562007.3562028","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3562007.3562028","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 3rd International Conference on Control, Robotics and Intelligent System","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6499999761581421,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W2489487449","https://openalex.org/W2997546679","https://openalex.org/W3100880133"],"related_works":["https://openalex.org/W3208326136","https://openalex.org/W3025582806","https://openalex.org/W2597787948","https://openalex.org/W2954428433","https://openalex.org/W3196155444","https://openalex.org/W4366320140","https://openalex.org/W3208584567","https://openalex.org/W3136151706","https://openalex.org/W4320063314","https://openalex.org/W3047894882"],"abstract_inverted_index":{"Supervised":[0],"learning":[1,49,76,85,192,219,290],"of":[2,14,63,71,80,90,102,137,163,184,206,212,216,222,227,241,269,287],"classifiers":[3],"for":[4,59,92,294],"text":[5,146],"classification":[6,279],"and":[7,132,234,277],"sentiment":[8,278],"analysis":[9],"relies":[10],"on":[11,144,199,245],"the":[12,33,42,61,64,68,72,126,185,195,204,210,228,288],"availability":[13],"labels":[15,31],"that":[16,53,285],"may":[17],"be":[18],"either":[19],"difficult":[20],"or":[21,297],"expensive":[22],"to":[23,29,32,189],"obtain.":[24],"A":[25],"standard":[26],"procedure":[27],"is":[28,50,77,96,151,193],"add":[30],"training":[34],"dataset":[35],"sequentially":[36],"by":[37,86,124,272],"querying":[38],"an":[39,217],"annotator":[40],"until":[41],"model":[43],"reaches":[44],"a":[45,51,78,81,88,120,141],"satisfactory":[46],"performance.":[47,180],"Active":[48],"process":[52],"optimizes":[54],"unlabeled":[55],"data":[56],"records":[57],"selection":[58,236],"which":[60],"knowledge":[62],"label":[65],"would":[66],"bring":[67],"highest":[69],"discriminability":[70],"dataset.":[73],"Batch":[74],"active":[75,84,191,218,289],"generalization":[79],"single":[82],"instance":[83],"selecting":[87],"batch":[89,110,112,190,235],"documents":[91,250],"labeling.":[93],"This":[94],"task":[95],"much":[97],"more":[98],"demanding":[99],"because":[100],"plenty":[101],"different":[103,145],"factors":[104,215,224,291],"come":[105],"into":[106,129],"consideration":[107],"(i.":[108],"e.":[109],"size,":[111],"evaluation,":[113],"etc.).":[114],"In":[115],"this":[116,207],"paper,":[117],"we":[118,283],"provide":[119],"large":[121],"scale":[122],"study":[123],"decomposing":[125],"existing":[127],"algorithms":[128],"building":[130],"blocks":[131,139],"systematically":[133],"comparing":[134,209],"meaningful":[135],"combinations":[136,165,240],"these":[138,223,242],"with":[140,169,178,249],"subsequent":[142],"evaluation":[143],"datasets.":[147,201],"While":[148],"each":[149,286],"block":[150],"known":[152],"(warm":[153],"start":[154,187],"weights":[155],"initialization,":[156],"Dropout":[157],"MC,":[158],"entropy":[159],"sampling,":[160],"etc.),":[161],"many":[162],"their":[164],"like":[166],"Bayesian":[167],"strategies":[168,198],"agglomerative":[170],"clustering":[171],"are":[172,243],"first":[173],"proposed":[174],"in":[175],"our":[176,182],"paper":[177],"excellent":[179],"Particularly,":[181],"extension":[183],"warm":[186],"method":[188],"among":[194],"top":[196],"performing":[197],"all":[200],"We":[202],"studied":[203],"effect":[205],"proposal":[208],"outcomes":[211],"varying":[213],"distinct":[214],"algorithm.":[220],"Some":[221],"include":[225],"initialization":[226],"algorithm,":[229],"uncertainty":[230],"representation,":[231],"acquisition":[232],"function,":[233],"strategy.":[237],"Further,":[238],"various":[239],"tested":[244],"selected":[246],"NLP":[247],"problems":[248],"encoded":[251],"using":[252],"RoBERTa":[253],"embeddings.":[254],"Datasets":[255],"cover":[256],"context":[257,274],"integrity":[258],"(Gibberish":[259],"Wackerow),":[260],"fake":[261],"news":[262],"detection":[263],"(Kaggle":[264],"Fake":[265],"News":[266],"Detection),":[267],"categorization":[268],"short":[270],"texts":[271],"emotional":[273],"(Twitter":[275],"Sentiment140),":[276],"(Amazon":[280],"Reviews).":[281],"Ultimately,":[282],"show":[284],"has":[292],"advantages":[293],"certain":[295],"datasets":[296],"experimental":[298],"settings.":[299]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}