{"id":"https://openalex.org/W4414560408","doi":"https://doi.org/10.1016/j.visinf.2025.100273","title":"CateSift: An interactive steering approach for classifying large scale text","display_name":"CateSift: An interactive steering approach for classifying large scale text","publication_year":2025,"publication_date":"2025-09-27","ids":{"openalex":"https://openalex.org/W4414560408","doi":"https://doi.org/10.1016/j.visinf.2025.100273"},"language":"en","primary_location":{"id":"doi:10.1016/j.visinf.2025.100273","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.visinf.2025.100273","pdf_url":null,"source":{"id":"https://openalex.org/S2898150413","display_name":"Visual Informatics","issn_l":"2468-502X","issn":["2468-502X","2543-2656"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Visual Informatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1016/j.visinf.2025.100273","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031825962","display_name":"Chundong Wang","orcid":"https://orcid.org/0000-0001-6728-0519"},"institutions":[{"id":"https://openalex.org/I1327237609","display_name":"Ministry of Education of the People's Republic of China","ror":"https://ror.org/01mv9t934","country_code":"CN","type":"government","lineage":["https://openalex.org/I1327237609","https://openalex.org/I4210127390"]},{"id":"https://openalex.org/I136765683","display_name":"Tianjin University of Technology","ror":"https://ror.org/00zbe0w13","country_code":"CN","type":"education","lineage":["https://openalex.org/I136765683"]},{"id":"https://openalex.org/I4210155969","display_name":"Tianjin Metallurgical Vocational Technical College","ror":"https://ror.org/04h9hnm31","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210155969"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chundong Wang","raw_affiliation_strings":["Key Laboratory of Ministry of Education for Computer Vision and System, Tianjin, China","National Engineering Laboratory for Computer Virus Prevention and Control Technology, Tianjin, China","School of Computer Science and Engineering, Tianjin University of Technology, Tianjin, China","Tianjin Public Security Professional College, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Ministry of Education for Computer Vision and System, Tianjin, China","institution_ids":["https://openalex.org/I1327237609"]},{"raw_affiliation_string":"National Engineering Laboratory for Computer Virus Prevention and Control Technology, Tianjin, China","institution_ids":[]},{"raw_affiliation_string":"School of Computer Science and Engineering, Tianjin University of Technology, Tianjin, China","institution_ids":["https://openalex.org/I136765683"]},{"raw_affiliation_string":"Tianjin Public Security Professional College, Tianjin, China","institution_ids":["https://openalex.org/I4210155969"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006602979","display_name":"Yang Tian","orcid":"https://orcid.org/0000-0001-9584-9696"},"institutions":[{"id":"https://openalex.org/I1327237609","display_name":"Ministry of Education of the People's Republic of China","ror":"https://ror.org/01mv9t934","country_code":"CN","type":"government","lineage":["https://openalex.org/I1327237609","https://openalex.org/I4210127390"]},{"id":"https://openalex.org/I136765683","display_name":"Tianjin University of Technology","ror":"https://ror.org/00zbe0w13","country_code":"CN","type":"education","lineage":["https://openalex.org/I136765683"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhan Tian","raw_affiliation_strings":["Key Laboratory of Ministry of Education for Computer Vision and System, Tianjin, China","National Engineering Laboratory for Computer Virus Prevention and Control Technology, Tianjin, China","School of Computer Science and Engineering, Tianjin University of Technology, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Ministry of Education for Computer Vision and System, Tianjin, China","institution_ids":["https://openalex.org/I1327237609"]},{"raw_affiliation_string":"National Engineering Laboratory for Computer Virus Prevention and Control Technology, Tianjin, China","institution_ids":[]},{"raw_affiliation_string":"School of Computer Science and Engineering, Tianjin University of Technology, Tianjin, China","institution_ids":["https://openalex.org/I136765683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115590873","display_name":"Xumeng Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xumeng Wang","raw_affiliation_strings":["DISSec, Nankai University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"DISSec, Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059582793","display_name":"Yixuan Song","orcid":null},"institutions":[{"id":"https://openalex.org/I1327237609","display_name":"Ministry of Education of the People's Republic of China","ror":"https://ror.org/01mv9t934","country_code":"CN","type":"government","lineage":["https://openalex.org/I1327237609","https://openalex.org/I4210127390"]},{"id":"https://openalex.org/I136765683","display_name":"Tianjin University of Technology","ror":"https://ror.org/00zbe0w13","country_code":"CN","type":"education","lineage":["https://openalex.org/I136765683"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yixuan Song","raw_affiliation_strings":["Key Laboratory of Ministry of Education for Computer Vision and System, Tianjin, China","National Engineering Laboratory for Computer Virus Prevention and Control Technology, Tianjin, China","School of Computer Science and Engineering, Tianjin University of Technology, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Ministry of Education for Computer Vision and System, Tianjin, China","institution_ids":["https://openalex.org/I1327237609"]},{"raw_affiliation_string":"National Engineering Laboratory for Computer Virus Prevention and Control Technology, Tianjin, China","institution_ids":[]},{"raw_affiliation_string":"School of Computer Science and Engineering, Tianjin University of Technology, Tianjin, China","institution_ids":["https://openalex.org/I136765683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100392974","display_name":"Haotian Zhang","orcid":"https://orcid.org/0009-0008-0293-337X"},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Haotian Zhang","raw_affiliation_strings":["College of Infection and Immunity, University of Glasgow, University Avenue, Glasgow, Scotland, UK"],"affiliations":[{"raw_affiliation_string":"College of Infection and Immunity, University of Glasgow, University Avenue, Glasgow, Scotland, UK","institution_ids":["https://openalex.org/I7882870"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019090473","display_name":"Yongxin Zhao","orcid":"https://orcid.org/0000-0003-4252-1114"},"institutions":[{"id":"https://openalex.org/I1327237609","display_name":"Ministry of Education of the People's Republic of China","ror":"https://ror.org/01mv9t934","country_code":"CN","type":"government","lineage":["https://openalex.org/I1327237609","https://openalex.org/I4210127390"]},{"id":"https://openalex.org/I136765683","display_name":"Tianjin University of Technology","ror":"https://ror.org/00zbe0w13","country_code":"CN","type":"education","lineage":["https://openalex.org/I136765683"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongxin Zhao","raw_affiliation_strings":["Key Laboratory of Ministry of Education for Computer Vision and System, Tianjin, China","National Engineering Laboratory for Computer Virus Prevention and Control Technology, Tianjin, China","School of Computer Science and Engineering, Tianjin University of Technology, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Ministry of Education for Computer Vision and System, Tianjin, China","institution_ids":["https://openalex.org/I1327237609"]},{"raw_affiliation_string":"National Engineering Laboratory for Computer Virus Prevention and Control Technology, Tianjin, China","institution_ids":[]},{"raw_affiliation_string":"School of Computer Science and Engineering, Tianjin University of Technology, Tianjin, China","institution_ids":["https://openalex.org/I136765683"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5115590873"],"corresponding_institution_ids":["https://openalex.org/I205237279"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1428663,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"10","issue":"1","first_page":"100273","last_page":"100273"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9878000020980835,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9878000020980835,"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":0.9817000031471252,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9761000275611877,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/flexibility","display_name":"Flexibility (engineering)","score":0.526199996471405},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5220999717712402},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.520799994468689},{"id":"https://openalex.org/keywords/multi-label-classification","display_name":"Multi-label classification","score":0.428600013256073},{"id":"https://openalex.org/keywords/document-classification","display_name":"Document classification","score":0.42730000615119934},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.41350001096725464},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.39800000190734863},{"id":"https://openalex.org/keywords/expert-system","display_name":"Expert system","score":0.374099999666214},{"id":"https://openalex.org/keywords/interactive-visualization","display_name":"Interactive visualization","score":0.3677999973297119}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7943000197410583},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.526199996471405},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5220999717712402},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.520799994468689},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5135999917984009},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.47589999437332153},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44429999589920044},{"id":"https://openalex.org/C2776482837","wikidata":"https://www.wikidata.org/wiki/Q3553958","display_name":"Multi-label classification","level":2,"score":0.428600013256073},{"id":"https://openalex.org/C2780479914","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Document classification","level":2,"score":0.42730000615119934},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.41350001096725464},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.39800000190734863},{"id":"https://openalex.org/C58328972","wikidata":"https://www.wikidata.org/wiki/Q184609","display_name":"Expert system","level":2,"score":0.374099999666214},{"id":"https://openalex.org/C64073096","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Interactive visualization","level":3,"score":0.3677999973297119},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.3452000021934509},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.33090001344680786},{"id":"https://openalex.org/C34872919","wikidata":"https://www.wikidata.org/wiki/Q7092302","display_name":"One-class classification","level":3,"score":0.3034999966621399},{"id":"https://openalex.org/C172367668","wikidata":"https://www.wikidata.org/wiki/Q6504956","display_name":"Data visualization","level":3,"score":0.29679998755455017},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.28850001096725464},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.2815000116825104},{"id":"https://openalex.org/C163797641","wikidata":"https://www.wikidata.org/wiki/Q2067937","display_name":"Tree structure","level":3,"score":0.28130000829696655},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.27649998664855957},{"id":"https://openalex.org/C144986985","wikidata":"https://www.wikidata.org/wiki/Q871236","display_name":"Hierarchical database model","level":2,"score":0.27219998836517334},{"id":"https://openalex.org/C110083411","wikidata":"https://www.wikidata.org/wiki/Q1744628","display_name":"Statistical classification","level":2,"score":0.2685000002384186},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.26829999685287476},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.2630999982357025},{"id":"https://openalex.org/C14669888","wikidata":"https://www.wikidata.org/wiki/Q4014850","display_name":"Creative visualization","level":3,"score":0.2621000111103058},{"id":"https://openalex.org/C107327155","wikidata":"https://www.wikidata.org/wiki/Q330268","display_name":"Decision support system","level":2,"score":0.2621000111103058},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2587999999523163},{"id":"https://openalex.org/C204126058","wikidata":"https://www.wikidata.org/wiki/Q48473","display_name":"Library classification","level":2,"score":0.2554999887943268}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.visinf.2025.100273","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.visinf.2025.100273","pdf_url":null,"source":{"id":"https://openalex.org/S2898150413","display_name":"Visual Informatics","issn_l":"2468-502X","issn":["2468-502X","2543-2656"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Visual Informatics","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1016/j.visinf.2025.100273","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.visinf.2025.100273","pdf_url":null,"source":{"id":"https://openalex.org/S2898150413","display_name":"Visual Informatics","issn_l":"2468-502X","issn":["2468-502X","2543-2656"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Visual Informatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1981119726","https://openalex.org/W1990995255","https://openalex.org/W2074930186","https://openalex.org/W2212107515","https://openalex.org/W2512274390","https://openalex.org/W2906330222","https://openalex.org/W2970597249","https://openalex.org/W3005984470","https://openalex.org/W3025713681","https://openalex.org/W3148955003","https://openalex.org/W3153427360","https://openalex.org/W3172642864","https://openalex.org/W3177312484","https://openalex.org/W3202452289","https://openalex.org/W3202567403","https://openalex.org/W3204602149","https://openalex.org/W4244034183","https://openalex.org/W4288089799","https://openalex.org/W4292779060","https://openalex.org/W4313563649","https://openalex.org/W4327919569","https://openalex.org/W4385245566","https://openalex.org/W4388286232","https://openalex.org/W4388776293","https://openalex.org/W4390044592","https://openalex.org/W4390886514","https://openalex.org/W4396833346","https://openalex.org/W4396851234","https://openalex.org/W4402436772","https://openalex.org/W4402450807","https://openalex.org/W4406779522","https://openalex.org/W4412712907"],"related_works":[],"abstract_inverted_index":{"Concept":[0],"management":[1],"for":[2,33,105,185],"large-scale":[3,106,155,186,217],"text":[4],"data":[5],"is":[6,249],"critical":[7],"in":[8,22,99,254],"domains":[9],"such":[10],"as":[11,87,235,237],"healthcare":[12],"informatics,":[13],"digital":[14],"libraries,":[15],"and":[16,25,51,72,101,108,139,181,203,231,256,267,280,286],"news":[17],"classification.":[18,243],"However,":[19],"the":[20,26,40,69,144,152,162,167,177,223,238],"variability":[21],"concept":[23,131],"structures":[24],"diversity":[27],"of":[28,83,154,225,264],"application":[29],"requirements":[30],"pose":[31],"challenges":[32],"existing":[34,226],"automated":[35,227],"methods,":[36],"which":[37,198],"often":[38],"lack":[39],"flexibility":[41],"to":[42,67,76,118,142,160,212,251],"accommodate":[43],"customized":[44],"needs.":[45],"Meanwhile,":[46],"manual":[47,242],"classification":[48,70,78,103,122,145,163,168,184,194,215,259],"remains":[49],"resource-intensive":[50],"inefficient.":[52],"To":[53,150],"address":[54,151],"this":[55,84],"issue,":[56],"we":[57],"propose":[58],"CateSift,":[59],"an":[60,192],"interactive":[61,193,246],"approach":[62,179],"that":[63,96,113,133,176],"integrates":[64,204],"public":[65],"knowledge":[66,75,117,211],"streamline":[68],"process":[71],"incorporates":[73],"expert":[74,116,210],"formulate":[77],"models.":[79],"The":[80,271],"main":[81],"contributions":[82],"work":[85],"are":[86],"follows:":[88],"(1)":[89],"a":[90,129],"visualization":[91],"interface,":[92],"called":[93],"CateSift":[94,125,157,196],",":[95,197],"facilitates":[97,273],"users":[98,127,141,159,253],"constructing":[100],"refining":[102],"models":[104,146,208],"data,":[107,156],"(2)":[109],"A":[110],"prompt-based":[111,205],"model":[112,164,258,275],"can":[114],"integrate":[115],"iteratively":[119],"refine":[120],"hierarchical":[121,130,214,232,269],"structures.":[123],"Specifically,":[124],"provides":[126],"with":[128,136,209,241],"tree":[132,169],"highlights":[134],"concepts":[135],"uncertain":[137],"classifications":[138],"invites":[140],"optimize":[143],"by":[147,165],"injecting":[148],"knowledge.":[149],"issue":[153],"allows":[158],"steer":[161],"adjusting":[166],"or":[170],"annotating":[171],"classifications.":[172],"Case":[173],"studies":[174],"indicate":[175],"proposed":[178],"effectively":[180,221],"efficiently":[182],"supports":[183],"data.":[187],"\u2022":[188,244],"This":[189,219],"study":[190],"presents":[191],"framework,":[195],"employs":[199],"multi-level":[200],"prompt":[201],"templates":[202],"large":[206],"language":[207],"perform":[213],"on":[216],"datasets.":[218],"method":[220],"overcomes":[222],"limitations":[224],"approaches":[228],"regarding":[229],"accuracy":[230],"structure":[233],"flexibility,":[234],"well":[236],"inefficiencies":[239],"associated":[240],"An":[245],"prototype":[247],"system":[248,272],"introduced":[250],"support":[252],"interpreting":[255],"guiding":[257],"outcomes,":[260],"enabling":[261],"efficient":[262],"detection":[263],"potential":[265],"errors":[266],"unstable":[268],"components.":[270],"iterative":[274],"refinement":[276],"through":[277],"user-provided":[278],"corrections":[279],"annotations,":[281],"accommodating":[282],"diverse":[283],"domain-specific":[284],"needs":[285],"further":[287],"decreasing":[288],"user":[289],"effort.":[290]},"counts_by_year":[],"updated_date":"2026-03-12T06:13:28.667946","created_date":"2025-10-10T00:00:00"}
