{"id":"https://openalex.org/W2252208617","doi":"https://doi.org/10.3115/v1/w14-2513","title":"Optimizing Features in Active Machine Learning for Complex Qualitative Content Analysis","display_name":"Optimizing Features in Active Machine Learning for Complex Qualitative Content Analysis","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W2252208617","doi":"https://doi.org/10.3115/v1/w14-2513","mag":"2252208617"},"language":"en","primary_location":{"id":"doi:10.3115/v1/w14-2513","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-2513","pdf_url":"https://aclanthology.org/W14-2513.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACL 2014 Workshop on Language Technologies and Computational Social Science","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/W14-2513.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Jasy Suet Yan Liew","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jasy Suet Yan Liew","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074933621","display_name":"Nancy McCracken","orcid":"https://orcid.org/0000-0002-1267-3443"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nancy McCracken","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086550048","display_name":"Shichun Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shichun Zhou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5007861624","display_name":"Kevin Crowston","orcid":"https://orcid.org/0000-0003-1996-3600"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kevin Crowston","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6916,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.8843441,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"44","last_page":"48"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9991999864578247,"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/T10028","display_name":"Topic Modeling","score":0.9991999864578247,"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/T13910","display_name":"Computational and Text Analysis Methods","score":0.9983999729156494,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9955999851226807,"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":0.8445171117782593},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.6879101395606995},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5906466245651245},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.587907075881958},{"id":"https://openalex.org/keywords/neural-coding","display_name":"Neural coding","score":0.4922262728214264},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.47891461849212646},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.46218904852867126},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4476543664932251},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.4305742681026459},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.33667129278182983},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.1150251030921936}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8445171117782593},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.6879101395606995},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5906466245651245},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.587907075881958},{"id":"https://openalex.org/C77637269","wikidata":"https://www.wikidata.org/wiki/Q7002051","display_name":"Neural coding","level":2,"score":0.4922262728214264},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.47891461849212646},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.46218904852867126},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4476543664932251},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.4305742681026459},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33667129278182983},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.1150251030921936},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3115/v1/w14-2513","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-2513","pdf_url":"https://aclanthology.org/W14-2513.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACL 2014 Workshop on Language Technologies and Computational Social Science","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.650.1757","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.650.1757","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://crowston.syr.edu/sites/crowston.syr.edu/files/9_Paper.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.674.1499","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.674.1499","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://anthology.aclweb.org/W/W14/W14-2513.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.3115/v1/w14-2513","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-2513","pdf_url":"https://aclanthology.org/W14-2513.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACL 2014 Workshop on Language Technologies and Computational Social Science","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.44999998807907104,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2252208617.pdf"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W1556808170","https://openalex.org/W1981740417","https://openalex.org/W2006037840","https://openalex.org/W2010577974","https://openalex.org/W2021255645","https://openalex.org/W2038373421","https://openalex.org/W2095655043","https://openalex.org/W2119732155","https://openalex.org/W2323434001","https://openalex.org/W2565297696","https://openalex.org/W2901457087"],"related_works":["https://openalex.org/W1975289146","https://openalex.org/W2105887828","https://openalex.org/W2122599759","https://openalex.org/W4236520801","https://openalex.org/W2132101312","https://openalex.org/W2078080292","https://openalex.org/W1537234410","https://openalex.org/W3147584709","https://openalex.org/W1995022398","https://openalex.org/W2065031478"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,17,25,119,126,162],"semi-automatic":[3],"approach":[4],"for":[5,50,99,167],"content":[6,121],"analysis":[7,122],"that":[8,77,124,149],"leverages":[9],"machine":[10,36],"learn-ing":[11],"(ML)":[12],"being":[13],"initially":[14],"trained":[15],"on":[16],"small":[18],"set":[19],"of":[20,67,145,165],"hand-coded":[21],"data":[22,75],"to":[23,40,44,63,82,102,109,142,153],"perform":[24],"first":[26],"pass":[27],"in":[28,38,118,175],"coding,":[29],"and":[30,90,130],"then":[31],"have":[32],"human":[33,100],"annotators":[34,101],"cor-rect":[35],"annotations":[37],"order":[39],"produce":[41],"more":[42],"examples":[43,96,174],"retrain":[45],"the":[46,65,68,78,111,176],"existing":[47],"model":[48,71,79,114,159],"incrementally":[49],"better":[51],"performance.":[52],"In":[53],"this":[54],"\u201cactive":[55],"learning":[56],"\u201d":[57],"approach,":[58],"it":[59,150],"is":[60,80,151],"equally":[61],"im-portant":[62],"optimize":[64],"creation":[66],"initial":[69,112,157],"ML":[70,113,158],"given":[72],"less":[73],"training":[74],"so":[76],"able":[81],"capture":[83],"most":[84],"if":[85],"not":[86],"all":[87],"posi-tive":[88,135],"examples,":[89],"filter":[91],"out":[92],"as":[93,97],"many":[94],"negative":[95],"possible":[98,152],"correct.":[103],"This":[104],"paper":[105],"reports":[106],"our":[107],"attempt":[108],"op-timize":[110],"through":[115],"feature":[116],"exploration":[117],"complex":[120],"project":[123],"uses":[125],"multidimensional":[127],"coding":[128],"scheme,":[129],"contains":[131],"codes":[132,139,168],"with":[133,169],"sparse":[134],"examples.":[136],"While":[137],"different":[138,143],"respond":[140],"optimally":[141],"combinations":[144],"fea-tures,":[146],"we":[147],"show":[148],"create":[154],"an":[155],"optimal":[156],"using":[160],"only":[161],"single":[163],"combination":[164],"features":[166],"at":[170],"least":[171],"100":[172],"positive":[173],"gold":[177],"stand-ard":[178],"corpus.":[179],"1":[180]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}