{"id":"https://openalex.org/W2533513334","doi":"https://doi.org/10.1145/2983323.2983721","title":"Effective Document Labeling with Very Few Seed Words","display_name":"Effective Document Labeling with Very Few Seed Words","publication_year":2016,"publication_date":"2016-10-24","ids":{"openalex":"https://openalex.org/W2533513334","doi":"https://doi.org/10.1145/2983323.2983721","mag":"2533513334"},"language":"en","primary_location":{"id":"doi:10.1145/2983323.2983721","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2983323.2983721","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM International on Conference on Information and Knowledge Management","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/A5100734069","display_name":"Chenliang Li","orcid":null},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chenliang Li","raw_affiliation_strings":["Wuhan University, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016171393","display_name":"Jian Xing","orcid":"https://orcid.org/0000-0001-7686-353X"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Xing","raw_affiliation_strings":["Wuhan University, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100618738","display_name":"Aixin Sun","orcid":"https://orcid.org/0000-0003-0764-4258"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Aixin Sun","raw_affiliation_strings":["Nanyang Technological University, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008327536","display_name":"Zongyang Ma","orcid":"https://orcid.org/0009-0003-1980-9379"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zongyang Ma","raw_affiliation_strings":["Nanyang Technological University, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100734069"],"corresponding_institution_ids":["https://openalex.org/I37461747"],"apc_list":null,"apc_paid":null,"fwci":7.7113,"has_fulltext":false,"cited_by_count":61,"citation_normalized_percentile":{"value":0.97384091,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"85","last_page":"94"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9998999834060669,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9998999834060669,"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":0.9994999766349792,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9950000047683716,"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":0.773781418800354},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6340566277503967},{"id":"https://openalex.org/keywords/novelty","display_name":"Novelty","score":0.6303787231445312},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5894361734390259},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5690775513648987},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5407261252403259},{"id":"https://openalex.org/keywords/meaning","display_name":"Meaning (existential)","score":0.5125515460968018},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5086272954940796},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4879602789878845},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.4789438843727112},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11675497889518738}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.773781418800354},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6340566277503967},{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.6303787231445312},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5894361734390259},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5690775513648987},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5407261252403259},{"id":"https://openalex.org/C2780876879","wikidata":"https://www.wikidata.org/wiki/Q3054749","display_name":"Meaning (existential)","level":2,"score":0.5125515460968018},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5086272954940796},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4879602789878845},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.4789438843727112},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11675497889518738},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C27206212","wikidata":"https://www.wikidata.org/wiki/Q34178","display_name":"Theology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2983323.2983721","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2983323.2983721","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM International on Conference on Information and Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5,"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals"}],"awards":[{"id":"https://openalex.org/G1235701029","display_name":null,"funder_award_id":"MOE2014-T2-2-066","funder_id":"https://openalex.org/F4320320751","funder_display_name":"Ministry of Education - Singapore"},{"id":"https://openalex.org/G1931582540","display_name":null,"funder_award_id":"2015CFB337","funder_id":"https://openalex.org/F4320322186","funder_display_name":"Natural Science Foundation of Hubei Province"},{"id":"https://openalex.org/G7050358598","display_name":null,"funder_award_id":"61502344","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320320751","display_name":"Ministry of Education - Singapore","ror":"https://ror.org/01kcva023"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322186","display_name":"Natural Science Foundation of Hubei Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W265767496","https://openalex.org/W658020064","https://openalex.org/W746911252","https://openalex.org/W1506246224","https://openalex.org/W1598801360","https://openalex.org/W1628041482","https://openalex.org/W1880262756","https://openalex.org/W1995866178","https://openalex.org/W2001082470","https://openalex.org/W2092970348","https://openalex.org/W2097089247","https://openalex.org/W2103587173","https://openalex.org/W2107743791","https://openalex.org/W2108281845","https://openalex.org/W2113378307","https://openalex.org/W2120779048","https://openalex.org/W2125327503","https://openalex.org/W2127416213","https://openalex.org/W2128507180","https://openalex.org/W2130339025","https://openalex.org/W2137268161","https://openalex.org/W2145078771","https://openalex.org/W2145494108","https://openalex.org/W2147152072","https://openalex.org/W2152253130","https://openalex.org/W2158085718","https://openalex.org/W2166353350","https://openalex.org/W2171506566","https://openalex.org/W2285986798","https://openalex.org/W2340381866","https://openalex.org/W2950477597","https://openalex.org/W3005822403","https://openalex.org/W4233135949"],"related_works":["https://openalex.org/W2381242807","https://openalex.org/W2751208925","https://openalex.org/W2347541121","https://openalex.org/W4288804799","https://openalex.org/W3089617106","https://openalex.org/W3032237421","https://openalex.org/W2080951048","https://openalex.org/W3011883280","https://openalex.org/W2390346111","https://openalex.org/W3023960764"],"abstract_inverted_index":{"Developing":[0],"text":[1,46,62,211],"classifiers":[2],"often":[3],"requires":[4],"a":[5,23,34,53,66,75,144,148,254,262],"large":[6],"number":[7],"of":[8,37,68,78,88,97,107,150,154,257],"labeled":[9],"documents":[10,17,31,99],"as":[11,44],"training":[12],"examples.":[13],"However,":[14],"manually":[15],"labeling":[16],"is":[18,114,141,157,186,239],"costly":[19],"and":[20,71,110,147,174],"time-consuming.":[21],"Recently,":[22],"few":[24],"methods":[25],"have":[26],"been":[27],"proposed":[28],"to":[29,84,241],"label":[30],"by":[32,163],"using":[33],"small":[35,76],"set":[36,77],"relevant":[38,83],"keywords":[39],"for":[40,59,72,265],"each":[41,73,139],"category,":[42,90,119],"known":[43],"dataless":[45,61,210],"classification.":[47],"In":[48,213],"this":[49],"paper,":[50],"we":[51],"propose":[52],"Seed-Guided":[54],"Topic":[55],"Model":[56],"(named":[57],"STM)":[58],"the":[60,85,89,91,94,98,127,132,155,161,165,171,181,208,227,242],"classification":[63,224],"task.":[64],"Given":[65],"collection":[67],"unlabeled":[69],"documents,":[70],"category":[74,95],"seed":[79,172],"words":[80,173,176],"that":[81,138,158,204,237],"are":[82],"semantic":[86,122,129],"meaning":[87],"STM":[92,103,136,159,205,216,238],"predicts":[93],"labels":[96],"through":[100],"topic":[101],"influence.":[102],"models":[104],"two":[105,199],"kinds":[106],"topics:":[108],"category-topics":[109],"general-topics.":[111,151],"Each":[112],"category-topic":[113,146,195],"associated":[115,142],"with":[116,143,247],"one":[117],"specific":[118],"representing":[120],"its":[121,193],"meaning.":[123],"The":[124],"general-topics":[125],"capture":[126],"global":[128],"information":[130],"underlying":[131],"whole":[133],"document":[134,140,182,185],"collection.":[135,183],"assumes":[137],"single":[145],"mixture":[149],"A":[152,184],"novelty":[153],"model":[156],"learns":[160],"topics":[162],"exploiting":[164],"explicit":[166],"word":[167],"co-occurrence":[168],"patterns":[169],"between":[170],"regular":[175],"(i.e.,":[177],"non-seed":[178],"words)":[179],"in":[180,253],"then":[187],"labeled,":[188],"or":[189,221],"classified,":[190],"based":[191],"on":[192,198],"posterior":[194],"assignment.":[196],"Experiments":[197],"widely":[200],"used":[201],"datasets":[202],"show":[203,236],"consistently":[206],"outperforms":[207],"state-of-the-art":[209,228],"classifiers.":[212],"some":[214],"tasks,":[215],"can":[217,250],"also":[218],"achieve":[219],"comparable":[220],"even":[222],"better":[223],"accuracy":[225],"than":[226],"supervised":[229],"learning":[230],"solutions.":[231],"Our":[232],"experimental":[233],"results":[234],"further":[235],"insensitive":[240],"tuning":[243],"parameters.":[244],"Stable":[245],"performance":[246],"little":[248],"variation":[249],"be":[251],"achieved":[252],"broad":[255],"range":[256],"parameter":[258],"settings,":[259],"making":[260],"it":[261],"desired":[263],"choice":[264],"real":[266],"applications.":[267]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":16},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":8}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}